# Data Preprocessing

# Importing the Library
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Importing the dataset
dataset= pd.read_csv('Data.csv')
X = dataset.iloc[: , [2, 3]].values
Y = dataset.iloc[: , 4].values

# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.transform(X_test)

# Fitting Logistic Regression to the Training set
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression(random_state = 0)
classifier.fit(X_train, y_train)

# Predicting the Test set results
y_pred = classifier.predict(X_test)

# Making the Confusion Matrix
fromsklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)

# Visualising the Training set results
from matplotlib.colors import ListedColormap
X_set, Y_set = X_train, y_train
X1, X2 = np.meshgrid(np.arrange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
                     np.arrange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01)
plt.contourf(X1, X2, classifier.predict(np.array([X1.rave(), X2.ravel()]).T).reshape(X1.shape),
             alpha = 0.75, cmap = ListedColormap(('red', 'Green')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X1.min(), X1.max())
for i, j in emunerate(np.unique(y_set)):
  plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1]
              c = ListedColormap(('red', 'green'))(i), label = j)
plt.title('Logistic Regression (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()

# Visualising the Test set results
from matplotlib.colors import ListedColormap
X_set, Y_set = X_train, y_train
X1, X2 = np.meshgrid(np.arrange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
                     np.arrange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01)
plt.contourf(X1, X2, classifier.predict(np.array([X1.rave(), X2.ravel()]).T).reshape(X1.shape),
             alpha = 0.75, cmap = ListedColormap(('red', 'Green')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X1.min(), X1.max())
for i, j in emunerate(np.unique(y_set)):
  plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1]
              c = ListedColormap(('red', 'green'))(i), label = j)
plt.title('Logistic Regression (Test set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()