About my project ["PREDECTING REAL ESTATE PRICE USING LINEAR REGRESSION AND SUPPORT VECTOR Machine"] http://localhost:8892/notebooks/real%20estate%20project%20graphs.ipynb
import numpy as nm
import matplotlib.pyplot as mtp
import pandas as pd
data_set = pd.read_cv("BENGULAR_DATASET")
3. Extract the dependent and independent variables into data set for location(iloc: stands for index location)
x = data_set.iloc[::-1]
y = data_set.iloc[::1]
#sklearn.library
from sklearn.model_selection import train_test_spilt:
x_train,x_test,y_test,y_train = train_test_split(x,y,test_size=0.3, random_state=5)
from sklearn.model import Linearregression;
regressor = LinearRegression;
regressor.fit(x_train,y_train)
y_predict = regressor.predict(x_test)
x_predict = regressor.predict(y_train)
mtp.scatter()(x_train,y_train,colour = "Green");
mtp.plot(x_train,y_predict,colour = "Red");
mtp.title("bath, totalsqfoot, bhk vs "prices")
mtp.x_label("Toatlsqfoot, bhk, bath");
mtp.y_label("prices");
8. then after we have to do the validation on testing the same instead of x_train,y_train we use x_test, y_test;
conclusion: linear regression is the Best fit model execution
from sklearn.model import svc(classifer)
classifer = support vector machine
classifier.fit(x_train,y_train)
y_train = classier.fit(x_train)
**Finally after doing two Algorithm executions we got the best fit model performance is "SUPPORT VECTOR MACHINE"(SVM) . We got the predected values and actual values are equal in svm model
[ support vector machine accuracy more than the linear regression ]