Category: natural-language

##############################################
#### 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