Showing posts with label Machine Learning (ML). Show all posts
Showing posts with label Machine Learning (ML). Show all posts

Wednesday, December 4, 2019

Understanding Simple Linear Regression, Multiple Linear Regression and Polynomial Regression - ML


import numpy as np
import matplotlib.pyplot as plt
import pandas as pd                                                                                      
dataset = pd.read_csv('D:\SEM 7\ML\data.csv')
X = dataset.iloc[:, :-1].values
Y = dataset.iloc[:, 1].values
fromsklearn.model_selection import train_test_split
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 1/3, random_state = 0)
fromsklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.transform(X_test)
fromsklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X_train, Y_train)
Y_pred=regressor.predict(X_test)
plt.scatter(X_train, Y_train, color = 'red')
plt.plot(X_train, regressor.predict(X_train), color = 'blue')
plt.title('Salary vs Experience (Training set)')
plt.xlabel('Years of Experience')
plt.ylabel('Salary')
plt.show()
plt.scatter(X_test, Y_test, color = 'red')
plt.plot(X_train, regressor.predict(X_train), color = 'blue')
plt.title('Salary vs Experience (Test set)')
plt.xlabel('Years of Experience')
plt.ylabel('Salary')
plt.show()



Dataset:-

Y_test and Y_train :-



Variable Explorer:- 

Graph:-



Understanding of Data Pre-Processing for given dataset 1 using Spyder - ML

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
dataset = pd.read_csv('D:\SEM 7\ML\dataset_p1.csv')
X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, 3].values
from sklearn.preprocessing import Imputer
imputer = Imputer(missing_values = 'NaN', strategy = 'most_frequent', axis = 0)
imputer = imputer.fit(X[:, 1:3])
X[:, 1:3] = imputer.transform(X[:, 1:3])
from sklearn.preprocessing import Imputer
from sklearn.impute import SimpleImputer
imputer = Imputer(missing_values = 'NaN', strategy = 'most_frequent', axis = 0)
imputer = SimpleImputer(missing_values=np.nan,strategy='mean',verbose=0)
imputer = imputer.fit(X[:, 1:3])
X[:, 1:3] = imputer.transform(X[:, 1:3])

Variable Explorer:-


Dataset:-


Output:-

Code :-

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
dataset = pd.read_csv('D:\SEM 7\ML\dataset2.csv')
X = dataset.iloc[:, :].values
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_X = LabelEncoder()
X[:, 0] = labelencoder_X.fit_transform(X[:, 0])
#onehotencoder = OneHotEncoder(categorical_features = [0])
#X = onehotencoder.fit_transform(X).toarray()
X[:, 1] = labelencoder_X.fit_transform(X[:, 2])
#onehotencoder = OneHotEncoder(categorical_features = [1])
#X = onehotencoder.fit_transform(X).toarray()
X[:, 2] = labelencoder_X.fit_transform(X[:, 2])
onehotencoder = OneHotEncoder(categorical_features = [0])
X = onehotencoder.fit_transform(X).toarray()
onehotencoder = OneHotEncoder(categorical_features = [4])
X = onehotencoder.fit_transform(X).toarray()
onehotencoder = OneHotEncoder(categorical_features = [6])
X = onehotencoder.fit_transform(X).toarray()

Variable Explorer:-


Dataset:-

Output:-