Add files via upload

5thRegressionMultiReg (1).py

@@ -0,0 +1,70 @@
+import pandas as pd
+df=pd.read_csv(open("D:/desktop/AI Training Content/multireg.csv","rb"))
+
+x=df.iloc[:,:-1]
+y=df.iloc[:,-1]
+
+
+import numpy as np
+x=np.array(x)
+y=np.array(y)
+
+
+from sklearn.impute import SimpleImputer
+im=SimpleImputer()
+x=im.fit_transform(x)   #rule: min 2D array
+
+
+from sklearn.preprocessing import MinMaxScaler
+sc=MinMaxScaler()
+x=sc.fit_transform(x)
+
+from sklearn.model_selection import train_test_split
+xtrain,xtest,ytrain,ytest=train_test_split(x,y, test_size=0.2)
+
+
+#now select the algo: as target is of continous type use regression algo: Linear Regression, RandomForest
+# it works on equation of a line: y=bx+a     
+
+#Types: Simple linear regression {1 input column: 1 output column} 2) Multi linear regression{more than 1 input and 1 output}.
+
+from sklearn.linear_model import LinearRegression
+lr=LinearRegression()
+lr.fit(xtrain,ytrain)
+pred=lr.predict(xtest)
+
+#for regression the evaluation method is completely different.
+#1) visualization
+
+xaxis=np.linspace(1,len(pred),len(pred))
+import matplotlib.pyplot as plt
+plt.plot(xaxis,pred,color='red')
+plt.plot(xaxis,ytest,color='blue')
+plt.show()
+
+#2) how much good??? to define it in a number RMSE calculate
+from sklearn.metrics import mean_squared_error
+res=np.sqrt(mean_squared_error(pred,ytest))
+
+
+
+from sklearn.ensemble import RandomForestRegressor
+rf=RandomForestRegressor()
+rf.fit(xtrain,ytrain)
+predrf=rf.predict(xtest)
+
+#for regression the evaluation method is completely different.
+#1) visualization
+
+xaxis=np.linspace(1,len(predrf),len(predrf))
+import matplotlib.pyplot as plt
+plt.plot(xaxis,predrf,color='red')
+plt.plot(xaxis,ytest,color='blue')
+plt.show()
+
+#2) how much good??? to define it in a number RMSE calculate
+from sklearn.metrics import mean_squared_error
+resrf=np.sqrt(mean_squared_error(predrf,ytest))
+
+
+

5thRegressionMultiReg.py

@@ -0,0 +1,77 @@
+import pandas as pd
+# df=pd.read_csv(open("D:/desktop/AI Training Content/multireg.csv","rb"))
+df=pd.read_csv(open("C:/Users/Admin/Downloads/Churn_Modelling.csv","rb"))
+
+
+# x=df.iloc[:,:-1]
+# y=df.iloc[:,-1]
+x=df.iloc[:,3:-1]
+y=df.iloc[:,-1]
+
+import numpy as np
+x=np.array(x)
+y=np.array(y)
+
+from sklearn.preprocessing import LabelEncoder
+lbl=LabelEncoder()
+x[:,1]=lbl.fit_transform(x[:,1])
+x[:,2]=lbl.fit_transform(x[:,2])
+
+from sklearn.impute import SimpleImputer
+im=SimpleImputer()
+x=im.fit_transform(x)   #rule: min 2D array
+
+
+from sklearn.preprocessing import MinMaxScaler
+sc=MinMaxScaler()
+x=sc.fit_transform(x)
+
+from sklearn.model_selection import train_test_split
+xtrain,xtest,ytrain,ytest=train_test_split(x,y, test_size=0.2)
+
+
+#now select the algo: as target is of continous type use regression algo: Linear Regression, RandomForest
+# it works on equation of a line: y=bx+a     
+
+#Types: Simple linear regression {1 input column: 1 output column} 2) Multi linear regression{more than 1 input and 1 output}.
+
+from sklearn.linear_model import LinearRegression
+lr=LinearRegression()
+lr.fit(xtrain,ytrain)
+pred=lr.predict(xtest)
+
+#for regression the evaluation method is completely different.
+#1) visualization
+
+xaxis=np.linspace(1,len(pred),len(pred))
+import matplotlib.pyplot as plt
+plt.plot(xaxis,pred,color='red')
+plt.plot(xaxis,ytest,color='blue')
+plt.show()
+
+#2) how much good??? to define it in a number RMSE calculate
+from sklearn.metrics import mean_squared_error
+res=np.sqrt(mean_squared_error(pred,ytest))
+
+
+
+from sklearn.ensemble import RandomForestRegressor
+rf=RandomForestRegressor()
+rf.fit(xtrain,ytrain)
+predrf=rf.predict(xtest)
+
+#for regression the evaluation method is completely different.
+#1) visualization
+
+xaxis=np.linspace(1,len(predrf),len(predrf))
+import matplotlib.pyplot as plt
+plt.plot(xaxis,predrf,color='red')
+plt.plot(xaxis,ytest,color='blue')
+plt.show()
+
+#2) how much good??? to define it in a number RMSE calculate
+from sklearn.metrics import mean_squared_error
+resrf=np.sqrt(mean_squared_error(predrf,ytest))
+
+
+

