Versions Compared

Old Version 21

changes.mady.by.user Chun Kang

Saved on

compared with

New Version 22

changes.mady.by.user Chun Kang

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

Code Block
# sort by multiple columns
from pandas import DataFrame
 
Cars = {'Brand': ['Honda Civic','Toyota Corolla','Ford Focus','Audi A4'],
        'Price': [22000,25000,27000,35000],
        'Year': [2015,2013,2018,2018]
        }
 
df = DataFrame(Cars, columns= ['Brand', 'Price','Year'])

# sort by multiple columns: Year and Price
df.sort_values(by=['Year','Price'], inplace=True)

print (df)

Join and merge Pandas DataFrames

Code Block
import pandas as pd
from IPython.display import display
from IPython.display import Image

raw_data = {
        'subject_id': ['1', '2', '3', '4', '5'],
        'first_name': ['Alex', 'Amy', 'Allen', 'Alice', 'Ayoung'], 
        'last_name': ['Anderson', 'Ackerman', 'Ali', 'Aoni', 'Atiches']}
df_a = pd.DataFrame(raw_data, columns = ['subject_id', 'first_name', 'last_name'])

raw_data = {
        'subject_id': ['4', '5', '6', '7', '8'],
        'first_name': ['Billy', 'Brian', 'Bran', 'Bryce', 'Betty'], 
        'last_name': ['Bonder', 'Black', 'Balwner', 'Brice', 'Btisan']}
df_b = pd.DataFrame(raw_data, columns = ['subject_id', 'first_name', 'last_name'])

raw_data = {
        'subject_id': ['1', '2', '3', '4', '5', '7', '8', '9', '10', '11'],
        'test_id': [51, 15, 15, 61, 16, 14, 15, 1, 61, 16]}
df_n = pd.DataFrame(raw_data, columns = ['subject_id','test_id'])

# Join the two dataframes along rows
df_new = pd.concat([df_a, df_b])

# Join the two dataframes along columns
pd.concat([df_a, df_b], axis=1)

# Merge two dataframes along the subject_id value
pd.merge(df_new, df_n, on='subject_id')

# Merge two dataframes with both the left and right dataframes using the subject_id key
pd.merge(df_new, df_n, left_on='subject_id', right_on='subject_id')

# Merge with outer join
pd.merge(df_a, df_b, on='subject_id', how='outer')

# Merge with inner join
pd.merge(df_a, df_b, on='subject_id', how='inner')

# Merge with right join
pd.merge(df_a, df_b, on='subject_id', how='right')

# Merge with left join
pd.merge(df_a, df_b, on='subject_id', how='left')

# Merge while adding a suffix to duplicate column names
pd.merge(df_a, df_b, on='subject_id', how='left', suffixes=('_left', '_right'))

# Merge based on indexes
pd.merge(df_a, df_b, right_index=True, left_index=True)


Random number generation

Code Block
import random

def lottery():
    # returns 6 numbers between 1 and 40
    for i in range(6):
        yield random.randint(1, 40)

    # returns a 7th number between 1 and 15
    yield random.randint(1,15)

for random_number in lottery():
       print("And the next number is... %d!" %(random_number))

...