Predicting ball movement from live sports using Open-CV Python & Kalman filter

Today, I’m going to discuss another Computer Vision installment. I’ll use Open CV & Kalman filter to predict a live ball movement of Cricket, one of the most popular sports in the Indian sub-continent, along with the UK & Australia. But before we start a deep dive, why don’t we first watch the demo?

Demo

Isn’t it exciting? Let’s explore it in detail.


Architecture:

Let us understand the flow of events –

The above diagram shows that the application, which uses Open CV, analyzes individual frames. It detects the cricket ball & finally, it tracks every movement by analyzing each frame & then it predicts (pink line) based on the supplied data points.


Python Packages:

Following are the python packages that are necessary to develop this brilliant use case –

pip install opencv-python
pip install numpy
pip install cvzone

CODE:

Let us now understand the code. For this use case, we will only discuss three python scripts. However, we need more than these three. However, we have already discussed them in some of the early posts. Hence, we will skip them here.

  • clsPredictBodyLine.py (The main class that will handle the prediction of Cricket balls in the real-time video feed.)


#####################################################
#### Written By: SATYAKI DE ####
#### Written On: 20-Nov-2022 ####
#### Modified On 30-Nov-2022 ####
#### ####
#### Objective: This is the main calling ####
#### python script that will invoke the ####
#### clsPredictBodyLine class to initiate ####
#### the prediction capability in real-time ####
#### & display the result from a live sports. ####
#####################################################
import cv2
import cvzone
from cvzone.ColorModule import ColorFinder
from clsKalmanFilter import clsKalmanFilter
from clsConfigClient import clsConfigClient as cf
import numpy as np
import math
import ssl
import time
# Bypassing SSL Authentication
try:
_create_unverified_https_context = ssl._create_unverified_context
except AttributeError:
# Legacy python that doesn't verify HTTPS certificates by default
pass
else:
# Handle target environment that doesn't support HTTPS verification
ssl._create_default_https_context = _create_unverified_https_context
# Disbling Warning
def warn(*args, **kwargs):
pass
import warnings
warnings.warn = warn
###############################################
### Global Section ###
###############################################
# Load Kalman filter to predict the trajectory
kf = clsKalmanFilter()
# Create the color ColorFinder
myColorFinder = ColorFinder(False)
posListX = []
posListY = []
xList = [item for item in range(0, 1300)]
prediction=False
###############################################
### End of Global Section ###
###############################################
class clsPredictBodyLine(object):
def __init__(self):
self.inputFile_1 = str(cf.conf['BASE_FILE'])
self.inputFile_2 = str(cf.conf['BASE_IMAGE_FILE'])
self.src_path = str(cf.conf['SRC_PATH'])
self.hsvVals = cf.conf['HSV']
self.pauseTime = cf.conf['PAUSE']
self.pT1 = int(cf.conf['POINT_1'])
self.pT2 = int(cf.conf['POINT_2'])
self.pT3 = int(cf.conf['POINT_3'])
self.pT4 = int(cf.conf['POINT_4'])
def predStream(self, img, hsvVals, FrNo):
try:
pT1 = self.pT1
pT2 = self.pT2
pT3 = self.pT3
pT4 = self.pT4
#Find the color ball
imgColor, mask = myColorFinder.update(img, hsvVals)
#Find location of the red_ball
imgContours, contours = cvzone.findContours(img, mask, minArea=500)
if contours:
posListX.append(contours[0]['center'][0])
posListY.append(contours[0]['center'][1])
if posListX:
# Find the Coefficients
A, B, C = np.polyfit(posListX, posListY, 2)
for i, (posX, posY) in enumerate(zip(posListX, posListY)):
pos = (posX, posY)
cv2.circle(imgContours, pos, 10, (0,255,0), cv2.FILLED)
# Using Karman Filter Prediction
predicted = kf.predict(posX, posY)
cv2.circle(imgContours, (predicted[0], predicted[1]), 12, (255,0,255), cv2.FILLED)
ballDetectFlag = True
if ballDetectFlag:
print('Balls Detected!')
if i == 0:
cv2.line(imgContours, pos, pos, (0,255,0), 5)
cv2.line(imgContours, predicted, predicted, (255,0,255), 5)
else:
predictedM = kf.predict(posListX[i1], posListY[i1])
cv2.line(imgContours, pos, (posListX[i1], posListY[i1]), (0,255,0), 5)
cv2.line(imgContours, predicted, predictedM, (255,0,255), 5)
if len(posListX) < 10:
# Calculation for best place to ball
a1 = A
b1 = B
c1 = C pT1
X1 = int(( b1 math.sqrt(b1**2 (4*a1*c1)))/(2*a1))
prediction1 = pT2 < X1 < pT3
a2 = A
b2 = B
c2 = C pT4
X2 = int(( b2 math.sqrt(b2**2 (4*a2*c2)))/(2*a2))
prediction2 = pT2 < X2 < pT3
prediction = prediction1 | prediction2
if prediction:
print('Good Length Ball!')
sMsg = "Good Length Ball – (" + str(FrNo) + ")"
cvzone.putTextRect(imgContours, sMsg, (50,150), scale=5, thickness=5, colorR=(0,200,0), offset=20)
else:
print('Loose Ball!')
sMsg = "Loose Ball – (" + str(FrNo) + ")"
cvzone.putTextRect(imgContours, sMsg, (50,150), scale=5, thickness=5, colorR=(0,0,200), offset=20)
return imgContours
except Exception as e:
x = str(e)
print('Error predStream:', x)
return img
def processVideo(self, debugInd, var):
try:
cnt = 0
lastRowFlag=True
breakFlag = False
pauseTime = self.pauseTime
src_path = self.src_path
inputFile_1 = self.inputFile_1
inputFile_2 = self.inputFile_2
hsvVals = self.hsvVals
FileName_1 = src_path + inputFile_1
FileName_2 = src_path + inputFile_2
# Initialize the video
cap = cv2.VideoCapture(FileName_1)
while True:
try:
if breakFlag:
break
# Grab the frames
success, img = cap.read()
time.sleep(pauseTime)
cnt+=1
print('*'*60)
print('Frame Number:', str(cnt))
if (cv2.waitKey(1) & 0xFF) == ord("q"):
break
if success:
imgContours = self.predStream(img, hsvVals, cnt)
if imgContours is None:
imgContours = img
imgColor = cv2.resize(imgContours, (0,0), None, 0.7, 0.7)
# Display
cv2.imshow("ImageColor", imgColor)
print('*'*60)
else:
breakFlag=True
except Exception as e:
x = str(e)
print('Error Main:', x)
cv2.destroyAllWindows()
return 0
except Exception as e:
x = str(e)
print('Error:', x)
cv2.destroyAllWindows()
return 1

Please find the key snippet from the above script –

kf = clsKalmanFilter()

The application is instantiating the modified Kalman filter.

myColorFinder = ColorFinder(False)

This command has more purpose than creating a proper mask in debug mode if you want to isolate the color of any object you want to track. To debug this property, one needs to set the flag to True. And you will see the following screen. Click the next video to get the process to generate the accurate HSV.

In the end, you will get a similar entry to the below one –

And you can see the entry that is available in the config for the following parameter –

'HSV': {'hmin': 173, 'smin':177, 'vmin':57, 'hmax':178, 'smax':255, 'vmax':255},

The next important block is –

def predStream(self, img, hsvVals, FrNo):
    try:
        pT1 = self.pT1
        pT2 = self.pT2
        pT3 = self.pT3
        pT4 = self.pT4

The four points mentioned above will help us determine the best region for the ball, forcing the batsman to play the shots & a 90% chance of getting caught behind.


The snippets below will apply the mask & identify the contour of the objects which the program intends to track. In this case, we are talking about the pink cricket ball.

#Find the color ball
imgColor, mask = myColorFinder.update(img, hsvVals)

#Find location of the red_ball
imgContours, contours = cvzone.findContours(img, mask, minArea=500)

if contours:
    posListX.append(contours[0]['center'][0])
    posListY.append(contours[0]['center'][1])

The next key snippets are as follows –

if posListX:
    # Find the Coefficients
    A, B, C = np.polyfit(posListX, posListY, 2)

    for i, (posX, posY) in enumerate(zip(posListX, posListY)):
        pos = (posX, posY)
        cv2.circle(imgContours, pos, 10, (0,255,0), cv2.FILLED)

        # Using Karman Filter Prediction
        predicted = kf.predict(posX, posY)
        cv2.circle(imgContours, (predicted[0], predicted[1]), 12, (255,0,255), cv2.FILLED)

        ballDetectFlag = True
        if ballDetectFlag:
            print('Balls Detected!')

        if i == 0:
            cv2.line(imgContours, pos, pos, (0,255,0), 5)
            cv2.line(imgContours, predicted, predicted, (255,0,255), 5)
        else:
            predictedM = kf.predict(posListX[i-1], posListY[i-1])

            cv2.line(imgContours, pos, (posListX[i-1], posListY[i-1]), (0,255,0), 5)
            cv2.line(imgContours, predicted, predictedM, (255,0,255), 5)

The above lines will track the original & predicted lines & then it will plot on top of the frame in real time.

The next line will be as follows –

if len(posListX) < 10:

    # Calculation for best place to ball
    a1 = A
    b1 = B
    c1 = C - pT1

    X1 = int((- b1 - math.sqrt(b1**2 - (4*a1*c1)))/(2*a1))
    prediction1 = pT2 < X1 < pT3

    a2 = A
    b2 = B
    c2 = C - pT4

    X2 = int((- b2 - math.sqrt(b2**2 - (4*a2*c2)))/(2*a2))
    prediction2 = pT2 < X2 < pT3

    prediction = prediction1 | prediction2

if prediction:
    print('Good Length Ball!')
    sMsg = "Good Length Ball - (" + str(FrNo) + ")"
    cvzone.putTextRect(imgContours, sMsg, (50,150), scale=5, thickness=5, colorR=(0,200,0), offset=20)
else:
    print('Loose Ball!')
    sMsg = "Loose Ball - (" + str(FrNo) + ")"
    cvzone.putTextRect(imgContours, sMsg, (50,150), scale=5, thickness=5, colorR=(0,0,200), offset=20)
  • predictBodyLine.py (The main python script that will invoke the class to predict Cricket balls in the real-time video feed.)


#####################################################
#### Written By: SATYAKI DE ####
#### Written On: 25-Nov-2022 ####
#### Modified On 30-Nov-2022 ####
#### ####
#### Objective: This is the main calling ####
#### python script that will invoke the ####
#### clsPredictBodyLine class to initiate ####
#### the predict capability in real-time ####
#### from a cricket (Sports) streaming. ####
#####################################################
# We keep the setup code in a different class as shown below.
import clsPredictBodyLine as pbdl
from clsConfigClient import clsConfigClient as cf
import datetime
import logging
def main():
try:
# Other useful variables
debugInd = 'Y'
var = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
var1 = datetime.datetime.now()
print('Start Time: ', str(var))
# End of useful variables
# Initiating Log Class
general_log_path = str(cf.conf['LOG_PATH'])
# Enabling Logging Info
logging.basicConfig(filename=general_log_path + 'predBodyLine.log', level=logging.INFO)
print('Started predicting best bodyline deliveries from the Cricket Streaming!')
# Passing source data csv file
x1 = pbdl.clsPredictBodyLine()
# Execute all the pass
r1 = x1.processVideo(debugInd, var)
if (r1 == 0):
print('Successfully predicted body-line deliveries!')
else:
print('Failed to predict body-line deliveries!')
var2 = datetime.datetime.now()
c = var2 var1
minutes = c.total_seconds() / 60
print('Total difference in minutes: ', str(minutes))
print('End Time: ', str(var1))
except Exception as e:
x = str(e)
print('Error: ', x)
if __name__ == "__main__":
main()

Here is the final key snippet –

# Passing source data csv file
x1 = pbdl.clsPredictBodyLine()

# Execute all the pass
r1 = x1.processVideo(debugInd, var)

if (r1 == 0):
    print('Successfully predicted body-line deliveries!')
else:
    print('Failed to predict body-line deliveries!')

The above lines will first instantiate the main class & then invoke it.

You can find it here if you want to know more about the Kalman filter.

So, finally, we’ve done it.


FOLDER STRUCTURE:

You will get the complete codebase in the following GitHub link.

I’ll bring some more exciting topics in the coming days from the Python verse. Please share & subscribe to my post & let me know your feedback.

Till then, Happy Avenging! 🙂

Note: All the data & scenarios posted here are representational data & scenarios & available over the internet & for educational purposes only. Some of the images (except my photo) we’ve used are available over the net. We don’t claim ownership of these images. There is always room for improvement & especially in the prediction quality.

Realtime reading from a Streaming using Computer Vision

This week we’re going to extend one of our earlier posts & trying to read an entire text from streaming using computer vision. If you want to view the previous post, please click the following link.

But, before we proceed, why don’t we view the demo first?

Demo

Architecture:

Let us understand the architecture flow –

Architecture flow

The above diagram shows that the application, which uses the Open-CV, analyzes individual frames from the source & extracts the complete text within the video & displays it on top of the target screen besides prints the same in the console.

Python Packages:

pip install imutils==0.5.4
pip install matplotlib==3.5.2
pip install numpy==1.21.6
pip install opencv-contrib-python==4.6.0.66
pip install opencv-contrib-python-headless==4.6.0.66
pip install opencv-python==4.6.0.66
pip install opencv-python-headless==4.6.0.66
pip install pandas==1.3.5
pip install Pillow==9.1.1
pip install pytesseract==0.3.9
pip install python-dateutil==2.8.2

CODE:

Let us now understand the code. For this use case, we will only discuss three python scripts. However, we need more than these three. However, we have already discussed them in some of the early posts. Hence, we will skip them here.

  • clsReadingTextFromStream.py (This is the main class of python script that will extract the text from the WebCAM streaming in real-time.)


##################################################
#### Written By: SATYAKI DE ####
#### Written On: 22-Jul-2022 ####
#### Modified On 25-Jul-2022 ####
#### ####
#### Objective: This is the main class of ####
#### python script that will invoke the ####
#### extraction of texts from a WebCAM. ####
#### ####
##################################################
# Importing necessary packages
from clsConfig import clsConfig as cf
from imutils.object_detection import non_max_suppression
import numpy as np
import pytesseract
import imutils
import time
import cv2
import time
###############################################
### Global Section ###
###############################################
# Two output layer names for the text detector model
lNames = cf.conf['LAYER_DET']
# Tesseract OCR text param values
strVal = "-l " + str(cf.conf['LANG']) + " –oem " + str(cf.conf['OEM_VAL']) + " –psm " + str(cf.conf['PSM_VAL']) + ""
config = (strVal)
###############################################
### End of Global Section ###
###############################################
class clsReadingTextFromStream:
def __init__(self):
self.sep = str(cf.conf['SEP'])
self.Curr_Path = str(cf.conf['INIT_PATH'])
self.CacheL = int(cf.conf['CACHE_LIM'])
self.modelPath = str(cf.conf['MODEL_PATH']) + str(cf.conf['MODEL_FILE_NAME'])
self.minConf = float(cf.conf['MIN_CONFIDENCE'])
self.wt = int(cf.conf['WIDTH'])
self.ht = int(cf.conf['HEIGHT'])
self.pad = float(cf.conf['PADDING'])
self.title = str(cf.conf['TITLE'])
self.Otitle = str(cf.conf['ORIG_TITLE'])
self.drawTag = cf.conf['DRAW_TAG']
self.aRange = int(cf.conf['ASCII_RANGE'])
self.sParam = cf.conf['SUBTRACT_PARAM']
def findBoundBox(self, boxes, res, rW, rH, orig, origW, origH, pad):
try:
# Loop over the bounding boxes
for (spX, spY, epX, epY) in boxes:
# Scale the bounding box coordinates based on the respective
# ratios
spX = int(spX * rW)
spY = int(spY * rH)
epX = int(epX * rW)
epY = int(epY * rH)
# To obtain a better OCR of the text we can potentially
# apply a bit of padding surrounding the bounding box.
# And, computing the deltas in both the x and y directions
dX = int((epX spX) * pad)
dY = int((epY spY) * pad)
# Apply padding to each side of the bounding box, respectively
spX = max(0, spX dX)
spY = max(0, spY dY)
epX = min(origW, epX + (dX * 2))
epY = min(origH, epY + (dY * 2))
# Extract the actual padded ROI
roi = orig[spY:epY, spX:epX]
# Choose the proper OCR Config
text = pytesseract.image_to_string(roi, config=config)
# Add the bounding box coordinates and OCR'd text to the list
# of results
res.append(((spX, spY, epX, epY), text))
# Sort the results bounding box coordinates from top to bottom
res = sorted(res, key=lambda r:r[0][1])
return res
except Exception as e:
x = str(e)
print(x)
return res
def predictText(self, imgScore, imgGeo):
try:
minConf = self.minConf
# Initializing the bounding box rectangles & confidence score by
# extracting the rows & columns from the imgScore volume.
(numRows, numCols) = imgScore.shape[2:4]
rects = []
confScore = []
for y in range(0, numRows):
# Extract the imgScore probabilities to derive potential
# bounding box coordinates that surround text
imgScoreData = imgScore[0, 0, y]
xVal0 = imgGeo[0, 0, y]
xVal1 = imgGeo[0, 1, y]
xVal2 = imgGeo[0, 2, y]
xVal3 = imgGeo[0, 3, y]
anglesData = imgGeo[0, 4, y]
for x in range(0, numCols):
# If our score does not have sufficient probability,
# ignore it
if imgScoreData[x] < minConf:
continue
# Compute the offset factor as our resulting feature
# maps will be 4x smaller than the input frame
(offX, offY) = (x * 4.0, y * 4.0)
# Extract the rotation angle for the prediction and
# then compute the sin and cosine
angle = anglesData[x]
cos = np.cos(angle)
sin = np.sin(angle)
# Derive the width and height of the bounding box from
# imgGeo
h = xVal0[x] + xVal2[x]
w = xVal1[x] + xVal3[x]
# Compute both the starting and ending (x, y)-coordinates
# for the text prediction bounding box
epX = int(offX + (cos * xVal1[x]) + (sin * xVal2[x]))
epY = int(offY (sin * xVal1[x]) + (cos * xVal2[x]))
spX = int(epX w)
spY = int(epY h)
# Adding bounding box coordinates and probability score
# to the respective lists
rects.append((spX, spY, epX, epY))
confScore.append(imgScoreData[x])
# return a tuple of the bounding boxes and associated confScore
return (rects, confScore)
except Exception as e:
x = str(e)
print(x)
rects = []
confScore = []
return (rects, confScore)
def processStream(self, debugInd, var):
try:
sep = self.sep
Curr_Path = self.Curr_Path
CacheL = self.CacheL
modelPath = self.modelPath
minConf = self.minConf
wt = self.wt
ht = self.ht
pad = self.pad
title = self.title
Otitle = self.Otitle
drawTag = self.drawTag
aRange = self.aRange
sParam = self.sParam
val = 0
# Initialize the video stream and allow the camera sensor to warm up
print("[INFO] Starting video stream…")
cap = cv2.VideoCapture(0)
# Loading the pre-trained text detector
print("[INFO] Loading Text Detector…")
net = cv2.dnn.readNet(modelPath)
# Loop over the frames from the video stream
while True:
try:
# Grab the frame from our video stream and resize it
success, frame = cap.read()
orig = frame.copy()
(origH, origW) = frame.shape[:2]
# Setting new width and height and then determine the ratio in change
# for both the width and height
(newW, newH) = (wt, ht)
rW = origW / float(newW)
rH = origH / float(newH)
# Resize the frame and grab the new frame dimensions
frame = cv2.resize(frame, (newW, newH))
(H, W) = frame.shape[:2]
# Construct a blob from the frame and then perform a forward pass of
# the model to obtain the two output layer sets
blob = cv2.dnn.blobFromImage(frame, 1.0, (W, H), sParam, swapRB=True, crop=False)
net.setInput(blob)
(confScore, imgGeo) = net.forward(lNames)
# Decode the predictions, then apply non-maxima suppression to
# suppress weak, overlapping bounding boxes
(rects, confidences) = self.predictText(confScore, imgGeo)
boxes = non_max_suppression(np.array(rects), probs=confidences)
# Initialize the list of results
res = []
# Getting BoundingBox boundaries
res = self.findBoundBox(boxes, res, rW, rH, orig, origW, origH, pad)
for ((spX, spY, epX, epY), text) in res:
# Display the text OCR by using Tesseract APIs
print("Reading Text::")
print("=" *60)
print(text)
print("=" *60)
# Removing the non-ASCII text so it can draw the text on the frame
# using OpenCV, then draw the text and a bounding box surrounding
# the text region of the input frame
text = "".join([c if ord(c) < aRange else "" for c in text]).strip()
output = orig.copy()
cv2.rectangle(output, (spX, spY), (epX, epY), drawTag, 2)
cv2.putText(output, text, (spX, spY 20), cv2.FONT_HERSHEY_SIMPLEX, 1.2, drawTag, 3)
# Show the output frame
cv2.imshow(title, output)
#cv2.imshow(Otitle, frame)
# If the `q` key was pressed, break from the loop
if cv2.waitKey(1) == ord('q'):
break
val = 0
except Exception as e:
x = str(e)
print(x)
val = 1
# Performing cleanup at the end
cap.release()
cv2.destroyAllWindows()
return val
except Exception as e:
x = str(e)
print('Error:', x)
return 1

Please find the key snippet from the above script –

# Two output layer names for the text detector model

lNames = cf.conf['LAYER_DET']

# Tesseract OCR text param values

strVal = "-l " + str(cf.conf['LANG']) + " --oem " + str(cf.conf['OEM_VAL']) + " --psm " + str(cf.conf['PSM_VAL']) + ""
config = (strVal)

The first line contains the two output layers’ names for the text detector model. Among them, the first one indicates the outcome possibilities & the second one use to derive the bounding box coordinates of the predicted text.

The second line contains various options for the tesseract APIs. You need to understand the opportunities in detail to make them work. These are the essential options for our use case –

  • Language – The intended language, for example, English, Spanish, Hindi, Bengali, etc.
  • OEM flag – In this case, the application will use 4 to indicate LSTM neural net model for OCR.
  • OEM Value – In this case, the selected value is 7, indicating that the application treats the ROI as a single line of text.

For more details, please refer to the config file.

print("[INFO] Loading Text Detector...")
net = cv2.dnn.readNet(modelPath)

The above lines bring the already created model & load it to memory for evaluation.

# Setting new width and height and then determine the ratio in change
# for both the width and height
(newW, newH) = (wt, ht)
rW = origW / float(newW)
rH = origH / float(newH)

# Resize the frame and grab the new frame dimensions
frame = cv2.resize(frame, (newW, newH))
(H, W) = frame.shape[:2]

# Construct a blob from the frame and then perform a forward pass of
# the model to obtain the two output layer sets
blob = cv2.dnn.blobFromImage(frame, 1.0, (W, H), sParam, swapRB=True, crop=False)
net.setInput(blob)
(confScore, imgGeo) = net.forward(lNames)

# Decode the predictions, then apply non-maxima suppression to
# suppress weak, overlapping bounding boxes
(rects, confidences) = self.predictText(confScore, imgGeo)
boxes = non_max_suppression(np.array(rects), probs=confidences)

The above lines are more of preparing individual frames to get the bounding box by resizing the height & width followed by a forward pass of the model to obtain two output layer sets. And then apply the non-maxima suppression to remove the weak, overlapping bounding box by interpreting the prediction. In short, this will identify the potential text region & put the bounding box surrounding it.

# Initialize the list of results
res = []

# Getting BoundingBox boundaries
res = self.findBoundBox(boxes, res, rW, rH, orig, origW, origH, pad)

The above function will create the bounding box surrounding the predicted text regions. Also, we will capture the expected text inside the result variable.

for (spX, spY, epX, epY) in boxes:
  # Scale the bounding box coordinates based on the respective
  # ratios
  spX = int(spX * rW)
  spY = int(spY * rH)
  epX = int(epX * rW)
  epY = int(epY * rH)

  # To obtain a better OCR of the text we can potentially
  # apply a bit of padding surrounding the bounding box.
  # And, computing the deltas in both the x and y directions
  dX = int((epX - spX) * pad)
  dY = int((epY - spY) * pad)

  # Apply padding to each side of the bounding box, respectively
  spX = max(0, spX - dX)
  spY = max(0, spY - dY)
  epX = min(origW, epX + (dX * 2))
  epY = min(origH, epY + (dY * 2))

  # Extract the actual padded ROI
  roi = orig[spY:epY, spX:epX]

Now, the application will scale the bounding boxes based on the previously computed ratio for actual text recognition. In this process, the application also padded the bounding boxes & then extracted the padded region of interest.

# Choose the proper OCR Config
text = pytesseract.image_to_string(roi, config=config)

# Add the bounding box coordinates and OCR'd text to the list
# of results
res.append(((spX, spY, epX, epY), text))

Using OCR options, the application extracts the text within the video frame & adds that to the res list.

# Sort the results bounding box coordinates from top to bottom
res = sorted(res, key=lambda r:r[0][1])

It then sends a sorted output to the primary calling functions.

for ((spX, spY, epX, epY), text) in res:
  # Display the text OCR by using Tesseract APIs
  print("Reading Text::")
  print("=" *60)
  print(text)
  print("=" *60)

  # Removing the non-ASCII text so it can draw the text on the frame
  # using OpenCV, then draw the text and a bounding box surrounding
  # the text region of the input frame
  text = "".join([c if ord(c) < aRange else "" for c in text]).strip()
  output = orig.copy()

  cv2.rectangle(output, (spX, spY), (epX, epY), drawTag, 2)
  cv2.putText(output, text, (spX, spY - 20), cv2.FONT_HERSHEY_SIMPLEX, 1.2, drawTag, 3)

  # Show the output frame
  cv2.imshow(title, output)

Finally, it fetches the potential text region along with the text & then prints on top of the source video. Also, it removed some non-printable characters during this time to avoid any cryptic texts.

  • readingVideo.py (Main calling script.)


#####################################################
#### Written By: SATYAKI DE ####
#### Written On: 22-Jul-2022 ####
#### Modified On 25-Jul-2022 ####
#### ####
#### Objective: This is the main calling ####
#### python script that will invoke the ####
#### clsReadingTextFromStream class to initiate ####
#### the reading capability in real-time ####
#### & display text via Web-CAM. ####
#####################################################
# We keep the setup code in a different class as shown below.
import clsReadingTextFromStream as rtfs
from clsConfig import clsConfig as cf
import datetime
import logging
###############################################
### Global Section ###
###############################################
# Instantiating all the main class
x1 = rtfs.clsReadingTextFromStream()
###############################################
### End of Global Section ###
###############################################
def main():
try:
# Other useful variables
debugInd = 'Y'
var = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
var1 = datetime.datetime.now()
print('Start Time: ', str(var))
# End of useful variables
# Initiating Log Class
general_log_path = str(cf.conf['LOG_PATH'])
# Enabling Logging Info
logging.basicConfig(filename=general_log_path + 'readingTextFromVideo.log', level=logging.INFO)
print('Started reading text from videos!')
# Execute all the pass
r1 = x1.processStream(debugInd, var)
if (r1 == 0):
print('Successfully read text from the Live Stream!')
else:
print('Failed to read text from the Live Stream!')
var2 = datetime.datetime.now()
c = var2 var1
minutes = c.total_seconds() / 60
print('Total difference in minutes: ', str(minutes))
print('End Time: ', str(var1))
except Exception as e:
x = str(e)
print('Error: ', x)
if __name__ == "__main__":
main()

view raw

readingVideo.py

hosted with ❤ by GitHub

Please find the key snippet –

# Instantiating all the main class

x1 = rtfs.clsReadingTextFromStream()

# Execute all the pass
r1 = x1.processStream(debugInd, var)

if (r1 == 0):
    print('Successfully read text from the Live Stream!')
else:
    print('Failed to read text from the Live Stream!')

The above lines instantiate the main calling class & then invoke the function to get the desired extracted text from the live streaming video if that is successful.

FOLDER STRUCTURE:

Here is the folder structure that contains all the files & directories in MAC O/S –

You will get the complete codebase in the following Github link.

Unfortunately, I cannot upload the model due to it’s size. I will share on the need basis.

I’ll bring some more exciting topic in the coming days from the Python verse. Please share & subscribe my post & let me know your feedback.

Till then, Happy Avenging! 🙂

Note: All the data & scenario posted here are representational data & scenarios & available over the internet & for educational purpose only. Some of the images (except my photo) that we’ve used are available over the net. We don’t claim the ownership of these images. There is an always room for improvement & especially the prediction quality.

Real-time augmented reality (AR) using Python-based Computer Vision

Hi Team,

Today, I’m going to discuss another Computer Vision installment. I’ll discuss how to implement Augmented Reality using Open-CV Computer Vision with full audio. We will be using part of a Bengali OTT Series called “Feludar Goendagiri” entirely for educational purposes & also as a tribute to the great legendary director, late Satyajit Roy. To know more about him, please click the following link.

Why don’t we see the demo first before jumping into the technical details?


Demo

Architecture:

Let us understand the architecture –

Process Flow

The above diagram shows that the application, which uses the Open-CV, analyzes individual frames from the source & blends that with the video trailer. Finally, it creates another video by correctly mixing the source audio.

Python Packages:

Following are the python packages that are necessary to develop this brilliant use case –

pip install opencv-python
pip install pygame

CODE:

Let us now understand the code. For this use case, we will only discuss three python scripts. However, we need more than these three. However, we have already discussed them in some of the early posts. Hence, we will skip them here.

  • clsAugmentedReality.py (This is the main class of python script that will embed the source video with the WebCAM streams in real-time.)


