ملء القيم المفقودة

مقدمة إلى fillna()

import pandas as pd
import numpy as np

df = pd.DataFrame({
    'product': ['A', 'B', 'C', 'D'],
    'price': [10.0, np.nan, 30.0, np.nan]
})

# Fill all NaN in 'price' with 0
filled = df['price'].fillna(0)
print(filled)
# 0    10.0
# 1     0.0
# 2    30.0
# 3     0.0

الملء بمتوسط العمود أو وسيطه

import pandas as pd
import numpy as np

df = pd.DataFrame({
    'salary': [50000, np.nan, 70000, 80000, np.nan, 60000]
})

mean_salary = df['salary'].mean()
median_salary = df['salary'].median()

df['salary_mean_filled'] = df['salary'].fillna(mean_salary)
df['salary_median_filled'] = df['salary'].fillna(median_salary)
print(df)
#     salary  salary_mean_filled  salary_median_filled
# 0  50000.0             50000.0               50000.0
# 1      NaN             65000.0               65000.0
# 2  70000.0             70000.0               70000.0

ملء الأعمدة الفئوية بالمنوال

import pandas as pd
import numpy as np

df = pd.DataFrame({
    'status': ['active', 'inactive', None, 'active', None, 'active']
})

most_common = df['status'].mode()[0]
print('Mode:', most_common)  # active

df['status'] = df['status'].fillna(most_common)
print(df['status'].tolist())
# ['active', 'inactive', 'active', 'active', 'active', 'active']

الملء إلى الأمام باستخدام ffill()

import pandas as pd
import numpy as np

price = pd.Series(
    [100, np.nan, np.nan, 105, np.nan, 110],
    index=pd.date_range('2024-01', periods=6, freq='ME')
)

filled = price.ffill()
print(filled)
# 2024-01-31    100.0
# 2024-02-29    100.0
# 2024-03-31    100.0
# 2024-04-30    105.0
# 2024-05-31    105.0
# 2024-06-30    110.0

الملء إلى الخلف باستخدام bfill()

import pandas as pd
import numpy as np

df = pd.DataFrame({'value': [np.nan, np.nan, 3, np.nan, 5]})

print(df['value'].bfill())
# 0    3.0
# 1    3.0
# 2    3.0
# 3    5.0
# 4    5.0
# dtype: float64

المعامل limit للملء إلى الأمام والخلف

import pandas as pd
import numpy as np

s = pd.Series([1.0, np.nan, np.nan, np.nan, 5.0])

# Fill only the first NaN gap, leave the rest
print(s.ffill(limit=1))
# 0    1.0
# 1    1.0   <- filled
# 2    NaN   <- still NaN (limit reached)
# 3    NaN
# 4    5.0

ملء الأعمدة المختلفة بطرق مختلفة

import pandas as pd
import numpy as np

df = pd.DataFrame({
    'age': [25, np.nan, 30],
    'income': [50000, np.nan, 70000],
    'country': ['USA', np.nan, 'UK']
})

fill_values = {
    'age': df['age'].median(),
    'income': df['income'].mean(),
    'country': 'Unknown'
}

filled = df.fillna(fill_values)
print(filled)
#     age   income  country
# 0  25.0  50000.0      USA
# 1  27.5  60000.0  Unknown
# 2  30.0  70000.0       UK

الإسناد المراعي للمجموعات

import pandas as pd
import numpy as np

df = pd.DataFrame({
    'dept': ['Eng', 'Eng', 'HR', 'HR', 'Eng'],
    'salary': [90000, np.nan, 50000, np.nan, 110000]
})

# Fill salary NaN with the median salary for each department
df['salary'] = df.groupby('dept')['salary'].transform(
    lambda x: x.fillna(x.median())
)
print(df)
#    dept   salary
# 0   Eng  90000.0
# 1   Eng  100000.0   <- group median (90k+110k)/2
# 2    HR  50000.0
# 3    HR  50000.0
# 4   Eng  110000.0

الملء بقيمة ثابتة مميِّزة

import pandas as pd
import numpy as np

df = pd.DataFrame({
    'user_id': [1, 2, 3],
    'referral_source': ['email', np.nan, 'ad'],
    'trial_days': [14, np.nan, 7]
})

df['referral_source'] = df['referral_source'].fillna('unknown')
df['trial_days'] = df['trial_days'].fillna(-1).astype(int)
print(df)
#    user_id referral_source  trial_days
# 0        1           email          14
# 1        2         unknown          -1
# 2        3              ad           7

تسلسل fillna() في خط أنابيب

import pandas as pd
import numpy as np

df = pd.DataFrame({
    'user_id': [1, None, 3, 4],
    'score': [88, 95, np.nan, 76],
    'label': ['A', 'B', None, 'D']
})

cleaned = (
    df
    .dropna(subset=['user_id'])
    .fillna({'score': df['score'].mean(), 'label': 'Unknown'})
)
print(cleaned)
#    user_id  score    label
# 0      1.0   88.0        A
# 2      3.0   86.3  Unknown
# 3      4.0   76.0        D

التحقق من عدم بقاء أي NaN

import pandas as pd
import numpy as np

df = pd.DataFrame({'a': [1.0, np.nan, 3.0], 'b': [np.nan, 2.0, 3.0]})
filled = df.fillna(0)

# Verify
assert filled.isna().sum().sum() == 0, 'Some NaN remain!'
print('All NaN filled successfully')
print(filled.isna().sum())
# a    0
# b    0
# dtype: int64

تحقق سريع

مراجعة الدرس