def tune_rf(self, X, y):
msg.print_line()
msg.tune_rf_message()
estimators = None
features = None
leaf = None
msg.loading_message()
rf_params = self.mysql_cn.read('select * from params_rf;')
n_estimators = rf_params['n_estimators'].tolist()
max_features = rf_params['max_features'].tolist()
min_samples_leaf = rf_params['min_samples_leaf'].tolist()
if not n_estimators or not max_features or not min_samples_leaf:
msg.tuning_message()
param_grid = {
'n_estimators': [10],
'max_features': ['auto', 'sqrt', 'log2'],
'min_samples_leaf': [1, 5, 10]
}
CV_rf = GridSearchCV(estimator=RF(), param_grid=param_grid, cv=5)
CV_rf.fit(X, y)
rf_param = CV_rf.best_params_
n_estimators = rf_param['n_estimators']
max_features = rf_param['max_features']
min_samples_leaf = rf_param['min_samples_leaf']
msg.print_rf_params(n_estimators, max_features, min_samples_leaf)
msg.insert_message()
self.mysql_cn.insert_update("INSERT INTO params_rf(n_estimators, max_features, min_samples_leaf) "
"VALUES(%d, '%s', %d)" % (n_estimators, max_features, min_samples_leaf))
return (n_estimators, max_features, min_samples_leaf)
elif self.check_tune[0]:
msg.tuning_message()
param_grid = {
'n_estimators': [10, 100],
'max_features': ['auto', 'sqrt', 'log2'],
'min_samples_leaf': [1, 5, 10]
}
CV_rf = GridSearchCV(estimator=RF(), param_grid=param_grid, cv=5)
CV_rf.fit(X, y)
rf_param = CV_rf.best_params_
n_estimators = rf_param['n_estimators']
max_features = rf_param['max_features']
min_samples_leaf = rf_param['min_samples_leaf']
msg.print_rf_params(n_estimators, max_features, min_samples_leaf)
msg.update_message()
self.mysql_cn.insert_update(
"UPDATE params_rf SET n_estimators = %d, max_features = '%s', min_samples_leaf = %d"
% (n_estimators, max_features, min_samples_leaf))
return (n_estimators, max_features, min_samples_leaf)
else:
msg.loading_message()
new_rf_params = self.mysql_cn.read('select * from params_rf;')
estimators = new_rf_params['n_estimators'].tolist()
features = new_rf_params['max_features'].tolist()
leaf = new_rf_params['min_samples_leaf'].tolist()
n_estimators = estimators[0]
max_features = features[0]
min_samples_leaf = leaf[0]
msg.print_rf_params(n_estimators, max_features, min_samples_leaf)
return (n_estimators, max_features, min_samples_leaf)
def tune_svm(self, X, y):
msg.print_line()
msg.tune_svm_message()
C_range = np.logspace(-2, 2, 9)
gamma_range = np.logspace(-2, 2, 9)
param_grid = [{'kernel': ['rbf'], 'gamma': gamma_range, 'C': C_range}]
msg.loading_message()
svm_params = self.mysql_cn.read('select * from params_svm;')
kernel = svm_params['kernel'].tolist()
c = svm_params['c'].tolist()
gamma = svm_params['gamma'].tolist()
if not kernel:
msg.tuning_message()
CV_svm = GridSearchCV(SVC(), param_grid=param_grid, cv=5)
CV_svm.fit(X, y)
svm_params = CV_svm.best_params_
kernel = svm_params['kernel']
c = svm_params['C']
gamma = svm_params['gamma']
msg.print_svm_params(kernel, c, gamma)
msg.insert_message()
self.mysql_cn.insert_update("INSERT INTO params_svm(kernel, c, gamma) "
"VALUES('%s', %s, %s)" % (kernel, c, gamma))
return (kernel, c, gamma)
elif self.check_tune[0]:
msg.tuning_message()
CV_svm = GridSearchCV(SVC(), param_grid=param_grid, cv=5)
CV_svm.fit(X, y)
svm_params = CV_svm.best_params_
kernel = svm_params['kernel']
c = svm_params['C']
gamma = svm_params['gamma']
msg.print_svm_params(kernel, c, gamma)
msg.update_message()
self.mysql_cn.insert_update(
"UPDATE params_svm SET kernel = '%s', c = %s, gamma = %s"
% (kernel, c, gamma))
return (kernel, c, gamma)
else:
msg.loading_message()
new_svm_params = self.mysql_cn.read('select * from params_svm;')
kernel = new_svm_params['kernel'].tolist()
c = new_svm_params['c'].tolist()
gamma = new_svm_params['gamma'].tolist()
msg.print_svm_params(kernel[0], c[0], gamma[0])
return (kernel[0], c[0], gamma[0])
def cv_predict(X, y, clf_class, **kwargs):
# Construct a kfolds object
kf = KFold(len(y), n_folds=10, shuffle=True)
y_prob = np.zeros((len(y), 2))
# Iterate through folds
for train_index, test_index in kf:
X_train, X_test = X[train_index], X[test_index]
y_train = y[train_index]
# Initialize a classifier with key word arguments
clf = clf_class(**kwargs)
clf.fit(X_train, y_train)
y_prob[test_index] = clf.predict_proba(X_test)
return y_prob, clf
msg.print_line()
msg.calculate_probs_message()
pred_prob, clf = cv_predict(X, y, KNN, n_neighbors=k)
pred_churn = pred_prob[:, 1]
joblib.dump(clf, 'D:\SLIIT\SoftwareIndustry\knn_model.pkl', compress=1)
# Number of times a predicted probability is assigned to an observation
counts = pandas.value_counts(np.ndarray.round(pred_churn, 3))
counts = pandas.concat([counts], axis=1).reset_index()
counts.columns = ['pred_prob', 'count']
print(counts)
df1 = pandas.DataFrame(counts).sort_values(by='pred_prob')
counts_list = df1.values.tolist()