##################################################
#### Written By: SATYAKI DE ####
#### Written On: 20-Jun-2022 ####
#### Modified On 25-Jun-2022 ####
#### ####
#### Objective: This is the main class of ####
#### python script that will embed the source ####
#### video with the WebCAM streams in ####
#### real-time. ####
##################################################
# Importing necessary packages
import numpy as np
import cv2
from clsConfig import clsConfig as cf
# Initialize our cached reference points
CACHED_REF_PTS = None
class clsAugmentedReality:
def __init__(self):
self.TOP_LEFT_X = int(cf.conf['TOP_LEFT_X'])
self.TOP_LEFT_Y = int(cf.conf['TOP_LEFT_Y'])
self.TOP_RIGHT_X = int(cf.conf['TOP_RIGHT_X'])
self.TOP_RIGHT_Y = int(cf.conf['TOP_RIGHT_Y'])
self.BOTTOM_RIGHT_X = int(cf.conf['BOTTOM_RIGHT_X'])
self.BOTTOM_RIGHT_Y = int(cf.conf['BOTTOM_RIGHT_Y'])
self.BOTTOM_LEFT_X = int(cf.conf['BOTTOM_LEFT_X'])
self.BOTTOM_LEFT_Y = int(cf.conf['BOTTOM_LEFT_Y'])
def getWarpImages(self, frame, source, cornerIDs, arucoDict, arucoParams, zoomFlag, useCache=False):
try:
# Assigning values
TOP_LEFT_X = self.TOP_LEFT_X
TOP_LEFT_Y = self.TOP_LEFT_Y
TOP_RIGHT_X = self.TOP_RIGHT_X
TOP_RIGHT_Y = self.TOP_RIGHT_Y
BOTTOM_RIGHT_X = self.BOTTOM_RIGHT_X
BOTTOM_RIGHT_Y = self.BOTTOM_RIGHT_Y
BOTTOM_LEFT_X = self.BOTTOM_LEFT_X
BOTTOM_LEFT_Y = self.BOTTOM_LEFT_Y
# Grab a reference to our cached reference points
global CACHED_REF_PTS
if source is None:
raise
# Grab the width and height of the frame and source image,
# respectively
# Extracting Frame from Camera
# Exracting Source from Video
(imgH, imgW) = frame.shape[:2]
(srcH, srcW) = source.shape[:2]
# Detect Aruco markers in the input frame
(corners, ids, rejected) = cv2.aruco.detectMarkers(frame, arucoDict, parameters=arucoParams)
print('Ids: ', str(ids))
print('Rejected: ', str(rejected))
# if we *did not* find our four ArUco markers, initialize an
# empty IDs list, otherwise flatten the ID list
print('Detecting Corners: ', str(len(corners)))
ids = np.array([]) if len(corners) != 4 else ids.flatten()
# Initialize our list of reference points
refPts = []
refPtTL1 = []
# Loop over the IDs of the ArUco markers in Top-Left, Top-Right,
# Bottom-Right, and Bottom-Left order
for i in cornerIDs:
# Grab the index of the corner with the current ID
j = np.squeeze(np.where(ids == i))
# If we receive an empty list instead of an integer index,
# then we could not find the marker with the current ID
if j.size == 0:
continue
# Otherwise, append the corner (x, y)-coordinates to our list
# of reference points
corner = np.squeeze(corners[j])
refPts.append(corner)
# Check to see if we failed to find the four ArUco markers
if len(refPts) != 4:
# If we are allowed to use cached reference points, fall
# back on them
if useCache and CACHED_REF_PTS is not None:
refPts = CACHED_REF_PTS
# Otherwise, we cannot use the cache and/or there are no
# previous cached reference points, so return early
else:
return None
# If we are allowed to use cached reference points, then update
# the cache with the current set
if useCache:
CACHED_REF_PTS = refPts
# Unpack our Aruco reference points and use the reference points
# to define the Destination transform matrix, making sure the
# points are specified in Top-Left, Top-Right, Bottom-Right, and
# Bottom-Left order
(refPtTL, refPtTR, refPtBR, refPtBL) = refPts
dstMat = [refPtTL[0], refPtTR[1], refPtBR[2], refPtBL[3]]
dstMat = np.array(dstMat)
# For zoom option recalculating all the 4 points
refPtTL1_L_X = refPtTL[0][0]TOP_LEFT_X
refPtTL1_L_Y = refPtTL[0][1]TOP_LEFT_Y
refPtTL1.append((refPtTL1_L_X,refPtTL1_L_Y))
refPtTL1_R_X = refPtTL[1][0]+TOP_RIGHT_X
refPtTL1_R_Y = refPtTL[1][1]+TOP_RIGHT_Y
refPtTL1.append((refPtTL1_R_X,refPtTL1_R_Y))
refPtTD1_L_X = refPtTL[2][0]+BOTTOM_RIGHT_X
refPtTD1_L_Y = refPtTL[2][1]+BOTTOM_RIGHT_Y
refPtTL1.append((refPtTD1_L_X,refPtTD1_L_Y))
refPtTD1_R_X = refPtTL[3][0]BOTTOM_LEFT_X
refPtTD1_R_Y = refPtTL[3][1]+BOTTOM_LEFT_Y
refPtTL1.append((refPtTD1_R_X,refPtTD1_R_Y))
dstMatMod = [refPtTL1[0], refPtTL1[1], refPtTL1[2], refPtTL1[3]]
dstMatMod = np.array(dstMatMod)
# Define the transform matrix for the *source* image in Top-Left,
# Top-Right, Bottom-Right, and Bottom-Left order
srcMat = np.array([[0, 0], [srcW, 0], [srcW, srcH], [0, srcH]])
# Compute the homography matrix and then warp the source image to
# the destination based on the homography depending upon the
# zoom flag
if zoomFlag == 1:
(H, _) = cv2.findHomography(srcMat, dstMat)
else:
(H, _) = cv2.findHomography(srcMat, dstMatMod)
warped = cv2.warpPerspective(source, H, (imgW, imgH))
# Construct a mask for the source image now that the perspective
# warp has taken place (we'll need this mask to copy the source
# image into the destination)
mask = np.zeros((imgH, imgW), dtype="uint8")
if zoomFlag == 1:
cv2.fillConvexPoly(mask, dstMat.astype("int32"), (255, 255, 255), cv2.LINE_AA)
else:
cv2.fillConvexPoly(mask, dstMatMod.astype("int32"), (255, 255, 255), cv2.LINE_AA)
# This optional step will give the source image a black
# border surrounding it when applied to the source image, you
# can apply a dilation operation
rect = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 3))
mask = cv2.dilate(mask, rect, iterations=2)
# Create a three channel version of the mask by stacking it
# depth-wise, such that we can copy the warped source image
# into the input image
maskScaled = mask.copy() / 255.0
maskScaled = np.dstack([maskScaled] * 3)
# Copy the warped source image into the input image by
# (1) Multiplying the warped image and masked together,
# (2) Then multiplying the original input image with the
# mask (giving more weight to the input where there
# are not masked pixels), and
# (3) Adding the resulting multiplications together
warpedMultiplied = cv2.multiply(warped.astype("float"), maskScaled)
imageMultiplied = cv2.multiply(frame.astype(float), 1.0 maskScaled)
output = cv2.add(warpedMultiplied, imageMultiplied)
output = output.astype("uint8")
# Return the output frame to the calling function
return output
except Exception as e:
# Delibarately raising the issue
# That way the control goes to main calling methods
# exception section
raise

Please find the key snippet from the above script –

(imgH, imgW) = frame.shape[:2]
(srcH, srcW) = source.shape[:2]

# Detect Aruco markers in the input frame
(corners, ids, rejected) = cv2.aruco.detectMarkers(frame, arucoDict, parameters=arucoParams)

Identifying the Aruco markers are key here. The above lines help the program detect all four corners.

However, let us discuss more on the Aruco markers & strategies that I’ve used for several different surfaces.

As you can see, the right-hand side Aruco marker is tiny compared to the left one. Hence, that one will be ideal for a curve surface like Coffee Mug, Bottle rather than a flat surface.

Also, we’ve demonstrated the zoom capability with the smaller Aruco marker that will Augment almost double the original surface area.

Let us understand why we need that; as you know, any spherical surface like a bottle is round-shaped. Hence, detecting relatively more significant Aruco markers in four corners will be difficult for any camera to identify.

Hence, we need a process where close four corners can be extrapolated mathematically to relatively larger projected areas easily detectable by any WebCAM.

Let’s observe the following figure –

Simulated Extrapolated corners

As you can see that the original position of the four corners is represented using the following points, i.e., (x1, y1), (x2, y2), (x3, y3) & (x4, y4).

And these positions are very close to each other. Hence, it will be easier for the camera to detect all the points (like a plain surface) without many retries.

And later, you can add specific values of x & y to them to get the derived four corners as shown in the above figures through the following points, i.e. (x1.1, y1.1), (x2.1, y2.1), (x3.1, y3.1) & (x4.1, y4.1).

# Loop over the IDs of the ArUco markers in Top-Left, Top-Right,
# Bottom-Right, and Bottom-Left order
for i in cornerIDs:
  # Grab the index of the corner with the current ID
  j = np.squeeze(np.where(ids == i))

  # If we receive an empty list instead of an integer index,
  # then we could not find the marker with the current ID
  if j.size == 0:
    continue

  # Otherwise, append the corner (x, y)-coordinates to our list
  # of reference points
  corner = np.squeeze(corners[j])
  refPts.append(corner)

# Check to see if we failed to find the four ArUco markers
if len(refPts) != 4:
  # If we are allowed to use cached reference points, fall
  # back on them
  if useCache and CACHED_REF_PTS is not None:
    refPts = CACHED_REF_PTS

  # Otherwise, we cannot use the cache and/or there are no
  # previous cached reference points, so return early
  else:
    return None

# If we are allowed to use cached reference points, then update
# the cache with the current set
if useCache:
  CACHED_REF_PTS = refPts

# Unpack our Aruco reference points and use the reference points
# to define the Destination transform matrix, making sure the
# points are specified in Top-Left, Top-Right, Bottom-Right, and
# Bottom-Left order
(refPtTL, refPtTR, refPtBR, refPtBL) = refPts
dstMat = [refPtTL[0], refPtTR[1], refPtBR[2], refPtBL[3]]
dstMat = np.array(dstMat)

In the above snippet, the application will scan through all the points & try to detect Aruco markers & then create a list of reference points, which will later be used to define the destination transformation matrix.

# For zoom option recalculating all the 4 points
refPtTL1_L_X = refPtTL[0][0]-TOP_LEFT_X
refPtTL1_L_Y = refPtTL[0][1]-TOP_LEFT_Y

refPtTL1.append((refPtTL1_L_X,refPtTL1_L_Y))

refPtTL1_R_X = refPtTL[1][0]+TOP_RIGHT_X
refPtTL1_R_Y = refPtTL[1][1]+TOP_RIGHT_Y

refPtTL1.append((refPtTL1_R_X,refPtTL1_R_Y))

refPtTD1_L_X = refPtTL[2][0]+BOTTOM_RIGHT_X
refPtTD1_L_Y = refPtTL[2][1]+BOTTOM_RIGHT_Y

refPtTL1.append((refPtTD1_L_X,refPtTD1_L_Y))

refPtTD1_R_X = refPtTL[3][0]-BOTTOM_LEFT_X
refPtTD1_R_Y = refPtTL[3][1]+BOTTOM_LEFT_Y

refPtTL1.append((refPtTD1_R_X,refPtTD1_R_Y))

dstMatMod = [refPtTL1[0], refPtTL1[1], refPtTL1[2], refPtTL1[3]]
dstMatMod = np.array(dstMatMod)

The above snippets calculate the revised points for the zoom-out capabilities as discussed in one of the earlier figures.

# Define the transform matrix for the *source* image in Top-Left,
# Top-Right, Bottom-Right, and Bottom-Left order
srcMat = np.array([[0, 0], [srcW, 0], [srcW, srcH], [0, srcH]])

The above snippet will create a transformation matrix for the video trailer.

# Compute the homography matrix and then warp the source image to
# the destination based on the homography depending upon the
# zoom flag
if zoomFlag == 1:
  (H, _) = cv2.findHomography(srcMat, dstMat)
else:
  (H, _) = cv2.findHomography(srcMat, dstMatMod)

warped = cv2.warpPerspective(source, H, (imgW, imgH))

# Construct a mask for the source image now that the perspective
# warp has taken place (we'll need this mask to copy the source
# image into the destination)
mask = np.zeros((imgH, imgW), dtype="uint8")
if zoomFlag == 1:
  cv2.fillConvexPoly(mask, dstMat.astype("int32"), (255, 255, 255), cv2.LINE_AA)
else:
  cv2.fillConvexPoly(mask, dstMatMod.astype("int32"), (255, 255, 255), cv2.LINE_AA)

# This optional step will give the source image a black
# border surrounding it when applied to the source image, you
# can apply a dilation operation
rect = cv2.getStructuringElement(cv2.MORPH_RECT, (3, 3))
mask = cv2.dilate(mask, rect, iterations=2)

# Create a three channel version of the mask by stacking it
# depth-wise, such that we can copy the warped source image
# into the input image
maskScaled = mask.copy() / 255.0
maskScaled = np.dstack([maskScaled] * 3)

# Copy the warped source image into the input image by
# (1) Multiplying the warped image and masked together,
# (2) Then multiplying the original input image with the
#     mask (giving more weight to the input where there
#     are not masked pixels), and
# (3) Adding the resulting multiplications together
warpedMultiplied = cv2.multiply(warped.astype("float"), maskScaled)
imageMultiplied = cv2.multiply(frame.astype(float), 1.0 - maskScaled)
output = cv2.add(warpedMultiplied, imageMultiplied)
output = output.astype("uint8")

Finally, depending upon the zoom flag, the application will create a warped image surrounded by an optionally black border.

  • clsEmbedVideoWithStream.py (This is the main class of python script that will invoke the clsAugmentedReality class to initiate augment reality after splitting the audio & video & then project them via the Web-CAM with a seamless broadcast.)


