# Import Library import numpy as np import pandas as pd import seaborn as sns import matplotlib.pyplot as plt import pickle from sklearn.neighbors import KNeighborsClassifier from sklearn.metrics import roc_auc_score import lightgbm #import dataset data = pd.read_csv('master_classification.csv).fillna(0) #creating a concise list of the categorical features cat = data[['year' , 'state', 'make', 'model', 'body', 'bodystyle']] #X-features X = data.loc[:, 'abs_text' 'features' 'c-sect' 'vehicle_age' 'Cylinders' 'kbb_M' 'kbb_C' 'kbb_R' 'milage'] X1 = pd.concat([X.astype(str),cat],axis=1) X.head() #Y-target y = data['bought'] # creating dummy binary variables for cat values X2= pd.get_dummies(X1) X_new=X2.to_numpy() from sklearn.model_selection import train_test_split X_train,X_test,y_train,y_test=train_test_split(X_new,y,test_size=0.25,random_state=42) #RESAMPLING DUE TO UNBALANCE DATA from imblearn.over_sampling import SMOTE # doctest: +NORMALIZE_WHITESPACE smote = SMOTE() X_train, y_train = smote.fit_resample(X_train, y_train) #NN CLASSIFIER from sklearn.neural_network import MLPClassifier NN_model = MLPClassifier(hidden_layer_sizes=(90,90,90,90)) NN_model.fit(X_train,y_train) y_pred=NN_model.predict(X_test) y_pred #pickle model pickle.dump(NN_model,open('gan_classifier.pkl','wb'))