def run_once(df_feature, df_label):
df_ohe = dynamic_get_dummies(df_feature)
train_x, test_x, train_y, test_y = train_test_split(df_ohe,
df_label,
test_size=0.3,
random_state=99)
# dbg_recover = pd.concat([test_x, test_y], axis=1)
# over sample
train_x, train_y = over_sample(train_x, train_y)
# build model
dc_tree = DecisionTreeClassifier(criterion='entropy',
min_samples_split=20,
random_state=99)
rfe = RFE(dc_tree, best_nof_feature)
rfe_train_x = rfe.fit_transform(train_x, train_y)
rfe_test_x = rfe.transform(test_x)
dc_tree.fit(rfe_train_x, train_y)
labels = df_label.unique()
# predict
test_y_predict = dc_tree.predict(rfe_test_x)
get_accuracy("decision tree", test_y, test_y_predict, labels)
# print features
cols = list(df_ohe.columns)
temp = pd.Series(rfe.support_, index=cols)
selected_features_rfe = temp[temp == True].index
save_print("Top " + str(best_nof_feature) + " features are: ")
save_print(selected_features_rfe)
# dump model
joblib.dump(dc_tree, root_folder + "dc_tree.pkl")
save_print("dc_tree Model dumped!")
joblib.dump(selected_features_rfe, root_folder + "dc_tree_cols.pkl")
save_print("dc_tree models columns dumped!")
def run_once(df_feature, df_label):
df_ohe = dynamic_get_dummies(df_feature)
train_x, test_x, train_y, test_y = train_test_split(df_ohe,
df_label,
test_size=0.3,
random_state=99)
# dbg_recover = pd.concat([test_x, test_y], axis=1)
# over sample
train_x, train_y = over_sample(train_x, train_y)
# build model
lg_regression = linear_model.LogisticRegression(solver='lbfgs')
rfe = RFE(lg_regression, best_nof_feature)
rfe_train_x = rfe.fit_transform(train_x, train_y)
rfe_test_x = rfe.transform(test_x)
lg_regression.fit(rfe_train_x, train_y)
labels = df_label.unique()
# predict probs
test_y_predict_probs = lg_regression.predict_proba(rfe_test_x)
test_y_predict_prob = test_y_predict_probs[:, 1]
prob_df = pd.DataFrame(test_y_predict_prob)
prob_df['predict'] = np.where(prob_df[0] >= lg_threshold, 1, 0)
get_accuracy("logistic regression predict_probs", test_y,
prob_df['predict'], labels)
# print features
cols = list(df_ohe.columns)
temp = pd.Series(rfe.support_, index=cols)
selected_features_rfe = temp[temp == True].index
save_print("Top " + str(best_nof_feature) + " features are: ")
save_print(selected_features_rfe)
# dump model
joblib.dump(lg_regression, root_folder + "lg_regression.pkl")
save_print("lg_regression Model dumped!")
joblib.dump(selected_features_rfe, root_folder + "lg_regression_cols.pkl")
save_print("lg_regression models columns dumped!")
def build_random_forest(df_feature, df_label):
df_ohe = dynamic_get_dummies(df_feature)
train_x, test_x, train_y, test_y = train_test_split(df_ohe, df_label, test_size=0.3, random_state=99)
# over sample
train_x, train_y = over_sample(train_x, train_y)
rf = RandomForestClassifier(n_estimators=1000)
rf.fit(train_x, train_y)
test_y_predict = rf.predict(test_x)
labels = df_label.unique()
get_accuracy("random forest", test_y, test_y_predict, labels)
def build_nearest_neighbors(df_feature, df_label):
df_ohe = dynamic_get_dummies(df_feature)
train_x, test_x, train_y, test_y = train_test_split(df_ohe,
df_label,
test_size=0.3,
random_state=99)
# over sample
train_x, train_y = over_sample(train_x, train_y)
knn = KNeighborsClassifier(num_of_neighbors, weights=knn_weights)
knn.fit(train_x, train_y)
test_y_predict = knn.predict(test_x)
labels = df_label.unique()
get_accuracy("nearest neighbors", test_y, test_y_predict, labels)
def build_ada_boosting(df_feature, df_label):
df_ohe = dynamic_get_dummies(df_feature)
train_x, test_x, train_y, test_y = train_test_split(df_ohe,
df_label,
test_size=0.3,
random_state=99)
# over sample
train_x, train_y = over_sample(train_x, train_y)
ab = AdaBoostClassifier(n_estimators=1000)
ab.fit(train_x, train_y)
test_y_predict = ab.predict(test_x)
labels = df_label.unique()
get_accuracy("ada boosting", test_y, test_y_predict, labels)
def run_rfe(df_feature, df_label):
df_ohe = dynamic_get_dummies(df_feature)
train_x, test_x, train_y, test_y = train_test_split(df_ohe,
df_label,
test_size=0.3,
random_state=99)
# dbg_recover = pd.concat([test_x, test_y], axis=1)
# over sample
train_x, train_y = over_sample(train_x, train_y)
# build model
nof_list = np.arange(1, (max_feature_try_numbers + 1))
class_1_precision_list = []
class_1_recall_list = []
for n in range(len(nof_list)):
save_print("********Current nof features are: " + str(nof_list[n]))
lg_regression = linear_model.LogisticRegression(solver='lbfgs')
rfe = RFE(lg_regression, nof_list[n])
rfe_train_x = rfe.fit_transform(train_x, train_y)
rfe_test_x = rfe.transform(test_x)
lg_regression.fit(rfe_train_x, train_y)
labels = df_label.unique()
# predict probs
test_y_predict_probs = lg_regression.predict_proba(rfe_test_x)
test_y_predict_prob = test_y_predict_probs[:, 1]
prob_df = pd.DataFrame(test_y_predict_prob)
prob_df['predict'] = np.where(prob_df[0] >= lg_threshold, 1, 0)
class_1_precision, class_1_recall = get_accuracy(
"logistic regression predict_probs", test_y, prob_df['predict'],
labels)
class_1_precision_list.append(class_1_precision)
class_1_recall_list.append(class_1_recall)
plot_pre_recall(nof_list, class_1_precision_list, class_1_recall_list,
'logistic regression')
def run_rfe(df_feature, df_label):
df_ohe = dynamic_get_dummies(df_feature)
train_x, test_x, train_y, test_y = train_test_split(df_ohe,
df_label,
test_size=0.3,
random_state=99)
# dbg_recover = pd.concat([test_x, test_y], axis=1)
# over sample
train_x, train_y = over_sample(train_x, train_y)
# build model
nof_list = np.arange(1, (max_feature_try_numbers + 1))
class_1_precision_list = []
class_1_recall_list = []
for n in range(len(nof_list)):
save_print("********Current nof features are: " + str(nof_list[n]))
dc_tree = DecisionTreeClassifier(criterion='entropy',
min_samples_split=20,
random_state=99)
rfe = RFE(dc_tree, nof_list[n])
rfe_train_x = rfe.fit_transform(train_x, train_y)
rfe_test_x = rfe.transform(test_x)
dc_tree.fit(rfe_train_x, train_y)
labels = df_label.unique()
# predict
test_y_predict = dc_tree.predict(rfe_test_x)
class_1_precision, class_1_recall = get_accuracy(
"decision tree", test_y, test_y_predict, labels)
class_1_precision_list.append(class_1_precision)
class_1_recall_list.append(class_1_recall)
plot_pre_recall(nof_list, class_1_precision_list, class_1_recall_list,
'decision tree')