CODEWITHSUNDEEP
pythonpandasmachine-learning
SKD
SKD

Reputation: 43

linear_regression

program:

import pandas as pd

ds=pd.read_csv('Animals.csv')

x=ds.iloc[:,1].values
y=ds.iloc[:,2].values

from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.2,random_state=0)
x_train = x_train.reshape(-1, 1)
y_train = y_train.reshape(-1,1)

from sklearn.linear_model import LinearRegression as lr
reg=lr()
reg.fit(x_train,y_train)

y_pred=reg.predict(x_test)

y_pred = array([[433.34494686],
                [433.20384407],
                [418.6791427 ],
                [433.34789435],
                [407.49640802],
                [432.25311216]])

y_test = array([[ 119.5],
                [ 157. ],
                [5712. ],
                [  56. ],
                [  50. ],
                [ 680. ]])

the prediction is not perfect why? is that any problem with dataset or what it maybe? im new to machine learning thanks in advance

Upvotes: 2

Views: 80

Answers (1)

yatu
yatu

Reputation: 88236

Well it really depends on what you are trying to predict and if the features you have are good predictors. So even though you are simply trying with a LR, if your target variable is explainable by the features you should get some reasonable accuracy metrics.

Looking at your y_testyou should consider removing outliers, which will probably improve the accuracy of the model.

You might also want to try with some more efficient regressors such as RandomForestRegressor or a SupportVectorRegressor.

Upvotes: 1

Related Questions