Alakhator

import numpy as np 
import pandas as pd

Alakhator

data = pd.read_csv(“Salary.csv”) 
print(data.head())

Alakhator

# Import label encoder 
from sklearn import preprocessing
# label_encoder object knows how to understand word labels. 
label_encoder = preprocessing.LabelEncoder()
# Encode labels in column 'Country'. 
data['Country']= label_encoder.fit_transform(data[‘Country']) 
print(data.head())

Alakhator

# importing one hot encoder 
from sklearn from sklearn.preprocessing import OneHotEncoder
# creating one hot encoder object 
onehotencoder = OneHotEncoder()
#reshape the 1-D country array to 2-D as fit_transform expects 2-D and finally fit the object 
X = onehotencoder.fit_transform(data.Country.values.reshape(-1,1)).toarray()
#To add this back into the original dataframe 
dfOneHot = pd.DataFrame(X, columns = ["Country_"+str(int(i)) for i in range(data.shape[1])]) 
df = pd.concat([data, dfOneHot], axis=1)
#droping the country column 

Alakhator

#import library
import pandas as pd
import numpy as np

Alakhator

#creating a dataframe
df=pd.DataFrame(np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]]), columns=['a', 'b', 'c']) 

Alakhator

#applying the transform function
df.transform(func = lambda x : x * 10)

Alakhator

import pandas as pd 
df=pd.read_csv(“purchase.csv”)  #Can be any csv of your choice.

Alakhator

df.groupby('User_ID')["Purchase"].mean()

Alakhator

mean_purchase =df.groupby('User_ID')["Purchase"].mean().rename("User_mean").reset_index() 
df_1 = df.merge(mean_purchase)