# Importation des librairies
#%matplotlib
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
from matplotlib.colors import ListedColormap
from mpl_toolkits.mplot3d import Axes3D
import seaborn as sns
import statsmodels.api as sm

# Importer le dataset
dataset = pd.read_csv('clients.csv')

# Visualisation des données
print(dataset.head())

#Suppression de User ID
dataset.drop(["User ID"],axis='columns',inplace=True)


# Transformer la variable Gender\
dataset.Gender = dataset.Gender.map({"Male": 1, "Female": 2})


# Influence du genre sur l'acte d'achat
table= pd.crosstab(dataset.Gender,dataset.Purchased)
table.div(table.sum(1).astype(float), axis=0).plot(kind='bar', stacked=True)

dataset.drop(["Gender"],axis='columns',inplace=True)
print(dataset.head())

table= pd.crosstab(dataset.Age,dataset.Purchased)

table= pd.crosstab(dataset.EstimatedSalary,dataset.Purchased)

# Définir notre variable dépendante y et nos varaibles indépendantes X
X = dataset.iloc[:, [0, 1]].values
y = dataset.iloc[:, -1].values


# Diviser le dataset entre le Training set et le Test set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)
# Feature Scaling - Centre les données et les affiches
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
print(X_test)
# Construction du modèle
classifier = LogisticRegression(random_state = 0, solver='liblinear')
classifier.fit(X_train, y_train)

# Faire de nouvelles prédictions - Affiche la nprédiction du modèle
y_pred = classifier.predict(X_test)
print(classifier.score(X_test,y_test))