import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score

training_set = pd.read_csv('/content/Facebook_Ads_2.csv',encoding='ISO-8859-1')

training_set.head()

click = training_set[training_set['Clicked'] == 1 ]
no_click = training_set[training_set['Clicked'] == 0]


click.head()

# no_click.head()

print("Total = ",len(training_set))
print("Click = ",len(click))
print("No click = ",len(no_click))

print("% who not clicked ", 1.*len(no_click)/len(training_set)*100.0,"%")
print("% who clicked ", 1.*len(click)/len(training_set)*100.0,"%")

training_set.Clicked.value_counts().plot(kind='bar')
training_set.Clicked.value_counts().plot(kind='pie')
sns.scatterplot(x='Time Spent on Site', y='Salary', hue='Clicked', data=training_set)
plt.figure(figsize=(5,5))
sns.boxplot(x='Clicked', y='Salary',data= training_set)

training_set.drop(['Names','emails','Country'],axis=1,inplace=True)

training_set.head()

x = training_set.drop('Clicked',axis=1).values
y = training_set['Clicked'].values

from sklearn.preprocessing import StandardScaler

sc = StandardScaler()
x = sc.fit_transform(x)

from sklearn.model_selection import train_test_split

x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.2,random_state=0)

from sklearn.linear_model import LogisticRegression

classifier = LogisticRegression(random_state = 0)
classifier.fit(x_train, y_train)

y_predict_train = classifier.predict(x_train)
y_predict_train
y_predict_test = classifier.predict(x_test)
y_predict_test

from sklearn.metrics import classification_report, confusion_matrix

cm = confusion_matrix(y_test, y_predict_test)
sns.heatmap(cm, annot=True, fmt='d')

from sklearn.metrics import classification_report

print(classification_report(y_test, y_predict_test))