##################################################
#### Written By: SATYAKI DE ####
#### Written On: 22-Jun-2022 ####
#### Modified On 25-Jun-2022 ####
#### ####
#### Objective: This is the main class of ####
#### python script that will invoke the ####
#### clsAugmentedReality class to initiate ####
#### augment reality after splitting the ####
#### audio & video & then project them via ####
#### the Web-CAM with a seamless broadcast. ####
##################################################
# Importing necessary packages
import clsAugmentedReality as ar
from clsConfig import clsConfig as cf
from imutils.video import VideoStream
from collections import deque
import imutils
import time
import cv2
import subprocess
import os
import pygame
import time
import threading
import sys
###############################################
### Global Section ###
###############################################
# Instantiating the dependant class
x1 = ar.clsAugmentedReality()
###############################################
### End of Global Section ###
###############################################
class BreakLoop(Exception):
pass
class clsEmbedVideoWithStream:
def __init__(self):
self.sep = str(cf.conf['SEP'])
self.Curr_Path = str(cf.conf['INIT_PATH'])
self.FileName = str(cf.conf['FILE_NAME'])
self.CacheL = int(cf.conf['CACHE_LIM'])
self.FileName_1 = str(cf.conf['FILE_NAME_1'])
self.audioLen = int(cf.conf['audioLen'])
self.audioFreq = float(cf.conf['audioFreq'])
self.videoFrame = float(cf.conf['videoFrame'])
self.stopFlag=cf.conf['stopFlag']
self.zFlag=int(cf.conf['zoomFlag'])
self.title = str(cf.conf['TITLE'])
def playAudio(self, audioFile, audioLen, freq, stopFlag=False):
try:
pygame.mixer.init()
pygame.init()
pygame.mixer.music.load(audioFile)
pygame.mixer.music.set_volume(10)
val = int(audioLen)
i = 0
while i < val:
pygame.mixer.music.play(loops=0, start=float(i))
time.sleep(freq)
i = i + 1
if (i >= val):
raise BreakLoop
if (stopFlag==True):
raise BreakLoop
return 0
except BreakLoop as s:
return 0
except Exception as e:
x = str(e)
print(x)
return 1
def extractAudio(self, video_file, output_ext="mp3"):
try:
"""Converts video to audio directly using `ffmpeg` command
with the help of subprocess module"""
filename, ext = os.path.splitext(video_file)
subprocess.call(["ffmpeg", "-y", "-i", video_file, f"{filename}.{output_ext}"],
stdout=subprocess.DEVNULL,
stderr=subprocess.STDOUT)
return 0
except Exception as e:
x = str(e)
print('Error: ', x)
return 1
def processStream(self, debugInd, var):
try:
sep = self.sep
Curr_Path = self.Curr_Path
FileName = self.FileName
CacheL = self.CacheL
FileName_1 = self.FileName_1
audioLen = self.audioLen
audioFreq = self.audioFreq
videoFrame = self.videoFrame
stopFlag = self.stopFlag
zFlag = self.zFlag
title = self.title
print('audioFreq:')
print(str(audioFreq))
print('videoFrame:')
print(str(videoFrame))
# Construct the source for Video & Temporary Audio
videoFile = Curr_Path + sep + 'Video' + sep + FileName
audioFile = Curr_Path + sep + 'Video' + sep + FileName_1
# Load the Aruco dictionary and grab the Aruco parameters
print("[INFO] initializing marker detector…")
arucoDict = cv2.aruco.Dictionary_get(cv2.aruco.DICT_ARUCO_ORIGINAL)
arucoParams = cv2.aruco.DetectorParameters_create()
# Initialize the video file stream
print("[INFO] accessing video stream…")
vf = cv2.VideoCapture(videoFile)
x = self.extractAudio(videoFile)
if x == 0:
print('Successfully Audio extracted from the source file!')
else:
print('Failed to extract the source audio!')
# Initialize a queue to maintain the next frame from the video stream
Q = deque(maxlen=128)
# We need to have a frame in our queue to start our augmented reality
# pipeline, so read the next frame from our video file source and add
# it to our queue
(grabbed, source) = vf.read()
Q.appendleft(source)
# Initialize the video stream and allow the camera sensor to warm up
print("[INFO] starting video stream…")
vs = VideoStream(src=0).start()
time.sleep(2.0)
flg = 0
t = threading.Thread(target=self.playAudio, args=(audioFile, audioLen, audioFreq, stopFlag,))
t.daemon = True
try:
# Loop over the frames from the video stream
while len(Q) > 0:
try:
# Grab the frame from our video stream and resize it
frame = vs.read()
frame = imutils.resize(frame, width=1020)
# Attempt to find the ArUCo markers in the frame, and provided
# they are found, take the current source image and warp it onto
# input frame using our augmented reality technique
warped = x1.getWarpImages(
frame, source,
cornerIDs=(923, 1001, 241, 1007),
arucoDict=arucoDict,
arucoParams=arucoParams,
zoomFlag=zFlag,
useCache=CacheL > 0)
# If the warped frame is not None, then we know (1) we found the
# four ArUCo markers and (2) the perspective warp was successfully
# applied
if warped is not None:
# Set the frame to the output augment reality frame and then
# grab the next video file frame from our queue
frame = warped
source = Q.popleft()
if flg == 0:
t.start()
flg = flg + 1
# For speed/efficiency, we can use a queue to keep the next video
# frame queue ready for us — the trick is to ensure the queue is
# always (or nearly full)
if len(Q) != Q.maxlen:
# Read the next frame from the video file stream
(grabbed, nextFrame) = vf.read()
# If the frame was read (meaning we are not at the end of the
# video file stream), add the frame to our queue
if grabbed:
Q.append(nextFrame)
# Show the output frame
cv2.imshow(title, frame)
time.sleep(videoFrame)
# If the `q` key was pressed, break from the loop
if cv2.waitKey(2) & 0xFF == ord('q'):
stopFlag = True
break
except BreakLoop:
raise BreakLoop
except Exception as e:
pass
if (len(Q) == Q.maxlen):
time.sleep(2)
break
except BreakLoop as s:
print('Processed completed!')
# Performing cleanup at the end
cv2.destroyAllWindows()
vs.stop()
except Exception as e:
x = str(e)
print(x)
# Performing cleanup at the end
cv2.destroyAllWindows()
vs.stop()
return 0
except Exception as e:
x = str(e)
print('Error:', x)
return 1

Please find the key snippet from the above script –

def playAudio(self, audioFile, audioLen, freq, stopFlag=False):
  try:
    pygame.mixer.init()
    pygame.init()
    pygame.mixer.music.load(audioFile)

    pygame.mixer.music.set_volume(10)

    val = int(audioLen)
    i = 0

    while i < val:
      pygame.mixer.music.play(loops=0, start=float(i))
      time.sleep(freq)

      i = i + 1

      if (i >= val):
        raise BreakLoop

      if (stopFlag==True):
        raise BreakLoop

    return 0
  except BreakLoop as s:
    return 0
  except Exception as e:
    x = str(e)
    print(x)

    return 1

The above function will initiate the pygame library to run the sound of the video file that has been extracted as part of a separate process.

def extractAudio(self, video_file, output_ext="mp3"):
    try:
        """Converts video to audio directly using `ffmpeg` command
        with the help of subprocess module"""
        filename, ext = os.path.splitext(video_file)
        subprocess.call(["ffmpeg", "-y", "-i", video_file, f"{filename}.{output_ext}"],
                        stdout=subprocess.DEVNULL,
                        stderr=subprocess.STDOUT)

        return 0
    except Exception as e:
        x = str(e)
        print('Error: ', x)

        return 1

The above function temporarily extracts the audio file from the source trailer video.

# Initialize the video file stream
print("[INFO] accessing video stream...")
vf = cv2.VideoCapture(videoFile)

x = self.extractAudio(videoFile)

if x == 0:
    print('Successfully Audio extracted from the source file!')
else:
    print('Failed to extract the source audio!')

# Initialize a queue to maintain the next frame from the video stream
Q = deque(maxlen=128)

# We need to have a frame in our queue to start our augmented reality
# pipeline, so read the next frame from our video file source and add
# it to our queue
(grabbed, source) = vf.read()
Q.appendleft(source)

# Initialize the video stream and allow the camera sensor to warm up
print("[INFO] starting video stream...")
vs = VideoStream(src=0).start()

time.sleep(2.0)
flg = 0

The above snippets read the frames from the video file after invoking the audio extraction. Then, it uses a Queue method to store all the video frames for better performance. And finally, it starts consuming the standard streaming video from the WebCAM to augment the trailer video on top of it.

t = threading.Thread(target=self.playAudio, args=(audioFile, audioLen, audioFreq, stopFlag,))
t.daemon = True

Now, the application has instantiated an orphan thread to spin off the audio play function. The reason is to void the performance & video frame frequency impact on top of it.

while len(Q) > 0:
  try:
    # Grab the frame from our video stream and resize it
    frame = vs.read()
    frame = imutils.resize(frame, width=1020)

    # Attempt to find the ArUCo markers in the frame, and provided
    # they are found, take the current source image and warp it onto
    # input frame using our augmented reality technique
    warped = x1.getWarpImages(
      frame, source,
      cornerIDs=(923, 1001, 241, 1007),
      arucoDict=arucoDict,
      arucoParams=arucoParams,
      zoomFlag=zFlag,
      useCache=CacheL > 0)

    # If the warped frame is not None, then we know (1) we found the
    # four ArUCo markers and (2) the perspective warp was successfully
    # applied
    if warped is not None:
      # Set the frame to the output augment reality frame and then
      # grab the next video file frame from our queue
      frame = warped
      source = Q.popleft()

      if flg == 0:

        t.start()
        flg = flg + 1

    # For speed/efficiency, we can use a queue to keep the next video
    # frame queue ready for us -- the trick is to ensure the queue is
    # always (or nearly full)
    if len(Q) != Q.maxlen:
      # Read the next frame from the video file stream
      (grabbed, nextFrame) = vf.read()

      # If the frame was read (meaning we are not at the end of the
      # video file stream), add the frame to our queue
      if grabbed:
        Q.append(nextFrame)

    # Show the output frame
    cv2.imshow(title, frame)
    time.sleep(videoFrame)

    # If the `q` key was pressed, break from the loop
    if cv2.waitKey(2) & 0xFF == ord('q'):
      stopFlag = True
      break

  except BreakLoop:
    raise BreakLoop
  except Exception as e:
    pass

  if (len(Q) == Q.maxlen):
    time.sleep(2)
    break

The final segment will call the getWarpImages function to get the Augmented image on top of the video. It also checks for the upcoming frames & whether the source video is finished or not. In case of the end, the application will initiate a break method to come out from the infinite WebCAM read. Also, there is a provision for manual exit by pressing the ‘Q’ from the MacBook keyboard.

# Performing cleanup at the end
cv2.destroyAllWindows()
vs.stop()

It is always advisable to close your camera & remove any temporarily available windows that are still left once the application finishes the process.

  • augmentedMovieTrailer.py (Main calling script)


#####################################################
#### Written By: SATYAKI DE ####
#### Written On: 22-Jun-2022 ####
#### Modified On 25-Jun-2022 ####
#### ####
#### Objective: This is the main calling ####
#### python script that will invoke the ####
#### clsEmbedVideoWithStream class to initiate ####
#### the augmented reality in real-time ####
#### & display a trailer on top of any surface ####
#### via Web-CAM. ####
#####################################################
# We keep the setup code in a different class as shown below.
import clsEmbedVideoWithStream as evws
from clsConfig import clsConfig as cf
import datetime
import logging
###############################################
### Global Section ###
###############################################
# Instantiating all the main class
x1 = evws.clsEmbedVideoWithStream()
###############################################
### End of Global Section ###
###############################################
def main():
try:
# Other useful variables
debugInd = 'Y'
var = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
var1 = datetime.datetime.now()
print('Start Time: ', str(var))
# End of useful variables
# Initiating Log Class
general_log_path = str(cf.conf['LOG_PATH'])
# Enabling Logging Info
logging.basicConfig(filename=general_log_path + 'augmentedMovieTrailer.log', level=logging.INFO)
print('Started augmenting videos!')
# Execute all the pass
r1 = x1.processStream(debugInd, var)
if (r1 == 0):
print('Successfully identified human emotions!')
else:
print('Failed to identify the human emotions!')
var2 = datetime.datetime.now()
c = var2 var1
minutes = c.total_seconds() / 60
print('Total difference in minutes: ', str(minutes))
print('End Time: ', str(var1))
except Exception as e:
x = str(e)
print('Error: ', x)
if __name__ == "__main__":
main()

The above script will initially instantiate the main calling class & then invoke the processStream function to create the Augmented Reality.


FOLDER STRUCTURE:

Here is the folder structure that contains all the files & directories in MAC O/S –

Directory Structure

You will get the complete codebase in the following Github link.

If you want to know more about this legendary director & his famous work, please visit the following link.

I’ll bring some more exciting topic in the coming days from the Python verse. Please share & subscribe my post & let me know your feedback.

Till then, Happy Avenging! 🙂

Note: All the data & scenario posted here are representational data & scenarios & available over the internet & for educational purpose only. Some of the images (except my photo) that we’ve used are available over the net. We don’t claim the ownership of these images. There is an always room for improvement & especially the prediction quality.

Live visual reading using Convolutional Neural Network (CNN) through Python-based machine-learning application.

This week we’re planning to touch on one of the exciting posts of visually reading characters from WebCAM & predict the letters using CNN methods. Before we dig deep, why don’t we see the demo run first?

Demo

Isn’t it fascinating? As we can see, the computer can record events and read like humans. And, thanks to the brilliant packages available in Python, which can help us predict the correct letter out of an Image.


What do we need to test it out?

  1. Preferably an external WebCAM.
  2. A moderate or good Laptop to test out this.
  3. Python 
  4. And a few other packages that we’ll mention next block.

What Python packages do we need?

Some of the critical packages that we must need to test out this application are –

cmake==3.22.1
dlib==19.19.0
face-recognition==1.3.0
face-recognition-models==0.3.0
imutils==0.5.3
jsonschema==4.4.0
keras==2.7.0
Keras-Preprocessing==1.1.2
matplotlib==3.5.1
matplotlib-inline==0.1.3
oauthlib==3.1.1
opencv-contrib-python==4.1.2.30
opencv-contrib-python-headless==4.4.0.46
opencv-python==4.5.5.62
opencv-python-headless==4.5.5.62
pickleshare==0.7.5
Pillow==9.0.0
python-dateutil==2.8.2
requests==2.27.1
requests-oauthlib==1.3.0
scikit-image==0.19.1
scikit-learn==1.0.2
tensorboard==2.7.0
tensorboard-data-server==0.6.1
tensorboard-plugin-wit==1.8.1
tensorflow==2.7.0
tensorflow-estimator==2.7.0
tensorflow-io-gcs-filesystem==0.23.1
tqdm==4.62.3

What is CNN?

In deep learning, a convolutional neural network (CNN/ConvNet) is a class of deep neural networks most commonly applied to analyze visual imagery.

Different Steps of CNN

We can understand from the above picture that a CNN generally takes an image as input. The neural network analyzes each pixel separately. The weights and biases of the model are then tweaked to detect the desired letters (In our use case) from the image. Like other algorithms, the data also has to pass through pre-processing stage. However, a CNN needs relatively less pre-processing than most other Deep Learning algorithms.

If you want to know more about this, there is an excellent article on CNN with some on-point animations explaining this concept. Please read it here.

Where do we get the data sets for our testing?

For testing, we are fortunate enough to have Kaggle with us. We have received a wide variety of sample data, which you can get from here.


Our use-case:

Architecture

From the above diagram, one can see that the python application will consume a live video feed of any random letters (both printed & handwritten) & predict the character as part of the machine learning model that we trained.


Code:

  1. clsConfig.py (Configuration file for the entire application.)


################################################
#### Written By: SATYAKI DE ####
#### Written On: 15-May-2020 ####
#### Modified On: 28-Dec-2021 ####
#### ####
#### Objective: This script is a config ####
#### file, contains all the keys for ####
#### Machine-Learning & streaming dashboard.####
#### ####
################################################
import os
import platform as pl
class clsConfig(object):
Curr_Path = os.path.dirname(os.path.realpath(__file__))
os_det = pl.system()
if os_det == "Windows":
sep = '\\'
else:
sep = '/'
conf = {
'APP_ID': 1,
'ARCH_DIR': Curr_Path + sep + 'arch' + sep,
'PROFILE_PATH': Curr_Path + sep + 'profile' + sep,
'LOG_PATH': Curr_Path + sep + 'log' + sep,
'REPORT_PATH': Curr_Path + sep + 'report',
'FILE_NAME': Curr_Path + sep + 'Data' + sep + 'A_Z_Handwritten_Data.csv',
'SRC_PATH': Curr_Path + sep + 'data' + sep,
'APP_DESC_1': 'Old Video Enhancement!',
'DEBUG_IND': 'N',
'INIT_PATH': Curr_Path,
'SUBDIR': 'data',
'SEP': sep,
'testRatio':0.2,
'valRatio':0.2,
'epochsVal':8,
'activationType':'relu',
'activationType2':'softmax',
'numOfClasses':26,
'kernelSize'🙁3, 3),
'poolSize'🙁2, 2),
'filterVal1':32,
'filterVal2':64,
'filterVal3':128,
'stridesVal':2,
'monitorVal':'val_loss',
'paddingVal1':'same',
'paddingVal2':'valid',
'reshapeVal':28,
'reshapeVal1'🙁28,28),
'patienceVal1':1,
'patienceVal2':2,
'sleepTime':3,
'sleepTime1':6,
'factorVal':0.2,
'learningRateVal':0.001,
'minDeltaVal':0,
'minLrVal':0.0001,
'verboseFlag':0,
'modeInd':'auto',
'shuffleVal':100,
'DenkseVal1':26,
'DenkseVal2':64,
'DenkseVal3':128,
'predParam':9,
'word_dict':{0:'A',1:'B',2:'C',3:'D',4:'E',5:'F',6:'G',7:'H',8:'I',9:'J',10:'K',11:'L',12:'M',13:'N',14:'O',15:'P',16:'Q',17:'R',18:'S',19:'T',20:'U',21:'V',22:'W',23:'X', 24:'Y',25:'Z'},
'width':640,
'height':480,
'imgSize': (32,32),
'threshold': 0.45,
'imgDimension': (400, 440),
'imgSmallDim': (7, 7),
'imgMidDim': (28, 28),
'reshapeParam1':1,
'reshapeParam2':28,
'colorFeed'🙁0,0,130),
'colorPredict'🙁0,25,255)
}

view raw

clsConfig.py

hosted with ❤ by GitHub

Important parameters that we need to follow from the above snippets are –

'testRatio':0.2,
'valRatio':0.2,
'epochsVal':8,
'activationType':'relu',
'activationType2':'softmax',
'numOfClasses':26,
'kernelSize':(3, 3),
'poolSize':(2, 2),
'word_dict':{0:'A',1:'B',2:'C',3:'D',4:'E',5:'F',6:'G',7:'H',8:'I',9:'J',10:'K',11:'L',12:'M',13:'N',14:'O',15:'P',16:'Q',17:'R',18:'S',19:'T',20:'U',21:'V',22:'W',23:'X', 24:'Y',25:'Z'},

Since we have 26 letters, we have classified it as 26 in the numOfClasses.

Since we are talking about characters, we had to come up with a process of identifying each character as numbers & then processing our entire logic. Hence, the above parameter named word_dict captured all the characters in a python dictionary & stored them. Moreover, the application translates the final number output to more appropriate characters as the prediction.

2. clsAlphabetReading.py (Main training class to teach the model to predict alphabets from visual reader.)


###############################################
#### Written By: SATYAKI DE ####
#### Written On: 17-Jan-2022 ####
#### Modified On 17-Jan-2022 ####
#### ####
#### Objective: This python script will ####
#### teach & perfect the model to read ####
#### visual alphabets using Convolutional ####
#### Neural Network (CNN). ####
###############################################
from keras.datasets import mnist
import matplotlib.pyplot as plt
import cv2
import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Flatten, Conv2D, MaxPool2D, Dropout
from tensorflow.keras.optimizers import SGD, Adam
from keras.callbacks import ReduceLROnPlateau, EarlyStopping
from keras.utils.np_utils import to_categorical
import pandas as p
import numpy as np
from sklearn.model_selection import train_test_split
from keras.utils import np_utils
import matplotlib.pyplot as plt
from tqdm import tqdm_notebook
from sklearn.utils import shuffle
import pickle
import os
import platform as pl
from clsConfig import clsConfig as cf
class clsAlphabetReading:
def __init__(self):
self.sep = str(cf.conf['SEP'])
self.Curr_Path = str(cf.conf['INIT_PATH'])
self.fileName = str(cf.conf['FILE_NAME'])
self.testRatio = float(cf.conf['testRatio'])
self.valRatio = float(cf.conf['valRatio'])
self.epochsVal = int(cf.conf['epochsVal'])
self.activationType = str(cf.conf['activationType'])
self.activationType2 = str(cf.conf['activationType2'])
self.numOfClasses = int(cf.conf['numOfClasses'])
self.kernelSize = cf.conf['kernelSize']
self.poolSize = cf.conf['poolSize']
self.filterVal1 = int(cf.conf['filterVal1'])
self.filterVal2 = int(cf.conf['filterVal2'])
self.filterVal3 = int(cf.conf['filterVal3'])
self.stridesVal = int(cf.conf['stridesVal'])
self.monitorVal = str(cf.conf['monitorVal'])
self.paddingVal1 = str(cf.conf['paddingVal1'])
self.paddingVal2 = str(cf.conf['paddingVal2'])
self.reshapeVal = int(cf.conf['reshapeVal'])
self.reshapeVal1 = cf.conf['reshapeVal1']
self.patienceVal1 = int(cf.conf['patienceVal1'])
self.patienceVal2 = int(cf.conf['patienceVal2'])
self.sleepTime = int(cf.conf['sleepTime'])
self.sleepTime1 = int(cf.conf['sleepTime1'])
self.factorVal = float(cf.conf['factorVal'])
self.learningRateVal = float(cf.conf['learningRateVal'])
self.minDeltaVal = int(cf.conf['minDeltaVal'])
self.minLrVal = float(cf.conf['minLrVal'])
self.verboseFlag = int(cf.conf['verboseFlag'])
self.modeInd = str(cf.conf['modeInd'])
self.shuffleVal = int(cf.conf['shuffleVal'])
self.DenkseVal1 = int(cf.conf['DenkseVal1'])
self.DenkseVal2 = int(cf.conf['DenkseVal2'])
self.DenkseVal3 = int(cf.conf['DenkseVal3'])
self.predParam = int(cf.conf['predParam'])
self.word_dict = cf.conf['word_dict']
def applyCNN(self, X_Train, Y_Train_Catg, X_Validation, Y_Validation_Catg):
try:
testRatio = self.testRatio
epochsVal = self.epochsVal
activationType = self.activationType
activationType2 = self.activationType2
numOfClasses = self.numOfClasses
kernelSize = self.kernelSize
poolSize = self.poolSize
filterVal1 = self.filterVal1
filterVal2 = self.filterVal2
filterVal3 = self.filterVal3
stridesVal = self.stridesVal
monitorVal = self.monitorVal
paddingVal1 = self.paddingVal1
paddingVal2 = self.paddingVal2
reshapeVal = self.reshapeVal
patienceVal1 = self.patienceVal1
patienceVal2 = self.patienceVal2
sleepTime = self.sleepTime
sleepTime1 = self.sleepTime1
factorVal = self.factorVal
learningRateVal = self.learningRateVal
minDeltaVal = self.minDeltaVal
minLrVal = self.minLrVal
verboseFlag = self.verboseFlag
modeInd = self.modeInd
shuffleVal = self.shuffleVal
DenkseVal1 = self.DenkseVal1
DenkseVal2 = self.DenkseVal2
DenkseVal3 = self.DenkseVal3
model = Sequential()
model.add(Conv2D(filters=filterVal1, kernel_size=kernelSize, activation=activationType, input_shape=(28,28,1)))
model.add(MaxPool2D(pool_size=poolSize, strides=stridesVal))
model.add(Conv2D(filters=filterVal2, kernel_size=kernelSize, activation=activationType, padding = paddingVal1))
model.add(MaxPool2D(pool_size=poolSize, strides=stridesVal))
model.add(Conv2D(filters=filterVal3, kernel_size=kernelSize, activation=activationType, padding = paddingVal2))
model.add(MaxPool2D(pool_size=poolSize, strides=stridesVal))
model.add(Flatten())
model.add(Dense(DenkseVal2,activation = activationType))
model.add(Dense(DenkseVal3,activation = activationType))
model.add(Dense(DenkseVal1,activation = activationType2))
model.compile(optimizer = Adam(learning_rate=learningRateVal), loss='categorical_crossentropy', metrics=['accuracy'])
reduce_lr = ReduceLROnPlateau(monitor=monitorVal, factor=factorVal, patience=patienceVal1, min_lr=minLrVal)
early_stop = EarlyStopping(monitor=monitorVal, min_delta=minDeltaVal, patience=patienceVal2, verbose=verboseFlag, mode=modeInd)
fittedModel = model.fit(X_Train, Y_Train_Catg, epochs=epochsVal, callbacks=[reduce_lr, early_stop], validation_data = (X_Validation,Y_Validation_Catg))
return (model, fittedModel)
except Exception as e:
x = str(e)
model = Sequential()
print('Error: ', x)
return (model, model)
def trainModel(self, debugInd, var):
try:
sep = self.sep
Curr_Path = self.Curr_Path
fileName = self.fileName
epochsVal = self.epochsVal
valRatio = self.valRatio
predParam = self.predParam
testRatio = self.testRatio
reshapeVal = self.reshapeVal
numOfClasses = self.numOfClasses
sleepTime = self.sleepTime
sleepTime1 = self.sleepTime1
shuffleVal = self.shuffleVal
reshapeVal1 = self.reshapeVal1
# Dictionary for getting characters from index values
word_dict = self.word_dict
print('File Name: ', str(fileName))
# Read the data
df_HW_Alphabet = p.read_csv(fileName).astype('float32')
# Sample Data
print('Sample Data: ')
print(df_HW_Alphabet.head())
# Split data the (x – Our data) & (y – the prdict label)
x = df_HW_Alphabet.drop('0',axis = 1)
y = df_HW_Alphabet['0']
# Reshaping the data in csv file to display as an image
X_Train, X_Test, Y_Train, Y_Test = train_test_split(x, y, test_size = testRatio)
X_Train, X_Validation, Y_Train, Y_Validation = train_test_split(X_Train, Y_Train, test_size = valRatio)
X_Train = np.reshape(X_Train.values, (X_Train.shape[0], reshapeVal, reshapeVal))
X_Test = np.reshape(X_Test.values, (X_Test.shape[0], reshapeVal, reshapeVal))
X_Validation = np.reshape(X_Validation.values, (X_Validation.shape[0], reshapeVal, reshapeVal))
print("Train Data Shape: ", X_Train.shape)
print("Test Data Shape: ", X_Test.shape)
print("Validation Data shape: ", X_Validation.shape)
# Plotting the number of alphabets in the dataset
Y_Train_Num = np.int0(y)
count = np.zeros(numOfClasses, dtype='int')
for i in Y_Train_Num:
count[i] +=1
alphabets = []
for i in word_dict.values():
alphabets.append(i)
fig, ax = plt.subplots(1,1, figsize=(7,7))
ax.barh(alphabets, count)
plt.xlabel("Number of elements ")
plt.ylabel("Alphabets")
plt.grid()
plt.show(block=False)
plt.pause(sleepTime)
plt.close()
# Shuffling the data
shuff = shuffle(X_Train[:shuffleVal])
# Model reshaping the training & test dataset
X_Train = X_Train.reshape(X_Train.shape[0],X_Train.shape[1],X_Train.shape[2],1)
print("Shape of Train Data: ", X_Train.shape)
X_Test = X_Test.reshape(X_Test.shape[0], X_Test.shape[1], X_Test.shape[2],1)
print("Shape of Test Data: ", X_Test.shape)
X_Validation = X_Validation.reshape(X_Validation.shape[0], X_Validation.shape[1], X_Validation.shape[2],1)
print("Shape of Validation data: ", X_Validation.shape)
# Converting the labels to categorical values
Y_Train_Catg = to_categorical(Y_Train, num_classes = numOfClasses, dtype='int')
print("Shape of Train Labels: ", Y_Train_Catg.shape)
Y_Test_Catg = to_categorical(Y_Test, num_classes = numOfClasses, dtype='int')
print("Shape of Test Labels: ", Y_Test_Catg.shape)
Y_Validation_Catg = to_categorical(Y_Validation, num_classes = numOfClasses, dtype='int')
print("Shape of validation labels: ", Y_Validation_Catg.shape)
model, history = self.applyCNN(X_Train, Y_Train_Catg, X_Validation, Y_Validation_Catg)
print('Model Summary: ')
print(model.summary())
# Displaying the accuracies & losses for train & validation set
print("Validation Accuracy :", history.history['val_accuracy'])
print("Training Accuracy :", history.history['accuracy'])
print("Validation Loss :", history.history['val_loss'])
print("Training Loss :", history.history['loss'])
# Displaying the Loss Graph
plt.figure(1)
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.legend(['training','validation'])
plt.title('Loss')
plt.xlabel('epoch')
plt.show(block=False)
plt.pause(sleepTime1)
plt.close()
# Dsiplaying the Accuracy Graph
plt.figure(2)
plt.plot(history.history['accuracy'])
plt.plot(history.history['val_accuracy'])
plt.legend(['training','validation'])
plt.title('Accuracy')
plt.xlabel('epoch')
plt.show(block=False)
plt.pause(sleepTime1)
plt.close()
# Making the model to predict
pred = model.predict(X_Test[:predParam])
print('Test Details::')
print('X_Test: ', X_Test.shape)
print('Y_Test_Catg: ', Y_Test_Catg.shape)
try:
score = model.evaluate(X_Test, Y_Test_Catg, verbose=0)
print('Test Score = ', score[0])
print('Test Accuracy = ', score[1])
except Exception as e:
x = str(e)
print('Error: ', x)
# Displaying some of the test images & their predicted labels
fig, ax = plt.subplots(3,3, figsize=(8,9))
axes = ax.flatten()
for i in range(9):
axes[i].imshow(np.reshape(X_Test[i], reshapeVal1), cmap="Greys")
pred = word_dict[np.argmax(Y_Test_Catg[i])]
print('Prediction: ', pred)
axes[i].set_title("Test Prediction: " + pred)
axes[i].grid()
plt.show(block=False)
plt.pause(sleepTime1)
plt.close()
fileName = Curr_Path + sep + 'Model' + sep + 'model_trained_' + str(epochsVal) + '.p'
print('Model Name: ', str(fileName))
pickle_out = open(fileName, 'wb')
pickle.dump(model, pickle_out)
pickle_out.close()
return 0
except Exception as e:
x = str(e)
print('Error: ', x)
return 1

Some of the key snippets from the above scripts are –

x = df_HW_Alphabet.drop('0',axis = 1)
y = df_HW_Alphabet['0']

In the above snippet, we have split the data into images & their corresponding labels.

X_Train, X_Test, Y_Train, Y_Test = train_test_split(x, y, test_size = testRatio)
X_Train, X_Validation, Y_Train, Y_Validation = train_test_split(X_Train, Y_Train, test_size = valRatio)

X_Train = np.reshape(X_Train.values, (X_Train.shape[0], reshapeVal, reshapeVal))
X_Test = np.reshape(X_Test.values, (X_Test.shape[0], reshapeVal, reshapeVal))
X_Validation = np.reshape(X_Validation.values, (X_Validation.shape[0], reshapeVal, reshapeVal))


print("Train Data Shape: ", X_Train.shape)
print("Test Data Shape: ", X_Test.shape)
print("Validation Data shape: ", X_Validation.shape)

We are splitting the data into Train, Test & Validation sets to get more accurate predictions and reshaping the raw data into the image by consuming the 784 data columns to 28×28 pixel images.

Since we are talking about characters, we had to come up with a process of identifying The following snippet will plot the character equivalent number into a matplotlib chart & showcase the overall distribution trend after splitting.

Y_Train_Num = np.int0(y)
count = np.zeros(numOfClasses, dtype='int')
for i in Y_Train_Num:
    count[i] +=1

alphabets = []
for i in word_dict.values():
    alphabets.append(i)

fig, ax = plt.subplots(1,1, figsize=(7,7))
ax.barh(alphabets, count)

plt.xlabel("Number of elements ")
plt.ylabel("Alphabets")
plt.grid()
plt.show(block=False)
plt.pause(sleepTime)
plt.close()

Note that we have tweaked the plt.show property with (block=False). This property will enable us to continue execution without human interventions after the initial pause.

