missing_data.py

# Data Preprocessing

# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Importing the dataset
dataset = pd.read_csv('Data.csv')
X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, 3].values

# Taking care of missing data
from sklearn.impute import SimpleImputer  # IMPORTING MISSING DATA HANDELING LIBRARY
imputer = SimpleImputer(missing_values = np.nan, strategy = 'mean')   #TAKES DATA COLUMN WISE
imputer.fit(X[:,1:3])    #SYNTAX
SimpleImputer()
X[:,1:3] = imputer.transform(X[:,1:3])


#  ENCODING CATEGORiCAL DATA
#from sklearn.preprocessing import LabelEncoder
#labelencoder_X = LabelEncoder()
#X[:, 0] = labelencoder_X.fit_transform(X[:, 0])


#DUMMY VARIABLE USE
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
from sklearn.compose import ColumnTransformer 
labelencoder_X = LabelEncoder()
X[:,0] = labelencoder_X.fit_transform(X[:,0])
ct = ColumnTransformer([("Country", OneHotEncoder(), [0])],    remainder = 'passthrough')
X = ct.fit_transform(X)
labelencoder_y = LabelEncoder()
y = labelencoder_y.fit_transform(y)


# SPLITTING THE DATASET INTO TEST SET AND TRAINING SET
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)


# FEATURE SCALING
from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.transform(X_test)