# 2.1 Pandas - Cook Book

🐼 Pandas Concepts with Demo Programs

This blog covers essential Pandas concepts with simple code examples. Each demo has syntax highlighting and a copy button — perfect for learning or sharing!

---

1. Importing Pandas & NumPy

import pandas as pd
import numpy as np

2. Creating Series & DataFrames

# