Python Pandas - Filling missing column values with mode

Mode is the value that appears most frequently in a dataset. In Pandas, you can fill missing values with the mode using the fillna() method combined with mode(). This is useful when you want to replace NaN values with the most common value in a column.

Syntax

dataframe.fillna(dataframe['column'].mode()[0], inplace=True)

Creating DataFrame with Missing Values

Let's start by importing the required libraries and creating a DataFrame with some missing values ?

import pandas as pd
import numpy as np

# Create DataFrame with NaN values
dataFrame = pd.DataFrame({
    "Car": ['BMW', 'Lexus', 'Lexus', 'Mustang', 'Bentley', 'Mustang'],
    "Units": [100, 150, np.NaN, 80, np.NaN, np.NaN]
})

print("Original DataFrame:")
print(dataFrame)

Original DataFrame:
       Car  Units
0      BMW  100.0
1    Lexus  150.0
2    Lexus    NaN
3  Mustang   80.0
4  Bentley    NaN
5  Mustang    NaN

Finding the Mode

First, let's find the mode of the Units column to understand what value will be used for filling ?

import pandas as pd
import numpy as np

dataFrame = pd.DataFrame({
    "Car": ['BMW', 'Lexus', 'Lexus', 'Mustang', 'Bentley', 'Mustang'],
    "Units": [100, 150, np.NaN, 80, np.NaN, np.NaN]
})

# Find mode of Units column
mode_value = dataFrame['Units'].mode()[0]
print("Mode of Units column:", mode_value)
print("Value counts:")
print(dataFrame['Units'].value_counts())

Mode of Units column: 80.0
Value counts:
Units
150.0    1
100.0    1
80.0     1
Name: count, dtype: int64

Filling Missing Values with Mode

Now let's fill the NaN values with the mode using fillna() ?

import pandas as pd
import numpy as np

# Create DataFrame
dataFrame = pd.DataFrame({
    "Car": ['BMW', 'Lexus', 'Lexus', 'Mustang', 'Bentley', 'Mustang'],
    "Units": [100, 150, np.NaN, 80, np.NaN, np.NaN]
})

print("DataFrame before filling:")
print(dataFrame)

# Fill NaN values with mode of Units column
dataFrame.fillna(dataFrame['Units'].mode()[0], inplace=True)

print("\nDataFrame after filling NaN values with mode:")
print(dataFrame)

DataFrame before filling:
       Car  Units
0      BMW  100.0
1    Lexus  150.0
2    Lexus    NaN
3  Mustang   80.0
4  Bentley    NaN
5  Mustang    NaN

DataFrame after filling NaN values with mode:
       Car  Units
0      BMW  100.0
1    Lexus  150.0
2    Lexus   80.0
3  Mustang   80.0
4  Bentley   80.0
5  Mustang   80.0

Filling Specific Columns

You can also fill missing values for specific columns only ?

import pandas as pd
import numpy as np

# Create DataFrame with multiple columns having NaN
dataFrame = pd.DataFrame({
    "Car": ['BMW', 'Lexus', np.NaN, 'Mustang', 'Bentley', 'Mustang'],
    "Units": [100, 150, np.NaN, 80, np.NaN, np.NaN],
    "Price": [50000, 60000, np.NaN, 45000, np.NaN, 45000]
})

print("Original DataFrame:")
print(dataFrame)

# Fill only Units column with its mode
dataFrame['Units'].fillna(dataFrame['Units'].mode()[0], inplace=True)

print("\nAfter filling Units column with mode:")
print(dataFrame)

Original DataFrame:
       Car  Units   Price
0      BMW  100.0  50000.0
1    Lexus  150.0  60000.0
2      NaN    NaN      NaN
3  Mustang   80.0  45000.0
4  Bentley    NaN      NaN
5  Mustang    NaN  45000.0

After filling Units column with mode:
       Car  Units   Price
0      BMW  100.0  50000.0
1    Lexus  150.0  60000.0
2      NaN   80.0      NaN
3  Mustang   80.0  45000.0
4  Bentley   80.0      NaN
5  Mustang   80.0  45000.0

Key Points

• The mode() method returns a Series, so use [0] to get the first mode value
• If all values are unique, the first value (alphabetically or numerically) becomes the mode
• Use inplace=True to modify the original DataFrame
• Mode filling is useful for categorical and discrete numerical data

Conclusion

Filling missing values with mode is an effective technique for handling NaN values in datasets. Use fillna() with mode()[0] to replace missing values with the most frequent value in the column.