FranciscusRenatus

# Fitting K-NN to the Training set
from sklearn.neighbors import KNeighborsClassifier
classifier = KNeighborsClassifier(n_neighbors = 5, metric = 'minkowski', p = 2)
classifier.fit(X_train, y_train)

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

# Making the Confusion Matrix
from sklearn.metrics import confusion_matrix

FranciscusRenatus

# Visualising the Training set results
from matplotlib.colors import ListedColormap
X_set, y_set = X_train, y_train
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
                     np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
             alpha = 0.75, cmap = ListedColormap(('red', 'green')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):

FranciscusRenatus

# 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
from sklearn.metrics import confusion_matrix

FranciscusRenatus

# Fitting Random Forest Regression to the dataset
from sklearn.ensemble import RandomForestRegressor
regressor = RandomForestRegressor(n_estimators = 10, random_state = 0)
regressor.fit(X, y)

# Predicting a new result
y_pred = regressor.predict(6.5)

FranciscusRenatus

# Visualising the Decision Tree Regression results (higher resolution)
# Interval is 0.01
X_grid = np.arange(min(X), max(X), 0.01)
X_grid = X_grid.reshape((len(X_grid), 1))
plt.scatter(X, y, color = 'red')
plt.plot(X_grid, regressor.predict(X_grid), color = 'blue')
plt.title('(Decision Tree Regression)')
plt.xlabel('xlabel')
plt.ylabel('ylabel')
plt.show()

FranciscusRenatus

# Fitting Decision Tree Regression to the dataset
from sklearn.tree import DecisionTreeRegressor
regressor = DecisionTreeRegressor(random_state = 0)
regressor.fit(X, y)

FranciscusRenatus

# Fitting SVR to the dataset
from sklearn.svm import SVR
regressor = SVR(kernel = 'rbf')
regressor.fit(X, y)

# Predicting a new result
# Note: dataset is scaled, needs transformation.
y_pred = sc_y.inverse_transform(regressor.predict(sc_X.transform(np.array([[6.5]]))))

FranciscusRenatus

# Importing LinearRegression for fitting
from sklearn.linear_model import LinearRegression
# Fitting Polynomial Regression to the dataset
# Importing PolynomialFeature for transforming.
from sklearn.preprocessing import PolynomialFeatures
poly_reg = PolynomialFeatures(degree = 4)
X_poly = poly_reg.fit_transform(X)
lin_reg_2 = LinearRegression()
lin_reg_2.fit(X_poly, y)

FranciscusRenatus

# Building the optimal model using backward elimination
import statsmodels.formula.api as sm
#Appending the contant as first col of the dataset for readability.
X = np.append(arr = np.ones((50, 1)).astype(int), values = X, axis = 1)
#X_optimized initialized with all features.
X_opt = X[:, [0,1,2,3,4,5]]
#Fitting using OLS
regressor_OLS = sm.OLS(endog = y, exog= X_opt).fit()
#Summary for results, any feature who can be eliminated ?
regressor_OLS.summary()

FranciscusRenatus

# Visualising the Training set results
plt.scatter(X_train, y_train, color = 'red')
plt.plot(X_train, regressor.predict(X_train), color = 'blue')
plt.title('Salary vs Experience (Training set)')
plt.xlabel('Years of Experience')
plt.ylabel('Salary')
plt.show()

# Visualising the Test set results
plt.scatter(X_test, y_test, color = 'red')