Optimization Project / Car price prediction

import numpy as np import pandas as pd

df = pd.read_csv("/work/Car details v3.csv")

df.shape

df.head()

	nameobject	yearint64	selling_priceint64	km_drivenint64	fuelobject	seller_typeobject	transmissionobject	ownerobject	mileageobject	engineobject	max_powerobject	torqueobject	seatsfloat64
0	Maruti Swift Dzire VDI	2014	450000	145500	Diesel	Individual	Manual	First Owner	23.4 kmpl	1248 CC	74 bhp	190Nm@ 2000rpm	5
1	Skoda Rapid 1.5 TDI Ambition	2014	370000	120000	Diesel	Individual	Manual	Second Owner	21.14 kmpl	1498 CC	103.52 bhp	250Nm@ 1500-2500rpm	5
2	Honda City 2017-2020 EXi	2006	158000	140000	Petrol	Individual	Manual	Third Owner	17.7 kmpl	1497 CC	78 bhp	12.7@ 2,700(kgm@ rpm)	5
3	Hyundai i20 Sportz Diesel	2010	225000	127000	Diesel	Individual	Manual	First Owner	23.0 kmpl	1396 CC	90 bhp	22.4 kgm at 1750-2750rpm	5
4	Maruti Swift VXI BSIII	2007	130000	120000	Petrol	Individual	Manual	First Owner	16.1 kmpl	1298 CC	88.2 bhp	11.5@ 4,500(kgm@ rpm)	5
5 rows × 13 columns

df.isnull().any()

df = df.dropna().reset_index(drop=True)

df.isnull().any()

def remove_unit(df,colum_name) : t = [] for i in df[colum_name]: number = str(i).split(' ')[0] t.append(float(number)) return t

df['engine'] = remove_unit(df,'engine') df['mileage'] = remove_unit(df,'mileage') df['max_power'] = remove_unit(df,'max_power')

df.head()

	nameobject	yearint64	selling_priceint64	km_drivenint64	fuelobject	seller_typeobject	transmissionobject	ownerobject	mileagefloat64	enginefloat64	max_powerfloat64	torqueobject	seatsfloat64
0	Maruti Swift Dzire VDI	2014	450000	145500	Diesel	Individual	Manual	First Owner	23.4	1248	74	190Nm@ 2000rpm	5
1	Skoda Rapid 1.5 TDI Ambition	2014	370000	120000	Diesel	Individual	Manual	Second Owner	21.14	1498	103.52	250Nm@ 1500-2500rpm	5
2	Honda City 2017-2020 EXi	2006	158000	140000	Petrol	Individual	Manual	Third Owner	17.7	1497	78	12.7@ 2,700(kgm@ rpm)	5
3	Hyundai i20 Sportz Diesel	2010	225000	127000	Diesel	Individual	Manual	First Owner	23	1396	90	22.4 kgm at 1750-2750rpm	5
4	Maruti Swift VXI BSIII	2007	130000	120000	Petrol	Individual	Manual	First Owner	16.1	1298	88.2	11.5@ 4,500(kgm@ rpm)	5
5 rows × 13 columns

df.drop(['name' ,'torque'], axis=1,inplace=True)

df.head()

	yearint64	selling_priceint64	km_drivenint64	fuelobject	seller_typeobject	transmissionobject	ownerobject	mileagefloat64	enginefloat64	max_powerfloat64	seatsfloat64
0	2014	450000	145500	Diesel	Individual	Manual	First Owner	23.4	1248	74	5
1	2014	370000	120000	Diesel	Individual	Manual	Second Owner	21.14	1498	103.52	5
2	2006	158000	140000	Petrol	Individual	Manual	Third Owner	17.7	1497	78	5
3	2010	225000	127000	Diesel	Individual	Manual	First Owner	23	1396	90	5
4	2007	130000	120000	Petrol	Individual	Manual	First Owner	16.1	1298	88.2	5
5 rows × 11 columns

df['fuel'].value_counts()

df = df[df.fuel != 'CNG'] df = df[df.fuel != 'LPG']

ColumsToConvert = [column for column in df.columns if df[column].dtype == 'O'] ColumsToConvert

def transform_col(df,Col): for i in Col: c = pd.get_dummies(df[i],prefix= i, drop_first =True) df = pd.concat ([df,c], axis = 1) df.drop(i , axis =1, inplace = True) return df

df = transform_col(df,ColumsToConvert)

df.columns

df.head()

	yearint64	selling_priceint64	km_drivenint64	mileagefloat64	enginefloat64	max_powerfloat64	seatsfloat64	fuel_Petroluint8	seller_type_Individualuint8	seller_type_Trustmark Dealeruint8	transmission_Manualuint8	owner_Fourth & Above Owneruint8	owner_Second Owneruint8	owner_Test Drive Caruint8	owner_Third Owneruint8
0	2014	450000	145500	23.4	1248	74	5	0	1	0	1	0	0	0	0
1	2014	370000	120000	21.14	1498	103.52	5	0	1	0	1	0	1	0	0
2	2006	158000	140000	17.7	1497	78	5	1	1	0	1	0	0	0	1
3	2010	225000	127000	23	1396	90	5	0	1	0	1	0	0	0	0
4	2007	130000	120000	16.1	1298	88.2	5	1	1	0	1	0	0	0	0
5 rows × 15 columns

x = df.drop('selling_price' , axis =1) y = df.iloc[:,1]

y = y.values x = x.values # y = y.to_numpy() # x = x.to_numpy()

from sklearn.preprocessing import StandardScaler scaler = StandardScaler() X = scaler.fit_transform(x)

from sklearn.model_selection import train_test_split Xtrain, Xtest, Ytrain, Ytest = train_test_split(X,y, test_size= 0.25, random_state=42)

from sklearn.metrics import mean_squared_error, mean_absolute_error from sklearn.model_selection import cross_val_score from sklearn.model_selection import validation_curve from sklearn.metrics import r2_score ModelList = []

from sklearn.linear_model import LinearRegression modelLR = LinearRegression() modelLR.fit(Xtrain,Ytrain) modelLR.score(Xtest,Ytest)

np.mean(cross_val_score(LinearRegression(), Xtrain, Ytrain, cv=10))

from sklearn.tree import DecisionTreeRegressor modelDTR = DecisionTreeRegressor() modelDTR.fit( Xtrain, Ytrain)

modelDTR.score(Xtest,Ytest)

np.mean(cross_val_score(DecisionTreeRegressor(), Xtrain, Ytrain, cv=10))

from sklearn.model_selection import GridSearchCV from sklearn.linear_model import Ridge modelRi = Ridge() parametersRidge = {'alpha': range(1,200)} RidgeGrid= GridSearchCV(modelRi, parametersRidge,cv=10)

RidgeGrid.fit(Xtrain,Ytrain)

RidgeGrid.score(Xtest,Ytest)

RidgeGrid.best_params_

np.mean(cross_val_score(Ridge(alpha= 191), Xtrain, Ytrain, cv=10))

from sklearn.neighbors import KNeighborsRegressor parametersKNN = [{'weights': ['uniform', 'distance'], 'n_neighbors': range(1, 10, 1), 'algorithm': ['ball_tree', 'kd_tree', 'brute'], 'p': range(1, 3, 1)}] modelKNN =KNeighborsRegressor() KNNGrid= GridSearchCV(modelKNN, parametersKNN,cv=10)

modelKNN.fit(Xtrain,Ytrain)

np.mean(cross_val_score(KNeighborsRegressor(), Xtrain, Ytrain, cv=12))

KNNGrid.fit(Xtrain,Ytrain)

KNNGrid.best_params_

np.mean(cross_val_score(KNeighborsRegressor(n_neighbors=3,weights='distance',algorithm='kd_tree', p=1), Xtrain, Ytrain, cv=12))

from sklearn.linear_model import SGDRegressor modelSGD = SGDRegressor() modelSGD.fit(Xtrain,Ytrain) modelSGD.score(Xtest,Ytest)

np.mean(cross_val_score(SGDRegressor(), Xtrain, Ytrain, cv=10))

from sklearn.ensemble import RandomForestRegressor modelRFR = RandomForestRegressor() modelRFR.fit(Xtrain,Ytrain) modelRFR.score(Xtest,Ytest)

np.mean(cross_val_score(RandomForestRegressor(), Xtrain, Ytrain, cv=10))

from sklearn.ensemble import GradientBoostingRegressor modelGBR = GradientBoostingRegressor() modelGBR.fit(Xtrain, Ytrain) modelGBR.score(Xtest,Ytest)

np.mean(cross_val_score(GradientBoostingRegressor(), Xtrain, Ytrain, cv=10))

!pip install xgboost==1.3.3

Collecting xgboost==1.3.3
  Downloading xgboost-1.3.3-py3-none-manylinux2010_x86_64.whl (157.5 MB)
     |████████████████████████████████| 157.5 MB 130 kB/s 
Requirement already satisfied: scipy in /shared-libs/python3.7/py/lib/python3.7/site-packages (from xgboost==1.3.3) (1.6.1)
Requirement already satisfied: numpy in /shared-libs/python3.7/py/lib/python3.7/site-packages (from xgboost==1.3.3) (1.19.5)
Installing collected packages: xgboost
Successfully installed xgboost-1.3.3
WARNING: You are using pip version 20.1.1; however, version 21.0.1 is available.
You should consider upgrading via the '/root/venv/bin/python -m pip install --upgrade pip' command.

from xgboost import XGBRegressor modelXGB = XGBRegressor() modelXGB.fit(Xtrain, Ytrain) modelXGB.score(Xtest,Ytest)

np.mean(cross_val_score(XGBRegressor(), Xtrain, Ytrain, cv=10))

from sklearn.ensemble import ExtraTreesRegressor modelETR = ExtraTreesRegressor() modelETR.fit(Xtrain, Ytrain) modelETR.score(Xtest,Ytest)

np.mean(cross_val_score(ExtraTreesRegressor(), Xtrain, Ytrain, cv=10))

ETRGrid = GridSearchCV( cv=5, estimator=modelETR, param_grid={ 'n_estimators': range(50,200, 10), 'max_features': ['sqrt', 'log2', 'auto'], 'min_samples_leaf': range(1,3,1), 'min_samples_split': range(2,10,1), } ) ETRGrid.fit(Xtrain,Ytrain)

ETRGrid.best_params_

modelETR1 = ExtraTreesRegressor(min_samples_leaf = 1, min_samples_split = 3,n_estimators = 100) modelETR1.fit(Xtrain, Ytrain) modelETR1.score(Xtest,Ytest)