Neuronale Netze #CODE STARTS NOW....
""" Created on Thu Jun 25 17:14:13 2020
@author: Tttec """ #Import Libraries
import pandas as pd import numpy as np import sklearn as sk from sklearn.metrics import r2_score
#Import Data
datas=pd.read_csv('car_dataset.csv')
price=datas.iloc[:,1:2].values brand=datas.iloc[:,2:3].values model=datas.iloc[:,3:4].values year=datas.iloc[:,4:5].values title_status=datas.iloc[:,5:6].values mileage=datas.iloc[:,6:7].values color=datas.iloc[:,7:8].values state=datas.iloc[:,10:11].values
from sklearn.preprocessing import LabelEncoder le = LabelEncoder() brand[:,0] = le.fit_transform(brand[:,0]) print(brand) title_status[:,0] = le.fit_transform(title_status[:,0]) color[:,0]=le.fit_transform(color[:,0]) model[:,0]=le.fit_transform(model[:,0]) state[:,0]=le.fit_transform(state[:,0])
#Onehotencoding from sklearn.preprocessing import OneHotEncoder ohe=OneHotEncoder() brand=ohe.fit_transform(brand).toarray() print(brand) title_status=ohe.fit_transform(title_status).toarray() color=ohe.fit_transform(color).toarray() model=ohe.fit_transform(model).toarray() state=ohe.fit_transform(state).toarray()
#Data after Preprocessing brand=pd.DataFrame(data=brand) print(brand) title_status=pd.DataFrame(data=title_status) color=pd.DataFrame(data=color) model=pd.DataFrame(data=model) state=pd.DataFrame(data=state) mileage=pd.DataFrame(data=mileage) year=pd.DataFrame(data=year) price=pd.DataFrame(data=price)
data2=pd.concat([brand,model,title_status,color,state,year,mileage], axis=1)
#split to data for test and train from sklearn.model_selection import train_test_split x_train, x_test, y_train, y_test = train_test_split(data2,price,test_size=0.25, random_state=1) #Random state
#Linear regression from sklearn.linear_model import LinearRegression, BayesianRidge regressor= BayesianRidge() #regressor1= BayesianRidge()
regressor.fit(x_train,y_train) y_pred = regressor.predict(x_test) """ regressor1.fit(x_train,y_train) y_pred1 = regressor1.predict(x_test) """ shape_of_data2=(data2.shape)
data_list = range(0,252)
import statsmodels.api as sm x= np.append(arr=np.ones((shape_of_data2[0],1)).astype(int),values=data2,axis=1) x_l= data2.iloc[:,data_list].values r=sm.OLS(endog=price,exog=x_l).fit() """ x1= np.append(arr=np.ones((shape_of_data2[0],1)).astype(int),values=data2,axis=1) x_l_1= data2.iloc[:,data_list].values r1=sm.OLS(endog=price,exog=x_l_1).fit() """
print(r.summary(), "\n")