def working_kernel_PCA_easy():
#Read data
MLobj = EasyClassi()
MLobj.read("Social_Network_Ads.csv")
#Prepare data
MLobj.explore()
MLobj.split_X_y()
MLobj.X = MLobj.X[:, 2:4]
MLobj.split_ds()
MLobj.scale_features(scaleY=False)
#Applyinh Kernel PCA
MLobj.applyKernelPCA()
#Classification
MLobj.fitLog()
#Predict
y_pred = MLobj.predict()
#Evaluation confusion matrix
cm = MLobj.create_confusion_matrix()
MLobj.printModelPerformance()
#Visualize data
#MLobj.visualize_lineal_2D_class(MLobj.X_train,MLobj.y_train,x1="KPC1",x2="KPC2")
MLobj.visualize_lineal_2D_class(x1="KPC1", x2="KPC2")
def working_class_dec_tree_easy():
#Read data
MLobj = EasyClassi()
MLobj.read("Social_Network_Ads.csv")
#Prepare data
MLobj.explore()
MLobj.split_X_y()
MLobj.X = MLobj.X[:, 2:4]
MLobj.split_ds(test_set=1 / 4)
MLobj.scale_features(scaleY=False)
#Classification
MLobj.fitDecTree()
#Predict
y_pred = MLobj.predict()
#Evaluation confusion matrix
cm = MLobj.create_confusion_matrix()
print(cm)
#Visualize data
MLobj.visualize_lineal_2D_class(MLobj.X_train, MLobj.y_train)
MLobj.visualize_lineal_2D_class()
def working_k_fold_cross_easy():
#Read data
MLobj = EasyClassi()
MLobj.read("Social_Network_Ads.csv")
#Prepare data
MLobj.explore()
MLobj.split_X_y()
MLobj.X = MLobj.X[:, 2:4]
MLobj.split_ds(test_set=1 / 4)
MLobj.scale_features(scaleY=False)
#Classification
MLobj.fitKernelSVM()
#Predict
y_pred = MLobj.predict()
#Evaluation confusion matrix
cm = MLobj.create_confusion_matrix()
#Applying K-Fold Cross validation
MLobj.apply_class_k_fold()
MLobj.print_k_fold_perf()
def working_ANN():
#Read data
MLobj = EasyClassi()
MLobj.read("Churn_Modelling.csv")
#Prepare data
MLobj.explore()
MLobj.split_X_y()
MLobj.X = MLobj.X[:, 3:]
#Encode
MLobj.encode_and_dummy([1, 2], [1], encode_y=False, removeFirstColumn=True)
#Split test and training set
MLobj.split_ds(test_set=0.2)
#Scale features
MLobj.scale_features()
#Initialising the ANN
classifier = Sequential()
#Defining ANN model.
#Number of hiden layers is avg(#inputNode,#outputNodes)=6
classifier.add(
Dense(output_dim=6, init="uniform", activation="relu", input_dim=11))
classifier.add(Dense(output_dim=6, init="uniform", activation="relu"))
classifier.add(Dense(output_dim=1, init="uniform", activation="sigmoid"))
#Compile ANN
classifier.compile(optimizer="adam",
loss="binary_crossentropy",
metrics=["accuracy"])
#Fit
classifier.fit(MLobj.X_train, MLobj.y_train, batch_size=10, nb_epoch=100)
#Predict
y_pred = classifier.predict(MLobj.X_test)
#Convert y_pred to True or False with 0.5
y_pred = (y_pred > 0.5)
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(MLobj.y_test, y_pred)
def working_grid_search():
#Read data
MLobj = EasyClassi()
MLobj.read("Social_Network_Ads.csv")
#Prepare data
MLobj.explore()
MLobj.split_X_y()
MLobj.X = MLobj.X[:, 2:4]
MLobj.split_ds(test_set=1 / 4)
MLobj.scale_features(scaleY=False)
#Classification
MLobj.fitKernelSVM()
#Predict
y_pred = MLobj.predict()
#Evaluation confusion matrix
cm = MLobj.create_confusion_matrix()
#Applying K-Fold Cross validation
MLobj.apply_class_k_fold()
MLobj.print_k_fold_perf()
#Apply grid search to find the best model and best parameters
from sklearn.model_selection import GridSearchCV
parameters = [{
'C': [1, 10, 100, 1000],
"kernel": ["linear"]
}, {
'C': [1, 10, 100, 1000],
"kernel": ["rbf"],
"gamma": [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]
}]
grid_search = GridSearchCV(estimator=MLobj.classifier,
param_grid=parameters,
scoring="accuracy",
cv=10,
n_jobs=-1)
grid_search = grid_search.fit(MLobj.X_train, MLobj.y_train)
best_accuracy = grid_search.best_score_
best_parameters = grid_search.best_params_
def working_grid_search_easy():
#Read data
MLobj = EasyClassi()
MLobj.read("Social_Network_Ads.csv")
#Prepare data
MLobj.explore()
MLobj.split_X_y()
MLobj.X = MLobj.X[:, 2:4]
MLobj.split_ds(test_set=1 / 4)
MLobj.scale_features(scaleY=False)
#Classification
MLobj.fitKernelSVM()
#Predict
y_pred = MLobj.predict()
#Evaluation confusion matrix
cm = MLobj.create_confusion_matrix()
#Applying K-Fold Cross validation
MLobj.apply_class_k_fold()
MLobj.print_k_fold_perf()
#Apply grid search to find the best model and best parameters
parameters = [{
'C': [1, 10, 100, 1000],
"kernel": ["linear"]
}, {
'C': [1, 10, 100, 1000],
"kernel": ["rbf"],
"gamma": [0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9]
}]
MLobj.apply_grid_search(paramsGS=parameters)
MLobj.print_grid_search_perf()
def working_class_logistic():
#Read data
MLobj = EasyClassi()
MLobj.read("Social_Network_Ads.csv")
#Prepare data
MLobj.explore()
MLobj.split_X_y()
MLobj.X = MLobj.X[:, 2:4]
MLobj.split_ds(test_set=1 / 4)
MLobj.scale_features(scaleY=False)
#Regression with random forrest
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression(random_state=0)
classifier.fit(MLobj.X_train, MLobj.y_train)
#Predict
y_pred = classifier.predict(MLobj.X_test)
print(y_pred)
#Making confusing matrix
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(MLobj.y_test, y_pred)
# Visualising the Training set results
from matplotlib.colors import ListedColormap
X_set, y_set = MLobj.X_train, MLobj.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)):
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 = MLobj.X_test, MLobj.y_test
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)):
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()