# Model reshaping the training & test dataset
X_Train = X_Train.reshape(X_Train.shape[0],X_Train.shape[1],X_Train.shape[2],1)
print("Shape of Train Data: ", X_Train.shape)

X_Test = X_Test.reshape(X_Test.shape[0], X_Test.shape[1], X_Test.shape[2],1)
print("Shape of Test Data: ", X_Test.shape)

X_Validation = X_Validation.reshape(X_Validation.shape[0], X_Validation.shape[1], X_Validation.shape[2],1)
print("Shape of Validation data: ", X_Validation.shape)

# Converting the labels to categorical values
Y_Train_Catg = to_categorical(Y_Train, num_classes = numOfClasses, dtype='int')
print("Shape of Train Labels: ", Y_Train_Catg.shape)

Y_Test_Catg = to_categorical(Y_Test, num_classes = numOfClasses, dtype='int')
print("Shape of Test Labels: ", Y_Test_Catg.shape)

Y_Validation_Catg = to_categorical(Y_Validation, num_classes = numOfClasses, dtype='int')
print("Shape of validation labels: ", Y_Validation_Catg.shape)

In the above diagram, the application did reshape all three categories of data before calling the primary CNN function.

model = Sequential()

model.add(Conv2D(filters=filterVal1, kernel_size=kernelSize, activation=activationType, input_shape=(28,28,1)))
model.add(MaxPool2D(pool_size=poolSize, strides=stridesVal))

model.add(Conv2D(filters=filterVal2, kernel_size=kernelSize, activation=activationType, padding = paddingVal1))
model.add(MaxPool2D(pool_size=poolSize, strides=stridesVal))

model.add(Conv2D(filters=filterVal3, kernel_size=kernelSize, activation=activationType, padding = paddingVal2))
model.add(MaxPool2D(pool_size=poolSize, strides=stridesVal))

model.add(Flatten())

model.add(Dense(DenkseVal2,activation = activationType))
model.add(Dense(DenkseVal3,activation = activationType))

model.add(Dense(DenkseVal1,activation = activationType2))

model.compile(optimizer = Adam(learning_rate=learningRateVal), loss='categorical_crossentropy', metrics=['accuracy'])
reduce_lr = ReduceLROnPlateau(monitor=monitorVal, factor=factorVal, patience=patienceVal1, min_lr=minLrVal)
early_stop = EarlyStopping(monitor=monitorVal, min_delta=minDeltaVal, patience=patienceVal2, verbose=verboseFlag, mode=modeInd)


fittedModel = model.fit(X_Train, Y_Train_Catg, epochs=epochsVal, callbacks=[reduce_lr, early_stop],  validation_data = (X_Validation,Y_Validation_Catg))

return (model, fittedModel)

In the above snippet, the convolution layers are followed by maxpool layers, which reduce the number of features extracted. The output of the maxpool layers and convolution layers are flattened into a vector of a single dimension and supplied as an input to the Dense layer—the CNN model prepared for training the model using the training dataset.

We have used optimization parameters like Adam, RMSProp & the application we trained for eight epochs for better accuracy & predictions.

# Displaying the accuracies & losses for train & validation set
print("Validation Accuracy :", history.history['val_accuracy'])
print("Training Accuracy :", history.history['accuracy'])
print("Validation Loss :", history.history['val_loss'])
print("Training Loss :", history.history['loss'])

# Displaying the Loss Graph
plt.figure(1)
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.legend(['training','validation'])
plt.title('Loss')
plt.xlabel('epoch')
plt.show(block=False)
plt.pause(sleepTime1)
plt.close()

# Dsiplaying the Accuracy Graph
plt.figure(2)
plt.plot(history.history['accuracy'])
plt.plot(history.history['val_accuracy'])
plt.legend(['training','validation'])
plt.title('Accuracy')
plt.xlabel('epoch')
plt.show(block=False)
plt.pause(sleepTime1)
plt.close()

Also, we have captured the validation Accuracy & Loss & plot them into two separate graphs for better understanding.

try:
    score = model.evaluate(X_Test, Y_Test_Catg, verbose=0)
    print('Test Score = ', score[0])
    print('Test Accuracy = ', score[1])
except Exception as e:
    x = str(e)
    print('Error: ', x)

Also, the application is trying to get the accuracy of the model that we trained & validated with the training & validation data. This time we have used test data to predict the confidence score.

# Displaying some of the test images & their predicted labels
fig, ax = plt.subplots(3,3, figsize=(8,9))
axes = ax.flatten()

for i in range(9):
    axes[i].imshow(np.reshape(X_Test[i], reshapeVal1), cmap="Greys")
    pred = word_dict[np.argmax(Y_Test_Catg[i])]
    print('Prediction: ', pred)
    axes[i].set_title("Test Prediction: " + pred)
    axes[i].grid()
plt.show(block=False)
plt.pause(sleepTime1)
plt.close()

Finally, the application testing with some random test data & tried to plot the output & prediction assessment.

Testing with Random Test Data
fileName = Curr_Path + sep + 'Model' + sep + 'model_trained_' + str(epochsVal) + '.p'
print('Model Name: ', str(fileName))

pickle_out = open(fileName, 'wb')
pickle.dump(model, pickle_out)
pickle_out.close()

As a part of the last step, the application will generate the models using a pickle package & save them under a specific location, which the reader application will use.

3. trainingVisualDataRead.py (Main application that will invoke the training class to predict alphabet through WebCam using Convolutional Neural Network (CNN).)


###############################################
#### Written By: SATYAKI DE ####
#### Written On: 17-Jan-2022 ####
#### Modified On 17-Jan-2022 ####
#### ####
#### Objective: This is the main calling ####
#### python script that will invoke the ####
#### clsAlhpabetReading class to initiate ####
#### teach & perfect the model to read ####
#### visual alphabets using Convolutional ####
#### Neural Network (CNN). ####
###############################################
# We keep the setup code in a different class as shown below.
import clsAlphabetReading as ar
from clsConfig import clsConfig as cf
import datetime
import logging
###############################################
### Global Section ###
###############################################
# Instantiating all the three classes
x1 = ar.clsAlphabetReading()
###############################################
### End of Global Section ###
###############################################
def main():
try:
# Other useful variables
debugInd = 'Y'
var = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
var1 = datetime.datetime.now()
print('Start Time: ', str(var))
# End of useful variables
# Initiating Log Class
general_log_path = str(cf.conf['LOG_PATH'])
# Enabling Logging Info
logging.basicConfig(filename=general_log_path + 'restoreVideo.log', level=logging.INFO)
print('Started Transformation!')
# Execute all the pass
r1 = x1.trainModel(debugInd, var)
if (r1 == 0):
print('Successfully Visual Alphabet Training Completed!')
else:
print('Failed to complete the Visual Alphabet Training!')
var2 = datetime.datetime.now()
c = var2 var1
minutes = c.total_seconds() / 60
print('Total difference in minutes: ', str(minutes))
print('End Time: ', str(var1))
except Exception as e:
x = str(e)
print('Error: ', x)
if __name__ == "__main__":
main()

And the core snippet from the above script is –

x1 = ar.clsAlphabetReading()

Instantiate the main class.

r1 = x1.trainModel(debugInd, var)

The python application will invoke the class & capture the returned value inside the r1 variable.

4. readingVisualData.py (Reading the model to predict Alphabet using WebCAM.)


###############################################
#### Written By: SATYAKI DE ####
#### Written On: 18-Jan-2022 ####
#### Modified On 18-Jan-2022 ####
#### ####
#### Objective: This python script will ####
#### scan the live video feed from the ####
#### web-cam & predict the alphabet that ####
#### read it. ####
###############################################
# We keep the setup code in a different class as shown below.
from clsConfig import clsConfig as cf
import datetime
import logging
import cv2
import pickle
import numpy as np
###############################################
### Global Section ###
###############################################
sep = str(cf.conf['SEP'])
Curr_Path = str(cf.conf['INIT_PATH'])
fileName = str(cf.conf['FILE_NAME'])
epochsVal = int(cf.conf['epochsVal'])
numOfClasses = int(cf.conf['numOfClasses'])
word_dict = cf.conf['word_dict']
width = int(cf.conf['width'])
height = int(cf.conf['height'])
imgSize = cf.conf['imgSize']
threshold = float(cf.conf['threshold'])
imgDimension = cf.conf['imgDimension']
imgSmallDim = cf.conf['imgSmallDim']
imgMidDim = cf.conf['imgMidDim']
reshapeParam1 = int(cf.conf['reshapeParam1'])
reshapeParam2 = int(cf.conf['reshapeParam2'])
colorFeed = cf.conf['colorFeed']
colorPredict = cf.conf['colorPredict']
###############################################
### End of Global Section ###
###############################################
def main():
try:
# Other useful variables
debugInd = 'Y'
var = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
var1 = datetime.datetime.now()
print('Start Time: ', str(var))
# End of useful variables
# Initiating Log Class
general_log_path = str(cf.conf['LOG_PATH'])
# Enabling Logging Info
logging.basicConfig(filename=general_log_path + 'restoreVideo.log', level=logging.INFO)
print('Started Live Streaming!')
cap = cv2.VideoCapture(0)
cap.set(3, width)
cap.set(4, height)
fileName = Curr_Path + sep + 'Model' + sep + 'model_trained_' + str(epochsVal) + '.p'
print('Model Name: ', str(fileName))
pickle_in = open(fileName, 'rb')
model = pickle.load(pickle_in)
while True:
status, img = cap.read()
if status == False:
break
img_copy = img.copy()
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img = cv2.resize(img, imgDimension)
img_copy = cv2.GaussianBlur(img_copy, imgSmallDim, 0)
img_gray = cv2.cvtColor(img_copy, cv2.COLOR_BGR2GRAY)
bin, img_thresh = cv2.threshold(img_gray, 100, 255, cv2.THRESH_BINARY_INV)
img_final = cv2.resize(img_thresh, imgMidDim)
img_final = np.reshape(img_final, (reshapeParam1,reshapeParam2,reshapeParam2,reshapeParam1))
img_pred = word_dict[np.argmax(model.predict(img_final))]
# Extracting Probability Values
Predict_X = model.predict(img_final)
probVal = round(np.amax(Predict_X) * 100)
cv2.putText(img, "Live Feed : (" + str(probVal) + "%) ", (20,25), cv2.FONT_HERSHEY_TRIPLEX, 0.7, color = colorFeed)
cv2.putText(img, "Prediction: " + img_pred, (20,410), cv2.FONT_HERSHEY_DUPLEX, 1.3, color = colorPredict)
cv2.imshow("Original Image", img)
if cv2.waitKey(1) & 0xFF == ord('q'):
r1=0
break
if (r1 == 0):
print('Successfully Alphabets predicted!')
else:
print('Failed to predict alphabet!')
var2 = datetime.datetime.now()
c = var2 var1
minutes = c.total_seconds() / 60
print('Total Run Time in minutes: ', str(minutes))
print('End Time: ', str(var1))
except Exception as e:
x = str(e)
print('Error: ', x)
if __name__ == "__main__":
main()

And the key snippet from the above code is –

cap = cv2.VideoCapture(0)
cap.set(3, width)
cap.set(4, height)

The application is reading the live video data from WebCAM. Also, set out the height & width for the video output.

fileName = Curr_Path + sep + 'Model' + sep + 'model_trained_' + str(epochsVal) + '.p'
print('Model Name: ', str(fileName))

pickle_in = open(fileName, 'rb')
model = pickle.load(pickle_in)

The application reads the model output generated as part of the previous script using the pickle package.

while True:
    status, img = cap.read()

    if status == False:
        break

The application will read the WebCAM & it exits if there is an end of video transmission or some kind of corrupt video frame.

img_copy = img.copy()

img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img = cv2.resize(img, imgDimension)

img_copy = cv2.GaussianBlur(img_copy, imgSmallDim, 0)
img_gray = cv2.cvtColor(img_copy, cv2.COLOR_BGR2GRAY)
bin, img_thresh = cv2.threshold(img_gray, 100, 255, cv2.THRESH_BINARY_INV)

img_final = cv2.resize(img_thresh, imgMidDim)
img_final = np.reshape(img_final, (reshapeParam1,reshapeParam2,reshapeParam2,reshapeParam1))


img_pred = word_dict[np.argmax(model.predict(img_final))]

We have initially cloned the original video frame & then it converted from BGR2GRAYSCALE while applying the threshold on it doe better prediction outcomes. Then the image has resized & reshaped for model input. Finally, the np.argmax function extracted the class index with the highest predicted probability. Furthermore, it is translated using the word_dict dictionary to an Alphabet & displayed on top of the Live View.

# Extracting Probability Values
Predict_X = model.predict(img_final)
probVal = round(np.amax(Predict_X) * 100)

Also, derive the confidence score of that probability & display that on top of the Live View.

if cv2.waitKey(1) & 0xFF == ord('q'):
    r1=0
    break

The above code will let the developer exit from this application by pressing the “Esc” or “q”-key from the keyboard & the program will terminate.


So, we’ve done it.

You will get the complete codebase in the following Github link.

I’ll bring some more exciting topic in the coming days from the Python verse. Please share & subscribe my post & let me know your feedback.

Till then, Happy Avenging! 😀

Note: All the data & scenario posted here are representational data & scenarios & available over the internet & for educational purpose only. Some of the images (except my photo) that we’ve used are available over the net. We don’t claim the ownership of these images. There is an always room for improvement & especially the prediction quality of Alphabet.

Canada’s Covid19 analysis based on Logistic Regression

Hi Guys,

Today, I’ll be demonstrating some scenarios based on open-source data from Canada. In this post, I will only explain some of the significant parts of the code. Not the entire range of scripts here.

Let’s explore a couple of sample source data –

2. Sample Input Data

I would like to explore how much this disease caused an impact on the elderly in Canada.

Let’s explore the source directory structure –

3. Source Directory Structures

For this, you need to install the following packages –

pip install pandas

pip install seaborn

Please find the PyPi link given below –

In this case, we’ve downloaded the data from Canada’s site. However, they have created API. So, you can consume the data through that way as well. Since the volume is a little large. I decided to download that in CSV & then use that for my analysis.

Before I start, let me explain a couple of critical assumptions that I had to make due to data impurities or availabilities.

  • If there is no data available for a specific case, my application will consider that patient as COVID-Active.
  • We will consider the patient is affected through Community-spreading until we have data to find it otherwise.
  • If there is no data available for gender, we’re marking these records as “Other.” So, that way, we’re making it into that category, where the patient doesn’t want to disclose their sexual orientation.
  • If we don’t have any data, then by default, the application is considering the patient is alive.
  • Lastly, my application considers the middle point of the age range data for all the categories, i.e., the patient’s age between 20 & 30 will be considered as 25.

1. clsCovidAnalysisByCountryAdv (This is the main script, which will invoke the Machine-Learning API & return 0 if successful.)

##############################################
#### Written By: SATYAKI DE               ####
#### Written On: 01-Jun-2020              ####
#### Modified On 01-Jun-2020              ####
####                                      ####
#### Objective: Main scripts for Logistic ####
#### Regression.                          ####
##############################################

import pandas as p
import clsL as log
import datetime

import matplotlib.pyplot as plt
import seaborn as sns
from clsConfig import clsConfig as cf

# %matplotlib inline -- for Jupyter Notebook
class clsCovidAnalysisByCountryAdv:
    def __init__(self):
        self.fileName_1 = cf.config['FILE_NAME_1']
        self.fileName_2 = cf.config['FILE_NAME_2']
        self.Ind = cf.config['DEBUG_IND']
        self.subdir = str(cf.config['LOG_DIR_NAME'])

    def setDefaultActiveCases(self, row):
        try:
            str_status = str(row['case_status'])

            if str_status == 'Not Reported':
                return 'Active'
            else:
                return str_status
        except:
            return 'Active'

    def setDefaultExposure(self, row):
        try:
            str_exposure = str(row['exposure'])

            if str_exposure == 'Not Reported':
                return 'Community'
            else:
                return str_exposure
        except:
            return 'Community'

    def setGender(self, row):
        try:
            str_gender = str(row['gender'])

            if str_gender == 'Not Reported':
                return 'Other'
            else:
                return str_gender
        except:
            return 'Other'

    def setSurviveStatus(self, row):
        try:
            # 0 - Deceased
            # 1 - Alive
            str_active = str(row['ActiveCases'])

            if str_active == 'Deceased':
                return 0
            else:
                return 1
        except:
            return 1

    def getAgeFromGroup(self, row):
        try:
            # We'll take the middle of the Age group
            # If a age range falls with 20, we'll
            # consider this as 10.
            # Similarly, a age group between 20 & 30,
            # should reflect by 25.
            # Anything above 80 will be considered as
            # 85

            str_age_group = str(row['AgeGroup'])

            if str_age_group == '<20':
                return 10
            elif str_age_group == '20-29':
                return 25
            elif str_age_group == '30-39':
                return 35
            elif str_age_group == '40-49':
                return 45
            elif str_age_group == '50-59':
                return 55
            elif str_age_group == '60-69':
                return 65
            elif str_age_group == '70-79':
                return 75
            else:
                return 85
        except:
            return 100

    def predictResult(self):
        try:
            
            # Initiating Logging Instances
            clog = log.clsL()

            # Important variables
            var = datetime.datetime.now().strftime(".%H.%M.%S")
            print('Target File Extension will contain the following:: ', var)
            Ind = self.Ind
            subdir = self.subdir

            #######################################
            #                                     #
            # Using Logistic Regression to        #
            # Idenitfy the following scenarios -  #
            #                                     #
            # Age wise Infection Vs Deaths        #
            #                                     #
            #######################################
            inputFileName_2 = self.fileName_2

            # Reading from Input File
            df_2 = p.read_csv(inputFileName_2)

            # Fetching only relevant columns
            df_2_Mod = df_2[['date_reported','age_group','gender','exposure','case_status']]
            df_2_Mod['State'] = df_2['province_abbr']

            print()
            print('Projecting 2nd file sample rows: ')
            print(df_2_Mod.head())

            print()
            x_row_1 = df_2_Mod.shape[0]
            x_col_1 = df_2_Mod.shape[1]

            print('Total Number of Rows: ', x_row_1)
            print('Total Number of columns: ', x_col_1)

            #########################################################################################
            # Few Assumptions                                                                       #
            #########################################################################################
            # By default, if there is no data on exposure - We'll treat that as community spreading #
            # By default, if there is no data on case_status - We'll consider this as active        #
            # By default, if there is no data on gender - We'll put that under a separate Gender    #
            # category marked as the "Other". This includes someone who doesn't want to identify    #
            # his/her gender or wants to be part of LGBT community in a generic term.               #
            #                                                                                       #
            # We'll transform our data accordingly based on the above logic.                        #
            #########################################################################################
            df_2_Mod['ActiveCases'] = df_2_Mod.apply(lambda row: self.setDefaultActiveCases(row), axis=1)
            df_2_Mod['ExposureStatus'] = df_2_Mod.apply(lambda row: self.setDefaultExposure(row), axis=1)
            df_2_Mod['Gender'] = df_2_Mod.apply(lambda row: self.setGender(row), axis=1)

            # Filtering all other records where we don't get any relevant information
            # Fetching Data for
            df_3 = df_2_Mod[(df_2_Mod['age_group'] != 'Not Reported')]

            # Dropping unwanted columns
            df_3.drop(columns=['exposure'], inplace=True)
            df_3.drop(columns=['case_status'], inplace=True)
            df_3.drop(columns=['date_reported'], inplace=True)
            df_3.drop(columns=['gender'], inplace=True)

            # Renaming one existing column
            df_3.rename(columns={"age_group": "AgeGroup"}, inplace=True)

            # Creating important feature
            # 0 - Deceased
            # 1 - Alive
            df_3['Survived'] = df_3.apply(lambda row: self.setSurviveStatus(row), axis=1)

            clog.logr('2.df_3' + var + '.csv', Ind, df_3, subdir)

            print()
            print('Projecting Filter sample rows: ')
            print(df_3.head())

            print()
            x_row_2 = df_3.shape[0]
            x_col_2 = df_3.shape[1]

            print('Total Number of Rows: ', x_row_2)
            print('Total Number of columns: ', x_col_2)

            # Let's do some basic checkings
            sns.set_style('whitegrid')
            #sns.countplot(x='Survived', hue='Gender', data=df_3, palette='RdBu_r')

            # Fixing Gender Column
            # This will check & indicate yellow for missing entries
            #sns.heatmap(df_3.isnull(), yticklabels=False, cbar=False, cmap='viridis')

            #sex = p.get_dummies(df_3['Gender'], drop_first=True)
            sex = p.get_dummies(df_3['Gender'])
            df_4 = p.concat([df_3, sex], axis=1)

            print('After New addition of columns: ')
            print(df_4.head())

            clog.logr('3.df_4' + var + '.csv', Ind, df_4, subdir)

            # Dropping unwanted columns for our Machine Learning
            df_4.drop(columns=['Gender'], inplace=True)
            df_4.drop(columns=['ActiveCases'], inplace=True)
            df_4.drop(columns=['Male','Other','Transgender'], inplace=True)

            clog.logr('4.df_4_Mod' + var + '.csv', Ind, df_4, subdir)

            # Fixing Spread Columns
            spread = p.get_dummies(df_4['ExposureStatus'], drop_first=True)
            df_5 = p.concat([df_4, spread], axis=1)

            print('After Spread columns:')
            print(df_5.head())

            clog.logr('5.df_5' + var + '.csv', Ind, df_5, subdir)

            # Dropping unwanted columns for our Machine Learning
            df_5.drop(columns=['ExposureStatus'], inplace=True)

            clog.logr('6.df_5_Mod' + var + '.csv', Ind, df_5, subdir)

            # Fixing Age Columns
            df_5['Age'] = df_5.apply(lambda row: self.getAgeFromGroup(row), axis=1)
            df_5.drop(columns=["AgeGroup"], inplace=True)

            clog.logr('7.df_6' + var + '.csv', Ind, df_5, subdir)

            # Fixing Dummy Columns Name
            # Renaming one existing column Travel-Related with Travel_Related
            df_5.rename(columns={"Travel-Related": "TravelRelated"}, inplace=True)

            clog.logr('8.df_7' + var + '.csv', Ind, df_5, subdir)

            # Removing state for temporary basis
            df_5.drop(columns=['State'], inplace=True)
            # df_5.drop(columns=['State','Other','Transgender','Pending','TravelRelated','Male'], inplace=True)

            # Casting this entire dataframe into Integer
            # df_5_temp.apply(p.to_numeric)

            print('Info::')
            print(df_5.info())
            print("*" * 60)
            print(df_5.describe())
            print("*" * 60)

            clog.logr('9.df_8' + var + '.csv', Ind, df_5, subdir)

            print('Intermediate Sample Dataframe for Age::')
            print(df_5.head())

            # Plotting it to Graph
            sns.jointplot(x="Age", y='Survived', data=df_5)
            sns.jointplot(x="Age", y='Survived', data=df_5, kind='kde', color='red')
            plt.xlabel("Age")
            plt.ylabel("Data Point (0 - Died   Vs    1 - Alive)")

            # Another check with Age Group
            sns.countplot(x='Survived', hue='Age', data=df_5, palette='RdBu_r')
            plt.xlabel("Survived(0 - Died   Vs    1 - Alive)")
            plt.ylabel("Total No Of Patient")

            df_6 = df_5.drop(columns=['Survived'], axis=1)

            clog.logr('10.df_9' + var + '.csv', Ind, df_6, subdir)

            # Train & Split Data
            x_1 = df_6
            y_1 = df_5['Survived']

            # Now Train-Test Split of your source data
            from sklearn.model_selection import train_test_split

            # test_size => % of allocated data for your test cases
            # random_state => A specific set of random split on your data
            X_train_1, X_test_1, Y_train_1, Y_test_1 = train_test_split(x_1, y_1, test_size=0.3, random_state=101)

            # Importing Model
            from sklearn.linear_model import LogisticRegression

            logmodel = LogisticRegression()
            logmodel.fit(X_train_1, Y_train_1)

            # Adding Predictions to it
            predictions_1 = logmodel.predict(X_test_1)

            from sklearn.metrics import classification_report

            print('Classification Report:: ')
            print(classification_report(Y_test_1, predictions_1))

            from sklearn.metrics import confusion_matrix

            print('Confusion Matrix:: ')
            print(confusion_matrix(Y_test_1, predictions_1))

            # This is require when you are trying to print from conventional
            # front & not using Jupyter notebook.
            plt.show()

            return 0

        except Exception  as e:
            x = str(e)
            print('Error : ', x)

            return 1

Key snippets from the above script –

df_2_Mod['ActiveCases'] = df_2_Mod.apply(lambda row: self.setDefaultActiveCases(row), axis=1)
df_2_Mod['ExposureStatus'] = df_2_Mod.apply(lambda row: self.setDefaultExposure(row), axis=1)
df_2_Mod['Gender'] = df_2_Mod.apply(lambda row: self.setGender(row), axis=1)

# Filtering all other records where we don't get any relevant information
# Fetching Data for
df_3 = df_2_Mod[(df_2_Mod['age_group'] != 'Not Reported')]

# Dropping unwanted columns
df_3.drop(columns=['exposure'], inplace=True)
df_3.drop(columns=['case_status'], inplace=True)
df_3.drop(columns=['date_reported'], inplace=True)
df_3.drop(columns=['gender'], inplace=True)

# Renaming one existing column
df_3.rename(columns={"age_group": "AgeGroup"}, inplace=True)

# Creating important feature
# 0 - Deceased
# 1 - Alive
df_3['Survived'] = df_3.apply(lambda row: self.setSurviveStatus(row), axis=1)

The above lines point to the critical transformation areas, where the application is invoking various essential business logic.

Let’s see at this moment our sample data –

6. 4_4_mod

Let’s look into the following part –

# Fixing Spread Columns
spread = p.get_dummies(df_4['ExposureStatus'], drop_first=True)
df_5 = p.concat([df_4, spread], axis=1)

The above lines will transform the data into this –

7. 5_5_Mod

As you can see, we’ve transformed the row values into columns with binary values. This kind of transformation is beneficial.

# Plotting it to Graph
sns.jointplot(x="Age", y='Survived', data=df_5)
sns.jointplot(x="Age", y='Survived', data=df_5, kind='kde', color='red')
plt.xlabel("Age")
plt.ylabel("Data Point (0 - Died   Vs    1 - Alive)")

# Another check with Age Group
sns.countplot(x='Survived', hue='Age', data=df_5, palette='RdBu_r')
plt.xlabel("Survived(0 - Died   Vs    1 - Alive)")
plt.ylabel("Total No Of Patient")

The above lines will process the data & visualize based on that.

x_1 = df_6
y_1 = df_5['Survived']

In the above snippet, we’ve assigned the features & target variable for our final logistic regression model.

# Now Train-Test Split of your source data
from sklearn.model_selection import train_test_split

# test_size => % of allocated data for your test cases
# random_state => A specific set of random split on your data
X_train_1, X_test_1, Y_train_1, Y_test_1 = train_test_split(x_1, y_1, test_size=0.3, random_state=101)

# Importing Model
from sklearn.linear_model import LogisticRegression

logmodel = LogisticRegression()
logmodel.fit(X_train_1, Y_train_1)

In the above snippet, we’re splitting the primary data & create a set of test & train data. Once we have the collection, the application will put the logistic regression model. And, finally, we’ll fit the training data.

# Adding Predictions to it
predictions_1 = logmodel.predict(X_test_1)

from sklearn.metrics import classification_report

print('Classification Report:: ')
print(classification_report(Y_test_1, predictions_1))

The above lines, finally use the model & then we feed our test data.

Let’s see how it runs –

5.1.Run_Windows
5.2. Run_Windows

And, here is the log directory –

4. Logs

For better understanding, I’m just clubbing both the diagram at one place & the final outcome is showing as follows –

1. MergeReport

So, from the above picture, we can see that the maximum vulnerable patients are patients who are 80+. The next two categories that also suffered are 70+ & 60+.

Also, We’ve checked the Female Vs. Male in the following code –

sns.countplot(x='Survived', hue='Female', data=df_5, palette='RdBu_r')
plt.xlabel("Survived(0 - Died   Vs    1 - Alive)")
plt.ylabel("Female Vs Male (Including Other Genders)")

And, the analysis represents through this –

8. Female_Male

In this case, you have to consider that the Male part includes all the other genders apart from the actual Male. Hence, I believe death for females would be more compared to people who identified themselves as males.

So, finally, we’ve done it.

During this challenging time, I would request you to follow strict health guidelines & stay healthy.

N.B.: All the data that are used here can be found in the public domain. We use this solely for educational purposes. You can find the details here.

Pandas, Numpy, Encryption/Decryption, Hidden Files In Python (Crossover between Space Stone, Reality Stone & Mind Stone of Python-Verse)

So, here we come up with another crossover of Space Stone, Reality Stone & Mind Stone of Python-Verse. It is indeed exciting & I cannot wait to explore that part further. Today, in this post, we’ll see how one application can integrate all these key ingredients in Python to serve the purpose. Our key focus will be involving popular packages like Pandas, Numpy & Popular Encryption-Decryption techniques, which include some hidden files as well.

So, our objective here is to proceed with the encryption & decryption technique. But, there is a catch. We need to store some salt or tokenized value inside a hidden file. Our application will extract the salt value from it & then based on that it will perform Encrypt/Decrypt on the data.

Why do we need this approach?

The answer is simple. On many occasions, we don’t want to store our right credentials in configuration files. Also, we don’t want to keep our keys to open to other developers. There are many ways you can achieve this kind of security.  Today, I’ll be showing a different approach to make the same.

Let’s explore.

As usual, I’ll provide the solution, which is tested in Windows & MAC & provide the script. Also, I’ll explain the critical lines of those scripts to understand it from a layman point of view. And, I won’t explain any script, which I’ve already explained in my earlier post. So, you have to refer my old post for that.

To encrypt & decrypt, we need the following files, which contains credentials in a csv. Please find the sample data –

Config_orig.csv

Orig_File

Please see the file, which will be hidden by the application process.

Token_Salt_File

As you can see, this column contains the salt, which will be used in our Encryption/Decryption.

