Exercise 1:

Create a DataFrame from a dictionary of lists.

Solution:

import pandas as pd

data = {'X': [1, 2, 3, 4], 'Y': [5, 6, 7, 8]}

df = pd.DataFrame(data)

print(df)

Copy
Output:

X Y
0 1 5
1 2 6
2 3 7
3 4 8
Exercise 2:

Select the first 3 rows of a DataFrame.

Solution:

import pandas as pd

data = {'X': [1, 2, 3, 4], 'Y': [5, 6, 7, 8]}

df = pd.DataFrame(data)

print(df.head(3))

Copy
Output:

X Y
0 1 5
1 2 6
2 3 7
Exercise 3:

Select the 'X' column from a DataFrame.

Solution:

import pandas as pd

data = {'X': [1, 2, 3, 4], 'Y': [5, 6, 7, 8]}

df = pd.DataFrame(data)

print(df['X'])

Copy
Output:

0 1
1 2
2 3
3 4
Name: X, dtype: int64
Exercise 4:

Filter rows based on a column condition.

Solution:

import pandas as pd

data = {'X': [1, 2, 3, 4], 'Y': [5, 6, 7, 8]}

df = pd.DataFrame(data)

filtered_df = df[df['X'] > 2]

print(filtered_df)

Copy
Output:

X Y
2 3 7
3 4 8
Exercise 5:

Add a new column to an existing DataFrame.

Solution:

import pandas as pd

data = {'X': [1, 2, 3, 4], 'Y': [5, 6, 7, 8]}

df = pd.DataFrame(data)

df['Z'] = df['X'] + df['Y']

print(df)

Copy
Output:

X Y Z
0 1 5 6
1 2 6 8
2 3 7 10
3 4 8 12
Exercise 6:

Remove a column from a DataFrame.

Solution:

import pandas as pd

data = {'X': [1, 2, 3, 4], 'Y': [5, 6, 7, 8], 'Z': [9, 10, 11, 12]}

df = pd.DataFrame(data)

df.drop(columns=['Z'], inplace=True)

print(df)

Copy
Output:
 X Y
0 1 5
1 2 6
2 3 7
3 4 8
Exercise 7:

Sort a DataFrame by a column.

Solution:

import pandas as pd

data = {'X': [4, 3, 2, 1], 'Y': [8, 7, 6, 5]}

df = pd.DataFrame(data)

df.sort_values(by='X', inplace=True)

print(df)

Copy
Output:

X Y
3 1 5
2 2 6
1 3 7
0 4 8
Exercise 8:

Group a DataFrame by a column and calculate the mean of each group.

Solution:

import pandas as pd

data = {'X': [1, 2, 1, 2], 'Y': [5, 6, 7, 8]}

df = pd.DataFrame(data)

grouped_df = df.groupby('X').mean()
print(grouped_df)

Copy
Output:

Y
X
1 6.0
2 7.0
Exercise 9:

Replace missing values in a DataFrame.

Solution:

import pandas as pd

data = {'X': [1, 2, None, 4], 'Y': [5, None, 7, 8]}

df = pd.DataFrame(data)

df.fillna(0, inplace=True)

print(df)

Copy
Output:

X Y
0 1.0 5.0
1 2.0 0.0
2 0.0 7.0
3 4.0 8.0
Exercise 10:

Convert a column to datetime.

Solution:

import pandas as pd

data = {'X': ['2020-01-01', '2020-01-02', '2020-01-03']}

df = pd.DataFrame(data)

df['X'] = pd.to_datetime(df['X'])

print(df)

Copy
Output:

X
0 2020-01-01
1 2020-01-02
2 2020-01-03
Exercise 11:

Create a DataFrame with specific column names.

Solution:

import pandas as pd

data = {'col1': [1, 2, 3], 'col2': [4, 5, 6]}

df = pd.DataFrame(data)

print(df)

Copy
Output:

col1 col2
0 1 4
1 2 5
2 3 6
Exercise 12:

Calculate the sum of values in each column.

Solution:

import pandas as pd

data = {'X': [1, 2, 3], 'Y': [4, 5, 6]}

df = pd.DataFrame(data)

print(df.sum())

Copy
Output:

X 6
Y 15
dtype: int64
Exercise 13:

Calculate the mean of values in each row.

Solution:

import pandas as pd

data = {'X': [1, 2, 3], 'Y': [4, 5, 6]}

df = pd.DataFrame(data)

print(df.mean(axis=1))

Copy
Output:

0 2.5
1 3.5
2 4.5
dtype: float64
Exercise 14:

Concatenate two DataFrames.

Solution:

import pandas as pd

data1 = {'X': [1, 2, 3]}

data2 = {'Y': [4, 5, 6]}

df1 = pd.DataFrame(data1)

df2 = pd.DataFrame(data2)

concatenated_df = pd.concat([df1, df2], axis=1)

print(concatenated_df)

Copy
Output:

X Y
0 1 4
1 2 5
2 3 6
Exercise 15:

Merge two DataFrames on a key.

Solution:

import pandas as pd

data1 = {'key': ['X', 'Y', 'Z'], 'value1': [1, 2, 3]}

data2 = {'key': ['X', 'Y', 'D'], 'value2': [4, 5, 6]}

df1 = pd.DataFrame(data1)

df2 = pd.DataFrame(data2)

merged_df = pd.merge(df1, df2, on='key')

print(merged_df)

Copy
Output:

key value1 value2

0 X 1 4
1 Y 2 5
Exercise 16:
Create a pivot table from a DataFrame.

Solution:

import pandas as pd

data = {'X': ['foo', 'foo', 'bar', 'bar'], 'Y': ['one', 'two', 'one', 'two'], 'Z': [1, 2, 3, 4]}

df = pd.DataFrame(data)

pivot_table = df.pivot_table(values='Z', index='X', columns='Y')

print(pivot_table)

Copy
Output:

Y one two
X
bar 3.0 4.0
foo 1.0 2.0
Exercise 17:

Reshape a DataFrame from long to wide format.