Mumbai_regression_housePredicvtion.py

@@ -0,0 +1,83 @@
+import numpy as np
+import pandas as pd
+
+
+df =pd.read_csv(r"C:\Users\user\Documents\Taral\DATA_SET\DATA_SET\Regression Data Set\Mumbai1.csv")
+print(df)
+df.info()
+df.drop("Unnamed: 0",axis ="columns",inplace =True)
+
+x = df.iloc[:,1:]#input
+print(x)
+x.info()
+x.corr()
+y =df.iloc[:,0]#output
+print(y)
+
+corr = x.corr()
+#training and testing data
+
+from sklearn.preprocessing import LabelEncoder
+lb = LabelEncoder()
+x.Location = lb.fit_transform(x.Location)
+print(x)
+
+from sklearn.model_selection import train_test_split
+x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.3,random_state=500)
+
+
+print(len(x_train))
+print(len(x_test))
+print(len(y_train))
+print(len(y_test))
+
+
+print(x_train)
+print(x_test)
+print(y_train)
+print(y_test)
+
+
+from sklearn.linear_model import LinearRegression
+lbl =LinearRegression()
+lbl.fit(x_train,y_train)
+lbl.predict(x_test)
+lbl.score(x_test,y_test)
+
+from sklearn.linear_model import Lasso,Ridge
+las1 = Lasso()
+
+las1.fit(x_train,y_train)
+
+las1.predict(x_test)
+las1.score(x_test,y_test)
+
+
+las1 = Lasso(alpha =1000,selection="random")
+
+las1.fit(x_train,y_train)
+
+las1.predict(x_test)
+las1.score(x_test,y_test)
+
+
+rid1 = Ridge()
+
+rid1.fit(x_train,y_train)
+
+predict1=rid1.predict(x_test)
+rid1.score(x_test,y_test)
+
+# dff = pd.DataFrame(predict1)
+# dff
+# dff["actual_value"] =y_test
+# dff
+
+rid2 = Ridge(alpha =50)
+
+rid2.fit(x_train,y_train)
+
+rid2.predict(x_test)
+rid2.score(x_test,y_test)
+rid2.score(x_train,y_train)
+

house_pred_duplicate.csv

@@ -0,0 +1,11 @@
+area,price
+3200,61000000
+2600,55000000
+2600,55000000
+3000,56500000
+3200,61000000
+3600,59500000
+4000,76000000
+3000,
+4011,
+2600,55000000

labelencoder_linearregression.py

@@ -0,0 +1,99 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Feb 25 12:06:40 2022
+Label Encoder Multilinear Regression
+
+@author: user
+"""
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+
+df =pd.read_csv(r"C:\Users\user\Documents\Taral\DATA_SET\DATA_SET\Regression Data Set\Basic Regression Data\multi_house_dummy.csv")
+print(df)
+df = df.reindex(columns=["area","town","price"])
+print(df)
+
+x = df.iloc[:,:-1]
+print(x)
+
+y =df.iloc[:,-1:]
+print(y)
+
+plt.scatter(x.area, y)
+plt.show()
+
+#LabelEncoder converts strings inot numbers
+from sklearn.preprocessing import LabelEncoder
+lbl =LabelEncoder()
+x.town = lbl.fit_transform(x.town)
+print(x)
+
+from sklearn.linear_model import LinearRegression
+reg = LinearRegression()
+reg.fit(x,y)
+reg.predict(x)
+
+from sklearn.preprocessing import PolynomialFeatures
+from sklearn.linear_model import LinearRegression
+
+pr = PolynomialFeatures(degree =3)
+x_poly = pr.fit_transform(x)
+reg = LinearRegression()
+reg.fit(x_poly,y)
+
+#lasso regression 
+#ridge regression
+#polynomail regression --> scatter
+
+print(reg.coef_)
+print(reg.intercept_)
+
+reg.predict(x_poly)
+reg.score(x_poly,y)
+
+reg.predict([[3600]])
+reg.predict([[2600]])
+reg.predict([[4600]])
+
+reg.predict([[1,2600]])
+reg.predict([[2,2600]])
+reg.score(x,y)
+
+plt.scatter(x.area, y)
+plt.plot(x.area,reg.predict(x),'rD:')
+plt.show()
+
+
+from sklearn.linear_model import Ridge,Lasso
+from sklearn.model_selection import GridSearchCV
+model1=Ridge(alpha=5)
+model1.fit(x,y)
+model1.score(x,y)
+print(model1.coef_)#coefiicent
+print(model1.intercept_)
+model1.predict([[2600]])
+model1.predict([[3600]])
+model1.predict([[4600]])
+model1.predict([[2000]])
+
+model2=Lasso(alpha=6)
+model2.fit(x,y)
+model2.score(x,y)
+print(model2.coef_)
+print(model2.intercept_)
+
+
+m1=Ridge()
+parameters={'alpha':[1e-15,1e-18,1e-8,1e-4,1e-3,1e-2,1,5,10,20]}
+
+lasso_regressor=GridSearchCV(m1,parameters,cv=5)
+lasso_regressor.fit(x,y)
+lasso_regressor.score(x,y)
+
+print(model2.coef_)
+
+# from sklearn.metrics import mean_squared_error
+# mse = mean_squared_error(y,ypred)
+# rmse= np.sqrt(mse)
+#