Pandas สำหรับการจัดการข้อมูล

What Is Pandas and Why Use It?

import pandas as pd
import numpy as np

# Create a DataFrame manually
df = pd.DataFrame({
    'name': ['Alice', 'Bob', 'Carol', 'Dave'],
    'age': [25, 30, 35, 28],
    'salary': [50000, 70000, 90000, 60000],
    'department': ['Engineering', 'Marketing', 'Engineering', 'Sales']
})
print(df)
print('\nShape:', df.shape)  # (4, 4)

Loading Data from CSV Files

import pandas as pd

# Load a CSV
df = pd.read_csv('titanic.csv')

# First inspection
print(df.head())       # first 5 rows
print(df.tail(3))      # last 3 rows
print(df.info())       # column types + non-null counts
print(df.describe())   # count, mean, std, min, max for numeric cols
print(df.columns.tolist())  # column names
print(df.shape)        # (891, 12)

Selecting Columns and Rows

import pandas as pd

df = pd.read_csv('titanic.csv')

# Select columns
age = df['Age']                          # Series
subset = df[['Age', 'Fare', 'Survived']] # DataFrame

# Filter rows with boolean conditions
survivors = df[df['Survived'] == 1]
first_class_women = df[(df['Pclass'] == 1) & (df['Sex'] == 'female')]

# Label-based selection (row label, column label)
print(df.loc[0, 'Name'])  # first row, Name column

# Position-based selection
print(df.iloc[0, 0])      # first row, first column

Handling Missing Values

import pandas as pd
import numpy as np

df = pd.read_csv('titanic.csv')

# Detect missing values
print(df.isnull().sum())  # count NaN per column
print(df.isnull().mean() * 100)  # % missing per column

# Drop columns with >50% missing
df_clean = df.dropna(thresh=len(df) * 0.5, axis=1)

# Fill numeric missing with median
df['Age'] = df['Age'].fillna(df['Age'].median())

# Fill categorical missing with most frequent
df['Embarked'] = df['Embarked'].fillna(df['Embarked'].mode()[0])

Data Types and Type Conversion

import pandas as pd

df = pd.read_csv('titanic.csv')
print(df.dtypes)  # see all column dtypes

# Convert a column's dtype
df['Survived'] = df['Survived'].astype(bool)
df['Pclass'] = df['Pclass'].astype('category')

# Convert object column to numeric (coerce errors to NaN)
df['Fare'] = pd.to_numeric(df['Fare'], errors='coerce')

# Parse dates
# df['date'] = pd.to_datetime(df['date'])

print(df.dtypes)

Adding and Transforming Columns

import pandas as pd

df = pd.read_csv('titanic.csv')

# Create a new column from existing ones
df['FamilySize'] = df['SibSp'] + df['Parch'] + 1  # +1 for self

# Binary flag: is the passenger alone?
df['IsAlone'] = (df['FamilySize'] == 1).astype(int)

# Bin a continuous feature into categories
df['AgeGroup'] = pd.cut(df['Age'], bins=[0, 12, 18, 60, 100],
                         labels=['Child', 'Teen', 'Adult', 'Senior'])

print(df[['FamilySize', 'IsAlone', 'AgeGroup']].head())

GroupBy: Aggregating by Category

import pandas as pd

df = pd.read_csv('titanic.csv')

# Mean survival rate by class
survival_by_class = df.groupby('Pclass')['Survived'].mean()
print(survival_by_class)
# Pclass 1: ~0.63, Pclass 2: ~0.47, Pclass 3: ~0.24

# Multiple aggregations at once
summary = df.groupby('Pclass').agg(
    passengers=('Survived', 'count'),
    survival_rate=('Survived', 'mean'),
    avg_fare=('Fare', 'mean')
)
print(summary)

Merging and Joining DataFrames

import pandas as pd

customers = pd.DataFrame({'id': [1, 2, 3], 'name': ['Alice', 'Bob', 'Carol']})
orders = pd.DataFrame({'id': [1, 1, 2], 'amount': [50, 30, 70]})

# Inner join on 'id'
merged = pd.merge(customers, orders, on='id', how='inner')
print(merged)

# Stack DataFrames with the same columns
df1 = pd.DataFrame({'A': [1, 2]})
df2 = pd.DataFrame({'A': [3, 4]})
combined = pd.concat([df1, df2], ignore_index=True)
print(combined)

Summary Statistics and Value Counts

import pandas as pd

df = pd.read_csv('titanic.csv')

# Numeric statistics
print(df['Age'].describe())
# count, mean, std, min, 25%, 50%, 75%, max

# Categorical distribution
print(df['Sex'].value_counts())
print(df['Pclass'].value_counts(normalize=True))  # proportions

# Correlation with target variable
correlations = df.corr()['Survived'].sort_values(ascending=False)
print(correlations)

Converting a DataFrame to NumPy for scikit-learn

import pandas as pd
from sklearn.model_selection import train_test_split

df = pd.read_csv('titanic.csv')

# Select numeric features only for simplicity
features = ['Pclass', 'Age', 'SibSp', 'Parch', 'Fare']
df_model = df[features + ['Survived']].dropna()

X = df_model[features].to_numpy()       # shape (n, 5)
y = df_model['Survived'].to_numpy()     # shape (n,)

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.2, random_state=42, stratify=y
)
print('Train shape:', X_train.shape)
print('Test shape:', X_test.shape)

Saving and Loading Processed Data

import pandas as pd

df = pd.read_csv('titanic.csv')

# Save as CSV
df.to_csv('titanic_processed.csv', index=False)

# Save as Parquet (much faster for large files)
# df.to_parquet('titanic_processed.parquet', index=False)

# Load back
df_reloaded = pd.read_csv('titanic_processed.csv')
print('Reloaded shape:', df_reloaded.shape)

Quick Check

Lesson Recap