pandas

merge two dataframe

Append the columns of df2 to df1

df1.join(df2)

select columns

Selecting columns based on their name

df['hue'] # single column

df[['alcohol','hue']] # multiple columns

Selecting a subset of columns based on difference of columns

df[df.columns.difference([‘alcohol’,’hue’])]

rename column

df.rename(columns = {'old_col1':'new_col1', 'old_col2':'new_col2'}, inplace = True)

add column

tutors = ['William', 'Henry', 'Michael', 'John', 'Messi']
df2 = df.assign(TutorsAssigned=tutors)

OR

df2=df.assign(Discount_Percent=lambda x: x.Fee * x.Discount / 100)

OR

ff['Discounted_Price'] = df.apply(lambda row: row.Cost - (row.Cost * 0.1), axis = 1)

create data frame

data = [10,20,30,40,50,60]
  
# Create the pandas DataFrame with column name is provided explicitly
df = pd.DataFrame(data, columns=['Numbers'])

OR

data = [['tom', 10], ['nick', 15], ['juli', 14]]
  
# Create the pandas DataFrame
df = pd.DataFrame(data, columns=['Name', 'Age'])

OR

data = {'Name': ['Tom', 'nick', 'krish', 'jack'],
        'Age': [20, 21, 19, 18]}
  
df = pd.DataFrame(data)

filter rows

df[df.apply(lambda x: x['b'] > x['c'], axis=1)]

process or transform a column

df['Col4'] = df.apply(lambda row:", ".join([(val if val[0]=='a' else "["+val+"]") for val in row if not pd.isna(val)]), axis=1)

test dataframe equality

from pandas.testing import assert_frame_equal
df1 = pd.DataFrame({'a': [1, 2], 'b': [3, 4]})
df2 = pd.DataFrame({'a': [1, 2], 'b': [3.0, 4.0]})
assert_frame_equal(df1, df1)