1. clsL.py (This script will create the csv files or any intermediate debug csv file after the corresponding process. Hence, the name comes into the picture.)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
###########################################
#### Written By: SATYAKI DE        ########
#### Written On: 25-Jan-2019       ########
####                               ########
#### Objective: Log File           ########
###########################################
import pandas as p
import platform as pl
from clsParam import clsParam as cf

class clsL(object):
    def __init__(self):
        self.path = cf.config['PATH']

    def logr(self, Filename, Ind, df, subdir=None):
        try:
            x = p.DataFrame()
            x = df
            sd = subdir

            os_det = pl.system()

            if sd == None:
                if os_det == "Windows":
                    fullFileName = self.path + '\\' + Filename
                else:
                    fullFileName = self.path + '/' + Filename
            else:
                if os_det == "Windows":
                    fullFileName = self.path + '\\' + sd + "\\" + Filename
                else:
                    fullFileName = self.path + '/' + sd + "/" + Filename

            if Ind == 'Y':
                x.to_csv(fullFileName, index=False)

            return 0

        except Exception as e:
            y = str(e)
            print(y)
            return 3

2. clsParam.py (This is the script that will be used as a parameter file & will be used in other python scripts.)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
###########################################
#### Written By: SATYAKI DE        ########
#### Written On: 25-Jan-2019       ########
#### Objective: Parameter File     ########
###########################################

import os
import platform as pl

class clsParam(object):

    config = {
        'FILENAME' : 'test.amca',
        'OSX_MOD_FILE_NM': '.test.amca',
        'CURR_PATH': os.path.dirname(os.path.realpath(__file__)),
        'NORMAL_FLAG': 32,
        'HIDDEN_FLAG': 34,
        'OS_DET': pl.system()
    }

 

3. clsWinHide.py (This script contains the core logic of hiding/unhiding a file under Windows OS. Hence, the name comes into the picture.)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
###########################################
#### Written By: SATYAKI DE          ######
#### Written On: 25-Jan-2019         ######
####                                 ######
#### This script will hide or Unhide ######
#### Files in Windows.               ######
###########################################

import win32file
import win32con
from clsParam import clsParam as cp

class clsWinHide(object):
    def __init__(self):
        self.path = cp.config['CURR_PATH']
        self.FileName = cp.config['FILENAME']
        self.normal_file_flag = cp.config['NORMAL_FLAG']

    def doit(self):
        try:
            path = self.path
            FileName = self.FileName

            FileNameWithPath = path + '\\' + FileName
            flags = win32file.GetFileAttributesW(FileNameWithPath)
            win32file.SetFileAttributes(FileNameWithPath,win32con.FILE_ATTRIBUTE_HIDDEN | flags)

            return 0
        except Exception as e:
            x = str(e)
            print(x)

            return 1

    def undoit(self):
        try:
            path = self.path
            FileName = self.FileName
            normal_file_flag = self.normal_file_flag

            FileNameWithPath = path + '\\' + FileName
            win32file.SetFileAttributes(FileNameWithPath,win32con.FILE_ATTRIBUTE_NORMAL | int(normal_file_flag))

            return 0
        except Exception as e:
            x = str(e)
            print(x)

            return 1

Key lines that we would like to explore are as follows –

def doit()

flags = win32file.GetFileAttributesW(FileNameWithPath)
win32file.SetFileAttributes(FileNameWithPath,win32con.FILE_ATTRIBUTE_HIDDEN | flags)

The above two lines under doit() functions are changing the file attributes in Windows OS to the hidden mode by assigning the FILE_ATTRIBUTE_HIDDEN property.

def undoit()

normal_file_flag = self.normal_file_flag

FileNameWithPath = path + '\\' + FileName
win32file.SetFileAttributes(FileNameWithPath,win32con.FILE_ATTRIBUTE_NORMAL | int(normal_file_flag))

As the script suggested, the application is setting the file attribute of a hidden file to FILE_ATTRIBUTE_NORMAL & set the correct flag from parameters, which leads to the file appears as a normal windows file.

4. clsOSXHide.py (This script contains the core logic of hiding/unhiding a file under OSX, i.e., MAC OS. Hence, the name comes into the picture.)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
###########################################
#### Written By: SATYAKI DE           #####
#### Written On: 25-Jan-2019          #####
####                                  #####
#### Objective: This script will hide #####
#### or Unhide the file in OSX.       #####
###########################################

import os
from clsParam import clsParam as cp

class clsOSXHide(object):
    def __init__(self):
        self.path = cp.config['CURR_PATH']
        self.FileName = cp.config['FILENAME']
        self.OSX_Mod_FileName = cp.config['OSX_MOD_FILE_NM']
        self.normal_file_flag = cp.config['NORMAL_FLAG']

    def doit(self):
        try:
            path = self.path
            FileName = self.FileName

            FileNameWithPath = path + '/' + FileName
            os.rename(FileNameWithPath, os.path.join(os.path.dirname(FileNameWithPath),'.'
                                                     + os.path.basename(FileNameWithPath)))

            return 0
        except Exception as e:
            x = str(e)
            print(x)

            return 1

    def undoit(self):
        try:
            path = self.path
            FileName = self.FileName
            OSX_Mod_FileName = self.OSX_Mod_FileName

            FileNameWithPath = path + '/' + FileName
            os.rename(OSX_Mod_FileName, FileNameWithPath)

            return 0
        except Exception as e:
            x = str(e)
            print(x)

            return 1

The key lines that we’ll be exploring here are as follows –

def doit()

FileNameWithPath = path + '/' + FileName
os.rename(FileNameWithPath, os.path.join(os.path.dirname(FileNameWithPath),'.'
                                         + os.path.basename(FileNameWithPath)))

In MAC or Linux, any file starts with ‘.’ will be considered as a hidden file. Hence, we’re changing the file type by doing this manipulation.

def undoit()

OSX_Mod_FileName = self.OSX_Mod_FileName

FileNameWithPath = path + '/' + FileName
os.rename(OSX_Mod_FileName, FileNameWithPath)

In this case, our application simply renaming a file with its the original file to get the file as a normal file.

Let’s understand that in Linux or MAC, you have a lot of other ways to restrict any files as it has much more granular level access control.  But, I thought, why not take a slightly different & fun way to achieve the same. After all, we’re building an Infinity War for Python verse. A little bit of fun will certainly make some sense. 🙂

5. clsProcess.py (This script will invoke any of the hide scripts, i.e. clsWinHide.py or clsOSXHide.py based on the OS platform. Hence, the name comes into the picture.)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
###########################################
#### Written By: SATYAKI DE          ######
#### Written On: 25-Jan-2019         ######
####                                 ######
#### Objective: Based on the OS, this######
#### script calls the actual script. ######
###########################################

from clsParam import clsParam as cp

plat_det = cp.config['OS_DET']

# Based on the platform
# Application is loading subprocess
# in order to avoid library missing
# case against cross platform

if plat_det == "Windows":
    import clsWinHide as win
else:
    import clsOSXHide as osx

# End of conditional class load

class clsProcess(object):
    def __init__(self):
        self.os_det = plat_det

    def doit(self):
        try:

            os_det = self.os_det
            print("OS Info: ", os_det)

            if os_det == "Windows":
                win_doit = win.clsWinHide()
                ret_val = win_doit.doit()
            else:
                osx_doit = osx.clsOSXHide()
                ret_val = osx_doit.doit()

            return ret_val
        except Exception as e:
            x = str(e)
            print(x)

            return 1

    def undoit(self):
        try:

            os_det = self.os_det
            print("OS Info: ", os_det)

            if os_det == "Windows":
                win_doit = win.clsWinHide()
                ret_val = win_doit.undoit()
            else:
                osx_doit = osx.clsOSXHide()
                ret_val = osx_doit.undoit()

            return ret_val
        except Exception as e:
            x = str(e)
            print(x)

            return 1

Key lines to explores are as follows –

from clsParam import clsParam as cp

plat_det = cp.config['OS_DET']

# Based on the platform
# Application is loading subprocess
# in order to avoid library missing
# case against cross platform

if plat_det == "Windows":
    import clsWinHide as win
else:
    import clsOSXHide as osx

This step is very essential to run the same python scripts in both the environments, e.g. in this case like MAC & Windows.

So, based on the platform details, which the application is getting from the clsParam class, it is loading the specific class to the application. And why it is so important.

Under Windows OS, this will work if you load both the class. But, under MAC, this will fail as the first program will try to load all the libraries & it may happen that the pywin32/pypiwin32 package might not available under MAC. Anyway, you are not even using that package. So, this conditional class loading is significant.

os_det = self.os_det
print("OS Info: ", os_det)

if os_det == "Windows":
    win_doit = win.clsWinHide()
    ret_val = win_doit.doit()
else:
    osx_doit = osx.clsOSXHide()
    ret_val = osx_doit.doit()

As you can see that, based on the OS, it is invoking the correct function of that corresponding class.

6. clsEnDec.py (This script will read the credentials from a csv file & then based on the salt captured from the hidden file, it will either encrypt or decrypt the content. Hence, the name comes into the picture.)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
###########################################
#### Written By: SATYAKI DE        ########
#### Written On: 25-Jan-2019       ########
#### Package Cryptography needs to ########
#### install in order to run this  ########
#### script.                       ########
####                               ########
#### Objective: This script will   ########
#### encrypt/decrypt based on the  ########
#### hidden supplied salt value.   ########
###########################################

import pandas as p
from cryptography.fernet import Fernet

class clsEnDec(object):

    def __init__(self, token):
        # Calculating Key
        self.token = token

    def encrypt_str(self):
        try:
            # Capturing the Salt Information
            salt = self.token
            # Fetching the content of lookup file
            df_orig = p.read_csv('Config_orig.csv', index_col=False)

            # Checking Individual Types inside the Dataframe
            cipher = Fernet(salt)

            df_orig['User'] = df_orig['User'].apply(lambda x1: cipher.encrypt(bytes(x1,'utf8')))
            df_orig['Pwd'] = df_orig['Pwd'].apply(lambda x2: cipher.encrypt(bytes(x2,'utf8')))

            # Writing to the File
            df_orig.to_csv('Encrypt_Config.csv', index=False)

            return 0
        except Exception as e:
            x = str(e)
            print(x)
            return 1

    def decrypt_str(self):
        try:
            # Capturing the Salt Information
            salt = self.token
            # Checking Individual Types inside the Dataframe
            cipher = Fernet(salt)

            # Fetching the Encrypted csv file
            df_orig = p.read_csv('Encrypt_Config.csv', index_col=False)

            df_orig['User'] = df_orig['User'].apply(lambda x1: str(cipher.decrypt(bytes(x1[2:-1],'utf8'))).replace("b'","").replace("'",""))
            df_orig['Pwd'] = df_orig['Pwd'].apply(lambda x2: str(cipher.decrypt(bytes(x2[2:-1],'utf8'))).replace("b'","").replace("'",""))

            # Writing to the file
            df_orig.to_csv('Decrypt_Config.csv', index=False)

            return 0
        except Exception as e:
            x = str(e)
            print(x)
            return 1

Key lines from this script are as follows –

def encrypt_str()

# Checking Individual Types inside the Dataframe
cipher = Fernet(salt)

df_orig['User'] = df_orig['User'].apply(lambda x1: cipher.encrypt(bytes(x1,'utf8')))
df_orig['Pwd'] = df_orig['Pwd'].apply(lambda x2: cipher.encrypt(bytes(x2,'utf8')))

So, once you captured the salt from that hidden file, the application is capturing that value over here. And, based on that both the field will be encrypted. But, note that cryptography package is required for this. And, you need to pass bytes value to work this thing. Hence, we’ve used bytes() function over here.

def decrypt_str()

cipher = Fernet(salt)

# Fetching the Encrypted csv file
df_orig = p.read_csv('Encrypt_Config.csv', index_col=False)

df_orig['User'] = df_orig['User'].apply(lambda x1: str(cipher.decrypt(bytes(x1[2:-1],'utf8'))).replace("b'","").replace("'",""))
df_orig['Pwd'] = df_orig['Pwd'].apply(lambda x2: str(cipher.decrypt(bytes(x2[2:-1],'utf8'))).replace("b'","").replace("'",""))

Again, in this step, our application is extracting the salt & then it retrieves the encrypted values of corresponding fields & applies the decryption logic on top of it. Note that, since we need to pass bytes value to get it to work. Hence, your output will be appended with (b’xxxxx’). To strip that, we’ve used the replace() functions. You can use regular expression using pattern matching as well.

7. callEnDec.py (This script will create the split csv files or final merge file after the corresponding process. However, this can be used as normal verbose debug logging as well. Hence, the name comes into the picture.)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
###########################################
#### Written By: SATYAKI DE           #####
#### Written On: 25-Jan-2019          #####
####                                  #####
#### Objective: Main calling function #####
###########################################

import clsEnDec as ed
import clsProcess as h
from clsParam import clsParam as cp
import time as t
import pandas as p

def main():
    print("")
    print("#" * 60)
    print("Calling (Encryption/Decryption) Package!!")
    print("#" * 60)
    print("")

    # Unhiding the file
    x = h.clsProcess()
    ret_val_unhide = x.undoit()

    if ret_val_unhide == 0:
        print("Successfully Unhide the file!")
    else:
        print("Unsuccessful to Unhide the file!")

    # To See the Unhide file
    t.sleep(10)

    print("*" * 60)
    print("Proceeding with Encryption...")
    print("*" * 60)

    # Getting Salt Value from the hidden files
    # by temporarily making it available
    FileName = cp.config['FILENAME']
    df = p.read_csv(FileName, index_col=False)
    salt = str(df.iloc[0]['Token_Salt'])
    print("-" * 60)
    print("Salt: ", salt)
    print("-" * 60)

    # Calling the Encryption Method
    x = ed.clsEnDec(salt)
    ret_val = x.encrypt_str()

    if ret_val == 0:
        print("Encryption Successful!")
    else:
        print("Encryption Failure!")

    print("")
    print("*" * 60)
    print("Checking Decryption Now...")
    print("*" * 60)

    # Calling the Decryption Method
    ret_val1 = x.decrypt_str()

    if ret_val1 == 0:
        print("Decryption Successful!")
    else:
        print("Decryption Failure!")

    # Hiding the salt file
    x = h.clsProcess()
    ret_val_hide = x.doit()

    if ret_val_hide == 0:
        print("Successfully Hide the file!")
    else:
        print("Unsuccessful to Hide the file!")

    print("*" * 60)
    print("Operation Done!")
    print("*" * 60)

if __name__ == '__main__':
    main()

And, here comes the final calling methods.

The key lines that we would like to discuss –

# Getting Salt Value from the hidden files
# by temporarily making it available
FileName = cp.config['FILENAME']
df = p.read_csv(FileName, index_col=False)
salt = str(df.iloc[0]['Token_Salt'])

As I’ve shown that, we have our hidden files that contain only 1 row & 1 column. To extract the specific value we’ve used iloc with the row number as 0 along with the column name, i.e. Token_Salt.

Now, let’s see how it runs –

Windows (64 bit):

Win_Run

Mac (32 bit):

MAC_Run

So, from the screenshot, we can see our desired output & you can calculate the aggregated value based on our sample provided in the previous screenshot.

Let’s check the Encrypted & Decrypted values –

Encrypted Values (Encrypt_Config.csv):

Encrypted_File

Decrypted Values (Decrypt_Config.csv):

Decrypted_File

So, finally, we’ve achieved our target.

I hope this will give you some more idea about more insights into the Python verse. Let me know – how do you think about this post.

Till then – Happy Avenging!