Scribd
Upload
111 views

Python Pandas Handson

The document provides an overview of Python Pandas HandsOn exercises covering topics such as: 1. Pandas data structures including Series, DataFrames, and generating random data. 2. Accessing Pandas data including selecting rows and columns from DataFrames. 3. Working with CSV files including reading from and writing DataFrames to CSV. 4. Indexing DataFrames including datetime indexing and multi-indexing. 5. Data cleaning techniques like dropping null values. 6. Data aggregation including filtering, grouping, and computing statistics. 7. Merging DataFrames by appending rows and merging on indexes.

Uploaded by

mohamed yasin
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
111 views

Python Pandas Handson

The document provides an overview of Python Pandas HandsOn exercises covering topics such as: 1. Pandas data structures including Series, DataFrames, and generating random data. 2. Accessing Pandas data including selecting rows and columns from DataFrames. 3. Working with CSV files including reading from and writing DataFrames to CSV. 4. Indexing DataFrames including datetime indexing and multi-indexing. 5. Data cleaning techniques like dropping null values. 6. Data aggregation including filtering, grouping, and computing statistics. 7. Merging DataFrames by appending rows and merging on indexes.

Uploaded by

mohamed yasin
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 6

Join our channel if you haven’t joined yet https://t.

me/fresco_milestone ( @fresco_milestone )

Python Pandas HandsOns

1. Pandas Data Structures

import pandas as pd
import numpy as np

heights_A= pd.Series([176.2, 158.4, 167.6, 156.2, 161.4])


heights_A.index = ['s1', 's2', 's3', 's4','s5']
print(heights_A.shape)

weights_A = pd.Series([85.1, 90.2, 76.8, 80.4 , 78.9])


weights_A.index = ['s1', 's2', 's3', 's4','s5']
print(weights_A.dtypes)

df_A = pd.DataFrame()
df_A['Student_height'] = heights_A
df_A['Student_weight'] = weights_A
print(df_A.shape)

my_mean = 170.0
my_std = 25.0
np.random.seed(100)
heights_B= pd.Series(np.random.normal(loc=my_mean, scale=my_std, size=5))
heights_B.index = ['s1', 's2', 's3', 's4','s5']

my_mean1 = 75.0
my_std1 = 12.0
weights_B =pd.Series(np.random.normal(loc=my_mean, scale=my_std, size=5))
weights_B.index = ['s1', 's2', 's3', 's4','s5']
print(heights_B.mean())

df_B = pd.DataFrame()
df_B['Student_height'] = heights_B
df_B['Student_weight'] = weights_B
print(df_B.columns.values.tolist() )
2. Accessing Pandas Data Structures

#Write your code here


import pandas as pd
import numpy as np

heights_A = pd.Series([176.2, 158.4, 167.6, 156.2, 161.4])


heights_A.index = ['s1', 's2', 's3', 's4','s5']
print(heights_A[1])
print(heights_A[[1,2,3]])

weights_A = pd.Series([85.1, 90.2, 76.8, 80.4 , 78.9])


weights_A.index = ['s1', 's2', 's3', 's4','s5']

df_A = pd.DataFrame()
df_A['Student_height'] = heights_A
Join our channel if you haven’t joined yet https://t.me/fresco_milestone ( @fresco_milestone )

df_A['Student_weight'] = weights_A

height = df_A['Student_height']
print(type(height))

df_s1s2 = df_A[df_A.index.isin(['s1','s2'])]
print(df_s1s2)

df_s2s5s1 = df_A[df_A.index.isin(['s1','s2','s5'])]
df_s2s5s1 = df_s2s5s1.reindex(['s2', 's5', 's1'])
print(df_s2s5s1)

df_s1s4 = df_A[df_A.index.isin(['s1','s4'])]
print(df_s1s4)

3. Working with CSV files

#Write your code here


import pandas as pd
import numpy as np

heights_A = pd.Series([176.2, 158.4, 167.6, 156.2, 161.4])


heights_A.index = ['s1', 's2', 's3', 's4','s5']

weights_A = pd.Series([85.1, 90.2, 76.8, 80.4 , 78.9])


weights_A.index = ['s1', 's2', 's3', 's4','s5']

df_A = pd.DataFrame()
df_A['Student_height'] = heights_A
df_A['Student_weight'] = weights_A

df_A.to_csv('classA.csv')

df_A2 = pd.read_csv('classA.csv')
print(df_A2)

df_A3 = pd.read_csv('classA.csv',index_col='Unnamed: 0')


print(df_A3)

my_mean = 170.0
my_std = 25.0
np.random.seed(100)
heights_B = pd.Series(np.random.normal(loc=my_mean, scale=my_std, size=5))
heights_B.index = ['s1', 's2', 's3', 's4','s5']
Join our channel if you haven’t joined yet https://t.me/fresco_milestone ( @fresco_milestone )

my_mean1 = 75.0
my_std1 = 12.0
np.random.seed(100)
weights_B = pd.Series(np.random.normal(loc=my_mean1, scale=my_std1, size=5))
weights_B.index = ['s1', 's2', 's3', 's4','s5']

df_B = pd.DataFrame()
df_B['Student_height'] = heights_B
df_B['Student_weight'] = weights_B

df_B.to_csv('classB.csv', index=False)

df_B2 = pd.read_csv('classB.csv')
print(df_B2)

df_B3 = pd.read_csv('classB.csv',header=None)
print(df_B3)

df_B4 = pd.read_csv('classB.csv',header=None,skiprows=2)
print(df_B4)

4. Indexing Dataframes

#Write your code here


import pandas as pd
import numpy as np

DatetimeIndex = pd.date_range(start='09/1/2017', end='09/15/2017')


print(DatetimeIndex[2])

datelist = ['14-Sep-2017', '9-Sep-2017']


dates_to_be_searched = pd.to_datetime(datelist)

print(dates_to_be_searched)

print(dates_to_be_searched.isin(DatetimeIndex))

arraylist = [['classA']*5 + ['classB']*5, ['s1', 's2', 's3','s4', 's5']*2]


mi_index = pd.MultiIndex.from_product(arraylist, names=['First Level','Second Level'])
print(mi_index.levels)

5. Data Cleaning
Join our channel if you haven’t joined yet https://t.me/fresco_milestone ( @fresco_milestone )

#Write your code here


import pandas as pd
import numpy as np

heights_A = pd.Series([176.2, 158.4, 167.6, 156.2, 161.4])


heights_A.index = ['s1', 's2', 's3', 's4','s5']

weights_A = pd.Series([85.1, 90.2, 76.8, 80.4 , 78.9])


weights_A.index = ['s1', 's2', 's3', 's4','s5']

df_A = pd.DataFrame()
df_A['Student_height'] = heights_A
df_A['Student_weight'] = weights_A

df_A.loc['s3'] = np.nan
df_A.loc['s5'][1] = np.nan

df_A2 = df_A.dropna(how ='any')


print(df_A2)

6. Data Aggregation

#Write your code here


import pandas as pd
import numpy as np

heights_A = pd.Series([176.2, 158.4, 167.6, 156.2, 161.4])


heights_A.index = ['s1', 's2', 's3', 's4','s5']

weights_A = pd.Series([85.1, 90.2, 76.8, 80.4 , 78.9])


weights_A.index = ['s1', 's2', 's3', 's4','s5']

df_A = pd.DataFrame()
df_A['Student_height'] = heights_A
df_A['Student_weight'] = weights_A

df_A_filter1 = df_A[(df_A.Student_height > 160.0) & (df_A.Student_weight < 80.0)]


print(df_A_filter1)

df_A_filter2 = df_A[df_A.index.isin(['s5'])]
print(df_A_filter2)
Join our channel if you haven’t joined yet https://t.me/fresco_milestone ( @fresco_milestone )

df_A['Gender'] = ['M', 'F', 'M', 'M', 'F']


df_groups = df_A.groupby('Gender')
print(df_groups.mean())

7. Data Merge 1

#Write your code here


import pandas as pd
import numpy as np

heights_A = pd.Series([176.2, 158.4, 167.6, 156.2, 161.4])


heights_A.index = ['s1', 's2', 's3', 's4','s5']

weights_A = pd.Series([85.1, 90.2, 76.8, 80.4 , 78.9])


weights_A.index = ['s1', 's2', 's3', 's4','s5']

df_A = pd.DataFrame()
df_A['Student_height'] = heights_A
df_A['Student_weight'] = weights_A

df_A['Gender'] = ['M', 'F', 'M', 'M', 'F']

s = pd.Series([165.4, 82.7, 'F'],index=['Student_height', 'Student_weight', 'Gender'],name='s6')

df_AA = df_A.append(s)
print(df_AA)

my_mean = 170.0
my_std = 25.0
np.random.seed(100)
heights_B = pd.Series(np.random.normal(loc=my_mean, scale=my_std, size=5))
heights_B.index = ['s1', 's2', 's3', 's4','s5']

my_mean1 = 75.0
my_std1 = 12.0
np.random.seed(100)
weights_B = pd.Series(np.random.normal(loc=my_mean1, scale=my_std1, size=5))
weights_B.index = ['s1', 's2', 's3', 's4','s5']

df_B = pd.DataFrame()
df_B['Student_height'] = heights_B
df_B['Student_weight'] = weights_B
Join our channel if you haven’t joined yet https://t.me/fresco_milestone ( @fresco_milestone )

df_B.index = [ 's7', 's8', 's9', 's10', 's11']


df_B['Gender'] = ['F', 'M', 'F', 'F', 'M']

df = pd.concat([df_AA,df_B])
print(df)

8. Data Merge – 2

#Write your code here


import pandas as pd
import numpy as np

nameid = pd.Series(range(101, 111))


name = pd.Series(['person' + str(i) for i in range(1, 11)])
master = pd.DataFrame()
master['nameid'] = nameid
master['name'] = name

transaction = pd.DataFrame({'nameid':[108, 108, 108,103], 'product':['iPhone', 'Nokia', 'Micromax', 'Viv


o']})

mdf = pd.merge(master,transaction,on='nameid')
print(mdf)

You might also like