Created
January 28, 2022 19:56
-
-
Save Hehehe421/b30f82eade00638c92284e8807f722ce to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Model 2: Simple logistic regression with l1 regularization on under sampling data | |
#1. Get under sampling training set and testing set | |
df_u = df_test_under.drop(['Visitor_Identifier'], axis = 1) | |
df_u_target = df_u['Lead _Form_submission'] | |
X_train_under, X_test_under, y_train_under, y_test_under = train_test_split(df_u, df_u_target, test_size=0.2) | |
print(X_train_under.shape) | |
print(X_test_under.shape) | |
print(y_train_under.shape) | |
print(y_test_under.shape) | |
X_train_under_vec, y_train_under_vec, X_train_under_frame = Data_preprocessing(X_train_under, y_train_under) | |
X_test_under_vec, y_test_under_vec , X_test_under_frame = Data_preprocessing(X_test_under, y_test_under) | |
print('X Train shape is : ', X_train_under_vec.shape) | |
print('Y Train shape is : ', y_train_under_vec.shape) | |
print('X Test shape is: ', X_test_under_vec.shape) | |
print('Y Test shape is: ', y_test_under_vec.shape) | |
#2. Model parameters | |
model2 = linear_model.LogisticRegression(C=1.0, penalty='l1', tol=1e-6) | |
model2.fit(X_train_under_vec, y_train_under_vec) | |
#2. Accuracy score on testing set | |
y_pred = model2.predict(X_test_under_vec) | |
accuracy = accuracy_score(y_test_under_vec, y_pred) | |
print("Accuracy: %.2f%%" % (accuracy * 100.0)) | |
#3. Confusion matrix | |
conf_mat = confusion_matrix(y_true=y_test_under_vec, y_pred=y_pred) | |
print('Confusion matrix:\n', conf_mat) | |
labels = ['Class 0', 'Class 1'] | |
fig = plt.figure() | |
ax = fig.add_subplot(111) | |
cax = ax.matshow(conf_mat, cmap=plt.cm.Blues) | |
fig.colorbar(cax) | |
ax.set_xticklabels([''] + labels) | |
ax.set_yticklabels([''] + labels) | |
plt.xlabel('Predicted') | |
plt.ylabel('Expected') | |
plt.show() | |
#4. Classification report | |
report = classification_report(y_test_under_vec, y_pred) | |
print(report) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment