finnqiao

finnqiao

# Create first pipeline for base without reducing features.

pipe = Pipeline([('classifier' , RandomForestClassifier())])
# pipe = Pipeline([('classifier', RandomForestClassifier())])

# Create param grid.

param_grid = [
    {'classifier' : [LogisticRegression()],
     'classifier__penalty' : ['l1', 'l2'],

finnqiao

from imblearn.over_sampling import SMOTE

X_train, X_test, y_train, y_test = train_test_split(X_df_2, y, test_size = 0.2, random_state = 10)

sm = SMOTE(random_state = 2)
X_train_res, y_train_res = sm.fit_sample(X_train, y_train.ravel())

clf = LogisticRegression()
model_res = clf.fit(X_train_res, y_train_res)

finnqiao

# Normalizing continuous variables

from sklearn.preprocessing import MinMaxScaler

scaler = MinMaxScaler(feature_range = (0,1))

scaler.fit(X_train)
X_train = scaler.transform(X_train)
X_test = scaler.transform(X_test)

finnqiao

# Label encode categorical variables.

label_encoder = LabelEncoder()
mappings = []

# Desired label orders for categorical columns.

educ_order = ['unknown', 'illiterate', 'basic.4y', 'basic.6y', 'basic.9y', 'high.school', 'professional.course', 'university.degree']
month_order = ['mar', 'apr', 'may', 'jun', 'jul', 'aug', 'sep', 'oct', 'nov', 'dec']
day_order = ['mon', 'tue', 'wed', 'thu', 'fri']

finnqiao

# Label Encode instead of dummy variables

mappings = []

from sklearn.preprocessing import LabelEncoder

label_encoder = LabelEncoder()

label_df = df.drop('y', axis=1)
for i, col in enumerate(label_df):

finnqiao

# Separating with continuous and categorical variables.

X_cont = ['age', 'campaign', 'pdays', 'previous', 'emp.var.rate', 'cons.price.idx', 'euribor3m', 'nr.employed']
X_cat = ['job', 'marital', 'education', 'default', 'housing', 'loan', 'contact', 'month', 'day_of_week', 'poutcome']

cont_df = X_df[X_cont]
cat_df = X_df[X_cat]

# Creating dummy variable dataframe from categorical variables.

finnqiao

%matplotlib inline
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from IPython.display import display
pd.options.display.max_columns = None
import missingno as msno

msno.bar(df)

finnqiao

print(test)

finnqiao