Solution:

import pandas as pd

data = {'X': ['foo', 'foo', 'bar', 'bar'], 'Y': ['one', 'two', 'one', 'two'], 'Z': [1, 2, 3, 4]}

df = pd.DataFrame(data)

wide_df = df.pivot(index='X', columns='Y', values='Z')

print(wide_df)

Copy
Output:

Y one two
X
bar 3 4
foo 1 2
Exercise 18:

Calculate the correlation between columns in a DataFrame.

Solution:

import pandas as pd

data = {'X': [1, 2, 3, 4], 'Y': [4, 3, 2, 1]}

df = pd.DataFrame(data)

correlation = df.corr()

print(correlation)

Copy
Output:

X Y
X 1.0 -1.0
Y -1.0 1.0
Exercise 19:

Iterate over rows in a DataFrame using iterrows().

Solution:

import pandas as pd

data = {'X': [1, 2, 3], 'Y': [4, 5, 6]}

df = pd.DataFrame(data)

for index, row in df.iterrows():

print(index, row['X'], row['Y'])

Copy
Output:

014
125
236
Exercise 20:

Apply a function to each element in a DataFrame.

Solution:

import pandas as pd # Import the Pandas library

# Create a sample DataFrame

data = {'X': [1, 2, 3], 'Y': [4, 5, 6]}

df = pd.DataFrame(data)

# Apply a function to each element using the map method

df = df.apply(lambda col: col.map(lambda x: x * 2))

print(df)

Copy
Output:

X Y
0 2 8
1 4 10
2 6 12
Exercise 21:

Create a DataFrame from a list of dictionaries.

Solution:

import pandas as pd

data = [{'X': 1, 'Y': 2}, {'X': 3, 'Y': 4}]

df = pd.DataFrame(data)

print(df)
Copy
Output:

X Y
0 1 2
1 3 4
Exercise 22:

Rename columns in a DataFrame.

Solution:

import pandas as pd

data = {'X': [1, 2, 3], 'Y': [4, 5, 6]}

df = pd.DataFrame(data)

df.rename(columns={'X': 'X', 'Y': 'Y'}, inplace=True)

print(df)

Copy
Output:

X Y
0 1 4
1 2 5
2 3 6
Exercise 23:

Filter rows by multiple conditions.

Solution:

import pandas as pd

data = {'X': [1, 2, 3, 4], 'Y': [4, 5, 6, 7]}

df = pd.DataFrame(data)

filtered_df = df[(df['X'] > 2) & (df['Y'] < 7)]

print(filtered_df)

Copy
Output:

X Y
2 3 6
Exercise 24:

Calculate the cumulative sum of a column.

Solution:

import pandas as pd

data = {'X': [1, 2, 3, 4]}

df = pd.DataFrame(data)

df['Cumulative_Sum'] = df['X'].cumsum()

print(df)

Copy
Output:

X Cumulative_Sum
0 1 1
1 2 3
2 3 6
3 4 10
Exercise 25:

Drop rows with missing values.

Solution:

import pandas as pd

data = {'X': [1, 2, None, 4], 'Y': [4, 5, 6, None]}

df = pd.DataFrame(data)
df.dropna(inplace=True)

print(df)

Copy
Output:

X Y
0 1.0 4.0
1 2.0 5.0
Exercise 26:

Replace values in a DataFrame based on a condition.

Solution:

import pandas as pd

data = {'X': [1, 2, 3, 4], 'Y': [5, 6, 7, 8]}

df = pd.DataFrame(data)

df.loc[df['X'] > 2, 'Y'] = 0

print(df)

Copy
Output:

X Y
0 1 5
1 2 6
2 3 0
3 4 0
Exercise 27:

Create a DataFrame with a MultiIndex.

Solution:

import pandas as pd

arrays = [['X', 'X', 'Y', 'Y'], [1, 2, 1, 2]]

index = pd.MultiIndex.from_arrays(arrays, names=('Group', 'Number'))

data = {'Value': [10, 20, 30, 40]}

df = pd.DataFrame(data, index=index)

print(df)

Copy
Output:

Value
Group Number
X 1 10
2 20
Y 1 30
2 40
Exercise 28:

Calculate the rolling mean of a column.

Solution:

import pandas as pd

data = {'X': [1, 2, 3, 4, 5, 6]}

df = pd.DataFrame(data)

df['Rolling_Mean'] = df['X'].rolling(window=3).mean()

print(df)

Copy
Output:

X Rolling_Mean
0 1 NaN
1 2 NaN
2 3 2.0
3 4 3.0
4 5 4.0
5 6 5.0
Exercise 29:

Create a DataFrame from a list of tuples.

Solution:

import pandas as pd

data = [(1, 2), (3, 4), (5, 6)]

df = pd.DataFrame(data, columns=['X', 'Y'])

print(df)

Copy
Output:

X Y
0 1 2
1 3 4
2 5 6
Exercise 30:

Add a row to a DataFrame.

Solution:

import pandas as pd # Import the Pandas library

# Create a sample DataFrame

data = {'X': [1, 2], 'Y': [3, 4]}

df = pd.DataFrame(data)

# Create a new row as a DataFrame

new_row = pd.DataFrame({'X': [5], 'Y': [6]})

# Concatenate the new row to the DataFrame

df = pd.concat([df, new_row], ignore_index=True)

print(df)

Copy
Output:

X Y
0 1 3
1 2 4
2 5 6
Exercise 31:

Create a DataFrame with random values.

Solution:

import pandas as pd

import numpy as np

data = np.random.rand(4, 3)

df = pd.DataFrame(data, columns=['X', 'Y', 'Z'])

print(df)

Copy
Output:

X Y Z
0 0.688292 0.950264 0.665916
1 0.497719 0.840536 0.923938
2 0.285218 0.091178 0.722034
3 0.037824 0.248689 0.584696
Exercise 32:

Calculate the rank of values in a DataFrame.

Solution:

import pandas as pd
data = {'X': [3, 1, 4, 1], 'Y': [2, 3, 1, 4]}

df = pd.DataFrame(data)

df['Rank'] = df['X'].rank()

print(df)

Copy
Output:

X Y Rank
0 3 2 3.0
1 1 3 1.5
2 4 1 4.0
3 1 4 1.5
Exercise 33:

Change the data type of a column.

Solution:

import pandas as pd

data = {'X': ['1', '2', '3']}

df = pd.DataFrame(data)

df['X'] = df['X'].astype(int)

print(df)

Copy
Output:

X
0 1
1 2
2 3
Exercise 34:

Filter rows based on string matching.

Solution:

import pandas as pd

data = {'X': ['foo', 'bar', 'baz', 'qux']}

df = pd.DataFrame(data)

filtered_df = df[df['X'].str.contains('ba')]

print(filtered_df)

Copy
Output:

X
1 bar
2 baz
Exercise 35:

Create a DataFrame with specified row and column labels.

Solution:

import pandas as pd

data = [[1, 2, 3], [4, 5, 6], [7, 8, 9]]

df = pd.DataFrame(data, index=['row1', 'row2', 'row3'], columns=['col1', 'col2',

'col3'])

print(df)

Copy
Output:

col1 col2 col3

row1 1 2 3
row2 4 5 6
row3 7 8 9
Exercise 36:

Transpose a DataFrame.
Solution:

import pandas as pd

data = {'X': [1, 2, 3], 'Y': [4, 5, 6]}

df = pd.DataFrame(data)

transposed_df = df.T

print(transposed_df)

Copy
Output:

0 1 2
X 1 2 3
Y 4 5 6
Exercise 37:

Set a column as the index of a DataFrame.

Solution:

import pandas as pd

data = {'X': [1, 2, 3], 'Y': [4, 5, 6]}

df = pd.DataFrame(data)

df.set_index('X', inplace=True)

print(df)

Copy
Output:

Y
X
1 4
2 5
3 6
Exercise 38:
Reset the index of a DataFrame.

Solution:

import pandas as pd

data = {'X': [1, 2, 3], 'Y': [4, 5, 6]}

df = pd.DataFrame(data)

df.set_index('X', inplace=True)

df.reset_index(inplace=True)

print(df)

Copy
Output:

X Y
0 1 4
1 2 5
2 3 6
Exercise 39:

Add a prefix or suffix to column names.

Solution:

import pandas as pd

data = {'X': [1, 2, 3], 'Y': [4, 5, 6]}

df = pd.DataFrame(data)

df = df.add_prefix('col_')

print(df)

Copy
Output:

col_X col_Y
0 1 4
1 2 5
2 3 6
Exercise 40:

Filter rows based on datetime index.

Solution:

import pandas as pd

date_range = pd.date_range(start='1/1/2020', periods=5, freq='D')

data = {'X': [1, 2, 3, 4, 5]}

df = pd.DataFrame(data, index=date_range)

filtered_df = df['2020-01-03':'2020-01-05']

print(filtered_df)

Copy
Output:

X
2020-01-03 3
2020-01-04 4
2020-01-05 5
Exercise 41:

Create a DataFrame with duplicate rows and remove duplicates.

Solution:

import pandas as pd

data = {'X': [1, 2, 2, 3], 'Y': [4, 5, 5, 6]}

df = pd.DataFrame(data)

df.drop_duplicates(inplace=True)

print(df)
Copy
Output:

X Y
0 1 4
1 2 5
3 3 6
Exercise 42:

Create a DataFrame with hierarchical index.

Solution:

import pandas as pd

arrays = [['X', 'X', 'Y', 'Y'], [1, 2, 1, 2]]

index = pd.MultiIndex.from_arrays(arrays, names=('Group', 'Number'))

data = {'Value': [10, 20, 30, 40]}

df = pd.DataFrame(data, index=index)

print(df)

Copy
Output:

Value
Group Number
X 1 10
2 20
Y 1 30
2 40
Exercise 43:

Calculate the difference between consecutive rows in a DataFrame.

Solution:

import pandas as pd
data = {'X': [1, 3, 6, 10]}

df = pd.DataFrame(data)

df['Difference'] = df['X'].diff()

print(df)

Copy
Output:

X Difference
0 1 NaN
1 3 2.0
2 6 3.0
3 10 4.0
Exercise 44:

Create a DataFrame with hierarchical columns.

Solution:

import pandas as pd

arrays = [['X', 'X', 'Y', 'Y'], ['C1', 'C2', 'C1', 'C2']]

columns = pd.MultiIndex.from_arrays(arrays, names=('Group', 'Type'))

data = [[1, 2, 3, 4], [5, 6, 7, 8], [9, 10, 11, 12]]

df = pd.DataFrame(data, columns=columns)

print(df)

Copy
Output:

Group X Y
Type C1 C2 C1 C2
0 1 2 3 4
1 5 6 7 8
2 9 10 11 12
Exercise 45:
Filter rows based on the length of strings in a column.

Solution:

import pandas as pd

data = {'X': ['foo', 'bar', 'baz', 'qux']}

df = pd.DataFrame(data)

filtered_df = df[df['X'].str.len() > 3]

print(filtered_df)

Copy
Output:

Empty DataFrame
Columns: [X]
Index: []
Exercise 46:

Calculate the percentage change between rows in a DataFrame.

Solution:

import pandas as pd

data = {'X': [1, 2, 3, 4]}

df = pd.DataFrame(data)

df['Pct_Change'] = df['X'].pct_change()

print(df)

Copy
Output:

X Pct_Change
0 1 NaN
1 2 1.000000
2 3 0.500000
3 4 0.333333
Exercise 47:

Create a DataFrame from a dictionary of Series.

Solution:

import pandas as pd

data = {'X': pd.Series([1, 2, 3]), 'Y': pd.Series([4, 5, 6])}

df = pd.DataFrame(data)

print(df)

Copy
Output:

X Y
0 1 4
1 2 5
2 3 6
Exercise 48:

Filter rows based on whether a column value is in a list.

Solution:

import pandas as pd

data = {'X': [1, 2, 3, 4], 'Y': [5, 6, 7, 8]}

df = pd.DataFrame(data)

filtered_df = df[df['X'].isin([2, 3])]

print(filtered_df)

Copy
Output:

X Y
1 2 6
2 3 7
Exercise 49:

Calculate the z-score of values in a DataFrame.

Solution:

import pandas as pd

import numpy as np

data = {'X': [1, 2, 3, 4], 'Y': [4, 5, 6, 7]}

df = pd.DataFrame(data)

df['zscore_A'] = (df['X'] - np.mean(df['X'])) / np.std(df['X'])

print(df)

Copy
Output:

X Y zscore_A
0 1 4 -1.341641
1 2 5 -0.447214
2 3 6 0.447214
3 4 7 1.341641
Exercise 50:

Create a DataFrame with random integers and calculate descriptive statistics.

Solution:

import pandas as pd

import numpy as np

data = np.random.randint(1, 100, size=(5, 3))

df = pd.DataFrame(data, columns=['X', 'Y', 'Z'])

print(df.describe())
Copy
Output:

X Y Z
count 5.000000 5.000000 5.000000
mean 60.600000 71.800000 42.600000
std 38.435661 13.971399 12.218838
min 5.000000 53.000000 28.000000
25% 40.000000 64.000000 34.000000
50% 69.000000 72.000000 41.000000
75% 91.000000 82.000000 55.000000
max 98.000000 88.000000 55.000000
Exercise 51:

Calculate the rank of values in each column of a DataFrame.

Solution:

import pandas as pd

data = {'X': [3, 1, 4, 1], 'Y': [2, 3, 1, 4]}

df = pd.DataFrame(data)

df['Rank_A'] = df['X'].rank()

df['Rank_B'] = df['Y'].rank()

print(df)

Copy
Output:

X Y Rank_A Rank_B
0 3 2 3.0 2.0
1 1 3 1.5 3.0
2 4 1 4.0 1.0
3 1 4 1.5 4.0
Exercise 52:

Filter rows based on multiple string conditions.

Solution:

import pandas as pd

data = {'X': ['foo', 'bar', 'baz', 'qux']}

df = pd.DataFrame(data)

filtered_df = df[df['X'].str.contains('ba|qu')]

print(filtered_df)

Copy
Output:

X
1 bar
2 baz
3 qux
Exercise 53:

Create a DataFrame with random values and calculate the skewness.

Solution:

import pandas as pd

data = {'X': ['foo', 'bar', 'baz', 'qux']}

df = pd.DataFrame(data)

filtered_df = df[df['X'].str.contains('ba|qu')]

print(filtered_df)

Copy
Output:

X
1 bar
2 baz
3 qux
Exercise 54:
Create a DataFrame and calculate the kurtosis.

Solution:

import pandas as pd

import numpy as np

data = np.random.rand(4, 3)

df = pd.DataFrame(data, columns=['X', 'Y', 'Z'])

print(df.kurt())

Copy
Output:

X 2.958407
Y -2.639654
Z 2.704430
dtype: float64
Exercise 55:

Calculate the cumulative product of a column in a DataFrame.

Solution:

import pandas as pd

data = {'X': [1, 2, 3, 4]}

df = pd.DataFrame(data)

df['Cumulative_Product'] = df['X'].cumprod()

print(df)

Copy
Output:

X Cumulative_Product
0 1 1
1 2 2
2 3 6
3 4 24
Exercise 56:

Create a DataFrame and calculate the rolling standard deviation.

Solution:

import pandas as pd

data = {'X': [1, 2, 3, 4, 5, 6]}

df = pd.DataFrame(data)

df['Rolling_Std'] = df['X'].rolling(window=3).std()

print(df)

Copy
Output:

X Rolling_Std
0 1 NaN
1 2 NaN
2 3 1.0
3 4 1.0
4 5 1.0
5 6 1.0
Exercise 57:

Create a DataFrame and calculate the expanding mean.

Solution:

import pandas as pd

data = {'X': [1, 2, 3, 4, 5, 6]}

df = pd.DataFrame(data)

df['Expanding_Mean'] = df['X'].expanding().mean()

print(df)
Copy
Output:

X Expanding_Mean
0 1 1.0
1 2 1.5
2 3 2.0
3 4 2.5
4 5 3.0
5 6 3.5
Exercise 58:

Create a DataFrame with random values and calculate the covariance matrix.

Solution:

import pandas as pd

import numpy as np

data = np.random.rand(4, 3)

df = pd.DataFrame(data, columns=['X', 'Y', 'Z'])

print(df.cov())

Copy
Output:

X Y Z
X 0.054079 0.007398 -0.031403
Y 0.007398 0.053211 -0.020480
Z -0.031403 -0.020480 0.048057
Exercise 59:

Create a DataFrame with random values and calculate the correlation matrix.

Solution:

import pandas as pd

import numpy as np
data = np.random.rand(4, 3)

df = pd.DataFrame(data, columns=['X', 'Y', 'Z'])

print(df.corr())

Copy
Output:

X Y Z
X 1.000000 -0.258187 0.541044
Y -0.258187 1.000000 -0.432419
Z 0.541044 -0.432419 1.000000
Exercise 60:

Create a DataFrame and calculate the rolling correlation between two columns.

Solution:

import pandas as pd

data = {'X': [1, 2, 3, 4, 5, 6], 'Y': [6, 5, 4, 3, 2, 1]}

df = pd.DataFrame(data)

df['Rolling_Corr'] = df['X'].rolling(window=3).corr(df['Y'])

print(df)

Copy
Output:

X Y Rolling_Corr
0 1 6 NaN
1 2 5 NaN
2 3 4 -1.0
3 4 3 -1.0
4 5 2 -1.0
5 6 1 -1.0
Exercise 61:

Create a DataFrame and calculate the expanding variance.

Solution:

import pandas as pd

data = {'X': [1, 2, 3, 4, 5, 6]}

df = pd.DataFrame(data)

df['Expanding_Var'] = df['X'].expanding().var()

print(df)

Copy
Output:

X Expanding_Var
0 1 NaN
1 2 0.500000
2 3 1.000000
3 4 1.666667
4 5 2.500000
5 6 3.500000
Exercise 62:

Create a DataFrame with datetime index and resample by month.

Solution:

import pandas as pd

date_range = pd.date_range(start='1/1/2020', periods=100, freq='D')

data = {'X': range(100)}

df = pd.DataFrame(data, index=date_range)

monthly_df = df.resample('M').sum()

print(monthly_df)

Copy
Output:
 X
2020-01-31 465
2020-02-29 1305
2020-03-31 2325
2020-04-30 855
Exercise 63:

Create a DataFrame and calculate the exponential moving average.

Solution:

import pandas as pd

data = {'X': [1, 2, 3, 4, 5, 6]}

df = pd.DataFrame(data)

df['EMA'] = df['X'].ewm(span=3, adjust=False).mean()

print(df)

Copy
Output:

X EMA
0 1 1.00000
1 2 1.50000
2 3 2.25000
3 4 3.12500
4 5 4.06250
5 6 5.03125
Exercise 64:

Create a DataFrame with random integers and calculate the mode.

Solution:

import pandas as pd

import numpy as np

data = np.random.randint(1, 10, size=(5, 3))

df = pd.DataFrame(data, columns=['X', 'Y', 'Z'])

print(df.mode())

Copy
Output:

X Y Z
0 2 1.0 2.0
1 3 3.0 7.0
2 5 NaN NaN
3 6 NaN NaN
4 9 NaN NaN
Exercise 65:

Create a DataFrame and calculate the z-score of each column.

Solution:

import pandas as pd

import numpy as np

data = {'X': [1, 2, 3, 4], 'Y': [4, 5, 6, 7]}

df = pd.DataFrame(data)

df['zscore_A'] = (df['X'] - np.mean(df['X'])) / np.std(df['X'])

df['zscore_B'] = (df['Y'] - np.mean(df['Y'])) / np.std(df['Y'])

print(df)

Copy
Output:

X Y zscore_A zscore_B
0 1 4 -1.341641 -1.341641
1 2 5 -0.447214 -0.447214
2 3 6 0.447214 0.447214
3 4 7 1.341641 1.341641
Exercise 66:
Create a DataFrame with random values and calculate the median.

Solution:

import pandas as pd

import numpy as np

data = np.random.rand(4, 3)

df = pd.DataFrame(data, columns=['X', 'Y', 'Z'])

print(df.median())

Copy
Output:

X 0.787042
Y 0.477837
Z 0.696911
dtype: float64
Exercise 67:

Create a DataFrame and apply a custom function to each column.

Solution:

import pandas as pd

data = {'X': [1, 2, 3], 'Y': [4, 5, 6]}

df = pd.DataFrame(data)

df = df.apply(lambda x: x + 1)

print(df)

Copy
Output:

X Y
0 2 5
1 3 6
2 4 7
Exercise 68:

Create a DataFrame with hierarchical index and calculate the mean for each group.

Solution:

import pandas as pd

arrays = [['X', 'X', 'Y', 'Y'], [1, 2, 1, 2]]

index = pd.MultiIndex.from_arrays(arrays, names=('Group', 'Number'))

data = {'Value': [10, 20, 30, 40]}

df = pd.DataFrame(data, index=index)

grouped_df = df.groupby('Group').mean()

print(grouped_df)

Copy
Output:

Value
Group
X 15.0
Y 35.0
Exercise 69:

Create a DataFrame and calculate the percentage of missing values in each column.

Solution:

import pandas as pd

data = {'X': [1, 2, None, 4], 'Y': [4, None, 6, 8]}

df = pd.DataFrame(data)

missing_percentage = df.isnull().mean() * 100

print(missing_percentage)
Copy
Output:

X 25.0
Y 25.0
dtype: float64
Exercise 70:

Create a DataFrame and apply a custom function to each row.

Solution:

import pandas as pd

data = {'X': [1, 2, 3], 'Y': [4, 5, 6]}

df = pd.DataFrame(data)

df['Sum'] = df.apply(lambda row: row['X'] + row['Y'], axis=1)

print(df)

Copy
Output:

X Y Sum
0 1 4 5
1 2 5 7
2 3 6 9
Exercise 71:

Create a DataFrame with random values and calculate the quantiles.

Solution:

import pandas as pd

import numpy as np

data = np.random.rand(4, 3)

df = pd.DataFrame(data, columns=['X', 'Y', 'Z'])

print(df.quantile([0.25, 0.5, 0.75]))

Copy
Output:

X Y Z
0.25 0.174265 0.184036 0.520573
0.50 0.468040 0.315593 0.644571
0.75 0.767870 0.436426 0.771297
Exercise 72:

Create a DataFrame and calculate the interquartile range (IQR).

Solution:

import pandas as pd

import numpy as np

data = np.random.rand(4, 3)

df = pd.DataFrame(data, columns=['X', 'Y', 'Z'])

Q1 = df.quantile(0.25)

Q3 = df.quantile(0.75)

IQR = Q3 - Q1

print(IQR)

Copy
Output:

X 0.354244
Y 0.329573
Z 0.245520
dtype: float64
Exercise 73:

Create a DataFrame with datetime index and calculate the rolling mean.

Solution:
import pandas as pd

date_range = pd.date_range(start='1/1/2020', periods=10, freq='D')

data = {'X': range(10)}

df = pd.DataFrame(data, index=date_range)

df['Rolling_Mean'] = df['X'].rolling(window=3).mean()

print(df)

Copy
Output:

X Rolling_Mean
2020-01-01 0 NaN
2020-01-02 1 NaN
2020-01-03 2 1.0
2020-01-04 3 2.0
2020-01-05 4 3.0
2020-01-06 5 4.0
2020-01-07 6 5.0
2020-01-08 7 6.0
2020-01-09 8 7.0
2020-01-10 9 8.0
Exercise 74:

Create a DataFrame and calculate the cumulative maximum.

Solution:

import pandas as pd

data = {'X': [1, 2, 3, 2, 1]}

df = pd.DataFrame(data)

df['Cumulative_Max'] = df['X'].cummax()

print(df)

Copy
Output:

X Cumulative_Max
0 1 1
1 2 2
2 3 3
3 2 3
4 1 3
Exercise 75:

Create a DataFrame and calculate the cumulative minimum.

Solution:

import pandas as pd

data = {'X': [1, 2, 3, 2, 1]}

df = pd.DataFrame(data)

df['Cumulative_Min'] = df['X'].cummin()

print(df)

Copy
Output:

X Cumulative_Min
0 1 1
1 2 1
2 3 1
3 2 1
4 1 1
Exercise 76:

Create a DataFrame with random values and calculate the cumulative variance.

Solution:

import pandas as pd

import numpy as np
data = np.random.rand(10, 3)

df = pd.DataFrame(data, columns=['X', 'Y', 'Z'])

df['Cumulative_Var'] = df['X'].expanding().var()

print(df)

Copy
Output:

X Y Z Cumulative_Var
0 0.315669 0.900791 0.404858 NaN
1 0.462000 0.463257 0.922495 0.010706
2 0.328968 0.200027 0.967625 0.006548
3 0.630370 0.992849 0.231884 0.021460
4 0.574397 0.968600 0.926893 0.020023
5 0.204077 0.889864 0.589022 0.027130
6 0.386806 0.630882 0.242157 0.022759
7 0.319831 0.935747 0.829739 0.020630
8 0.786435 0.377739 0.879458 0.034407
9 0.523467 0.077937 0.764476 0.031194
Exercise 77:

Create a DataFrame and apply a custom function to each element.

Solution:

import pandas as pd

# Create a DataFrame

data = {'X': [1, 2, 3], 'Y': [4, 5, 6]}

df = pd.DataFrame(data)

# Define the custom function

def custom_function(x):

return x * 2

# Apply the function to each element using map on each column

df = df.apply(lambda col: col.map(custom_function))

# Print the DataFrame

print(df)

Copy
Output:

X Y
0 2 8
1 4 10
2 6 12
Exercise 78:

Create a DataFrame with random values and calculate the z-score for each element.

Solution:

import pandas as pd

import numpy as np

data = np.random.rand(4, 3)

df = pd.DataFrame(data, columns=['X', 'Y', 'Z'])

df = df.apply(lambda x: (x - x.mean()) / x.std(), axis=0)

print(df)

Copy
Output:

X Y Z
0 1.027393 0.656858 1.032853
1 0.674079 -1.277904 -0.220065
2 -0.996641 -0.298841 0.475217
3 -0.704831 0.919887 -1.288005
Exercise 79:

Create a DataFrame and calculate the cumulative sum for each group.
Solution:

import pandas as pd

data = {'X': ['foo', 'bar', 'foo', 'bar'], 'Y': [1, 2, 3, 4]}

df = pd.DataFrame(data)

df['Cumulative_Sum'] = df.groupby('X')['Y'].cumsum()

print(df)

Copy
Output:

X Y Cumulative_Sum
0 foo 1 1
1 bar 2 2
2 foo 3 4
3 bar 4 6
Exercise 80:

Create a DataFrame with random values and calculate the rank for each element.

Solution:

import pandas as pd

import numpy as np

data = np.random.rand(4, 3)

df = pd.DataFrame(data, columns=['X', 'Y', 'Z'])

df = df.rank()

print(df)

Copy
Output:

X Y Z
0 4.0 3.0 3.0
1 3.0 2.0 2.0
2 1.0 4.0 1.0
3 2.0 1.0 4.0
Exercise 81:

Create a DataFrame and calculate the cumulative product for each group.

Solution:

import pandas as pd

data = {'X': ['foo', 'bar', 'foo', 'bar'], 'Y': [1, 2, 3, 4]}

df = pd.DataFrame(data)

df['Cumulative_Product'] = df.groupby('X')['Y'].cumprod()

print(df)

Copy
Output:

X Y Cumulative_Product
0 foo 1 1
1 bar 2 2
2 foo 3 3
3 bar 4 8
Exercise 82:

Create a DataFrame with random values and calculate the expanding sum.

Solution:

import pandas as pd

import numpy as np

data = np.random.rand(4, 3)

df = pd.DataFrame(data, columns=['X', 'Y', 'Z'])

df['Expanding_Sum'] = df['X'].expanding().sum()
print(df)

Copy
Output:

X Y Z Expanding_Sum
0 0.815750 0.062819 0.699743 0.815750
1 0.128772 0.843222 0.411903 0.944522
2 0.857516 0.219424 0.234460 1.802038
3 0.011010 0.774375 0.259412 1.813048
Exercise 83:

Create a DataFrame and calculate the expanding minimum for each group.

Solution:

import pandas as pd

data = {'X': ['foo', 'bar', 'foo', 'bar'], 'Y': [1, 2, 3, 4]}

df = pd.DataFrame(data)

df['Expanding_Min'] = df.groupby('X')['Y'].expanding().min().reset_index(level=0,
drop=True)

print(df)

Copy
Output:

X Y Expanding_Min
0 foo 1 1.0
1 bar 2 2.0
2 foo 3 1.0
3 bar 4 2.0
Exercise 84:

Create a DataFrame with random values and calculate the expanding maximum for
each group.

Solution:
import pandas as pd

import numpy as np

data = np.random.rand(4, 3)

df = pd.DataFrame(data, columns=['X', 'Y', 'Z'])

df['Expanding_Max'] = df.groupby('X')
['Y'].expanding().max().reset_index(level=0, drop=True)

print(df)

Copy
Output:

X Y Z Expanding_Max
0 0.751392 0.015856 0.313990 0.015856
1 0.812436 0.701808 0.069307 0.701808
2 0.148614 0.838726 0.290646 0.838726
3 0.764419 0.586510 0.470466 0.586510
Exercise 85:

Create a DataFrame and calculate the expanding variance for each group.

Solution:

import pandas as pd

data = {'X': ['foo', 'bar', 'foo', 'bar'], 'Y': [1, 2, 3, 4]}

df = pd.DataFrame(data)

df['Expanding_Var'] = df.groupby('X')['Y'].expanding().var().reset_index(level=0,
drop=True)

print(df)

Copy
Output:

X Y Expanding_Var
0 foo 1 NaN
1 bar 2 NaN
2 foo 3 2.0
3 bar 4 2.0
Exercise 86:

Create a DataFrame with random values and calculate the expanding standard
deviation.

Solution:

import pandas as pd

import numpy as np

data = np.random.rand(4, 3)

df = pd.DataFrame(data, columns=['X', 'Y', 'Z'])

df['Expanding_Std'] = df['X'].expanding().std()

print(df)

Copy
Output:

X Y Z Expanding_Std
0 0.693184 0.088273 0.109510 NaN
1 0.031186 0.163005 0.803467 0.468103
2 0.294881 0.409395 0.278145 0.333272
3 0.918778 0.854961 0.791329 0.397322

Exercise 87:

Create a DataFrame and calculate the expanding covariance.

Solution:

import pandas as pd

data = {'X': [1, 2, 3, 4], 'Y': [4, 3, 2, 1]}

df = pd.DataFrame(data)
df['Expanding_Cov'] = df['X'].expanding().cov(df['Y'])

print(df)

Copy
Output:

X Y Expanding_Cov
0 1 4 NaN
1 2 3 -0.500000
2 3 2 -1.000000
3 4 1 -1.666667
Exercise 88:

Create a DataFrame with random values and calculate the expanding correlation.

Solution:

import pandas as pd

import numpy as np

data = np.random.rand(4, 3)

df = pd.DataFrame(data, columns=['X', 'Y', 'Z'])

df['Expanding_Corr'] = df['X'].expanding().corr(df['Y'])

print(df)

Copy
Output:

X Y Z Expanding_Corr
0 0.094026 0.320246 0.044218 NaN
1 0.422531 0.002172 0.995907 -1.000000
2 0.265459 0.391239 0.589878 -0.751147
3 0.118812 0.061489 0.837821 -0.372750
Exercise 89:

Create a DataFrame and calculate the expanding median.

Solution:

import pandas as pd

data = {'X': [1, 2, 3, 4, 5, 6]}

df = pd.DataFrame(data)

df['Expanding_Median'] = df['X'].expanding().median()

print(df)

Copy
Output:

X Expanding_Median
0 1 1.0
1 2 1.5
2 3 2.0
3 4 2.5
4 5 3.0
5 6 3.5
Exercise 90:

Create a DataFrame with datetime index and calculate the expanding mean for
each group.

Solution:

import pandas as pd

date_range = pd.date_range(start='1/1/2020', periods=10, freq='D')

data = {'X': ['foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'bar'], 'Y': range(10)}

df = pd.DataFrame(data, index=date_range)

df['Expanding_Mean'] = df.groupby('X')
['Y'].expanding().mean().reset_index(level=0, drop=True)

print(df)

Copy
Output:

X Y Expanding_Mean
2020-01-01 foo 0 0.0
2020-01-02 bar 1 1.0
2020-01-03 foo 2 1.0
2020-01-04 bar 3 2.0
2020-01-05 foo 4 2.0
2020-01-06 bar 5 3.0
2020-01-07 foo 6 3.0
2020-01-08 bar 7 4.0
2020-01-09 foo 8 4.0
2020-01-10 bar 9 5.0
Exercise 91:

Create a DataFrame with random values and calculate the rolling sum for each
group.

Solution:

import pandas as pd

import numpy as np

data = np.random.rand(10, 3)

df = pd.DataFrame(data, columns=['X', 'Y', 'Z'])

df['Rolling_Sum'] = df.groupby('X')
['Y'].rolling(window=3).sum().reset_index(level=0, drop=True)

print(df)

Copy
Output:

X Y Z Rolling_Sum
0 0.342706 0.579330 0.902681 NaN
1 0.182432 0.163406 0.156607 NaN
2 0.983085 0.052785 0.588865 NaN
3 0.756982 0.123991 0.704262 NaN
4 0.876875 0.710953 0.923588 NaN
5 0.359818 0.135520 0.277327 NaN
6 0.693156 0.590918 0.985834 NaN
7 0.892253 0.633529 0.169000 NaN
8 0.084238 0.007579 0.076730 NaN
9 0.663869 0.780832 0.644874 NaN
Exercise 92:

Create a DataFrame and calculate the rolling mean for each group.

Solution:

import pandas as pd

data = {'X': ['foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'bar'], 'Y': range(10)}

df = pd.DataFrame(data)

df['Rolling_Mean'] = df.groupby('X')
['Y'].rolling(window=3).mean().reset_index(level=0, drop=True)

print(df)

Copy
Output:

X Y Rolling_Mean
0 foo 0 NaN
1 bar 1 NaN
2 foo 2 NaN
3 bar 3 NaN
4 foo 4 2.0
5 bar 5 3.0
6 foo 6 4.0
7 bar 7 5.0
8 foo 8 6.0
9 bar 9 7.0
Exercise 93:

Create a DataFrame with random values and calculate the rolling standard
deviation for each group.
Solution:

import pandas as pd

import numpy as np

data = np.random.rand(10, 3)

df = pd.DataFrame(data, columns=['X', 'Y', 'Z'])

df['Rolling_Std'] = df.groupby('X')
['Y'].rolling(window=3).std().reset_index(level=0, drop=True)

print(df)

Copy
Output:

X Y Z Rolling_Std
0 0.154838 0.162793 0.808882 NaN
1 0.740167 0.920318 0.650240 NaN
2 0.033449 0.007883 0.249656 NaN
3 0.983601 0.261995 0.399816 NaN
4 0.883155 0.051084 0.125735 NaN
5 0.986930 0.470328 0.612276 NaN
6 0.981338 0.016731 0.627210 NaN
7 0.670522 0.247346 0.530971 NaN
8 0.978909 0.752500 0.903401 NaN
9 0.185614 0.362602 0.541459 NaN
Exercise 94:

Create a DataFrame and calculate the rolling variance for each group.

Solution:

import pandas as pd

data = {'X': ['foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'bar'], 'Y': range(10)}

df = pd.DataFrame(data)

df['Rolling_Var'] = df.groupby('X')
['Y'].rolling(window=3).var().reset_index(level=0, drop=True)
print(df)

Copy
Output:

X Y Rolling_Var
0 foo 0 NaN
1 bar 1 NaN
2 foo 2 NaN
3 bar 3 NaN
4 foo 4 4.0
5 bar 5 4.0
6 foo 6 4.0
7 bar 7 4.0
8 foo 8 4.0
9 bar 9 4.0
Exercise 95:

Create a DataFrame with random values and calculate the rolling correlation for
each group.

Solution:

import pandas as pd

import numpy as np

# Create a DataFrame with random values

np.random.seed(42) # For reproducibility

data = np.random.rand(10, 3)

df = pd.DataFrame(data, columns=['X', 'Y', 'Z'])

# Optionally create a group column if necessary

df['Group'] = np.random.choice(['A', 'B'], size=10)

# Calculate the rolling correlation for each group

df['Rolling_Corr'] = df.groupby('Group').apply(lambda group:

group['Y'].rolling(window=3).corr(group['Z'])).reset_index(level=0, drop=True)
print(df)

Copy
Output:

X Z Group Rolling_Corr
0 0.374540 0.950714 0.731994 A NaN
1 0.598658 0.156019 0.155995 A NaN
2 0.058084 0.866176 0.601115 A 0.992633
3 0.708073 0.020584 0.969910 A -0.095420
4 0.832443 0.212339 0.181825 A -0.180021
5 0.183405 0.304242 0.524756 B NaN
6 0.431945 0.291229 0.611853 B NaN
7 0.139494 0.292145 0.366362 A -0.869948
8 0.456070 0.785176 0.199674 B -0.984073
9 0.514234 0.592415 0.046450 B -0.788379
Exercise 96:

Create a DataFrame and calculate the rolling covariance for each group.

Solution:

import pandas as pd

# Create a DataFrame with sample data

data = {'X': ['foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'bar'],

'Y': range(10), 'Z': range(10, 20)}

df = pd.DataFrame(data)

# Calculate the rolling covariance for each group

rolling_cov = df.groupby('X').apply(lambda group:

group['Y'].rolling(window=3).cov(group['Z'])).reset_index(level=0, drop=True)

# Add the rolling covariance to the original DataFrame

df['Rolling_Cov'] = rolling_cov
print(df)

Copy
Output:

X Y Z Rolling_Cov
0 foo 0 10 NaN
1 bar 1 11 NaN
2 foo 2 12 NaN
3 bar 3 13 NaN
4 foo 4 14 4.0
5 bar 5 15 4.0
6 foo 6 16 4.0
7 bar 7 17 4.0
8 foo 8 18 4.0
9 bar 9 19 4.0
Exercise 97:

Create a DataFrame with random values and calculate the rolling skewness for
each group.

Solution:

import pandas as pd

import numpy as np

data = np.random.rand(10, 3)

df = pd.DataFrame(data, columns=['X', 'Y', 'Z'])

df['Rolling_Skew'] = df.groupby('X')
['Y'].rolling(window=3).skew().reset_index(level=0, drop=True)

print(df)

Copy
Output:

X Y Z Rolling_Skew
0 0.808397 0.304614 0.097672 NaN
1 0.684233 0.440152 0.122038 NaN
2 0.495177 0.034389 0.909320 NaN
3 0.258780 0.662522 0.311711 NaN
4 0.520068 0.546710 0.184854 NaN
5 0.969585 0.775133 0.939499 NaN
6 0.894827 0.597900 0.921874 NaN
7 0.088493 0.195983 0.045227 NaN
8 0.325330 0.388677 0.271349 NaN
9 0.828738 0.356753 0.280935 NaN
Exercise 98:

Create a DataFrame and calculate the rolling kurtosis for each group.

Solution:

import pandas as pd

data = {'X': ['foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'bar'], 'Y': range(10)}

df = pd.DataFrame(data)

df['Rolling_Kurt'] = df.groupby('X')
['Y'].rolling(window=3).kurt().reset_index(level=0, drop=True)

print(df)

Copy
Output:

X Y Rolling_Kurt
0 foo 0 NaN
1 bar 1 NaN
2 foo 2 NaN
3 bar 3 NaN
4 foo 4 NaN
5 bar 5 NaN
6 foo 6 NaN
7 bar 7 NaN
8 foo 8 NaN
9 bar 9 NaN
Exercise 99:
Create a DataFrame with random values and calculate the rolling median for each
group.

Solution:

import pandas as pd

import numpy as np

data = np.random.rand(10, 3)

df = pd.DataFrame(data, columns=['X', 'Y', 'Z'])

df['Rolling_Median'] = df.groupby('X')
['Y'].rolling(window=3).median().reset_index(level=0, drop=True)

print(df)

Copy
Output:

X Y Z Rolling_Median
0 0.542696 0.140924 0.802197 NaN
1 0.074551 0.986887 0.772245 NaN
2 0.198716 0.005522 0.815461 NaN
3 0.706857 0.729007 0.771270 NaN
4 0.074045 0.358466 0.115869 NaN
5 0.863103 0.623298 0.330898 NaN
6 0.063558 0.310982 0.325183 NaN
7 0.729606 0.637557 0.887213 NaN
8 0.472215 0.119594 0.713245 NaN
9 0.760785 0.561277 0.770967 NaN
Exercise 100:

Create a DataFrame and calculate the expanding sum for each group.

Solution:

import pandas as pd

data = {'X': ['foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'bar'], 'Y': range(10)}
df = pd.DataFrame(data)

df['Expanding_Sum'] = df.groupby('X')
['Y'].expanding().sum().reset_index(level=0, drop=True)

print(df)

Output:

X Y Expanding_Sum
0 foo 0 0.0
1 bar 1 1.0
2 foo 2 2.0
3 bar 3 4.0
4 foo 4 6.0
5 bar 5 9.0
6 foo 6 12.0
7 bar 7 16.0
8 foo 8 20.0
9 bar 9 25.0