def working_PCA():
#Read data
MLobj = EasyClassi()
MLobj.read("wine.csv")
#Prepare data
MLobj.explore()
MLobj.split_X_y()
MLobj.split_ds()
MLobj.scale_features(scaleY=False)
#Applyinh PCA
from sklearn.decomposition import PCA
pca = PCA(n_components=2)
MLobj.X_train = pca.fit_transform(MLobj.X_train)
MLobj.X_test = pca.transform(MLobj.X_test)
explained_variance = pca.explained_variance_ratio_
#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="PC1",x2="PC2",classNum=3)
MLobj.visualize_lineal_2D_class(x1="PC1", x2="PC2", classNum=3)
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_PCA_easy():
#Read data
MLobj = EasyClassi()
MLobj.read("wine.csv")
#Prepare data
MLobj.explore()
MLobj.split_X_y()
MLobj.split_ds()
MLobj.scale_features(scaleY=False)
#Applyinh PCA
MLobj.applyPCA()
PCAratio = MLobj.getPCAVarianceRatio()
#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="PC1",x2="PC2",classNum=3)
MLobj.visualize_lineal_2D_class(x1="PC1", x2="PC2", classNum=3)
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_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_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()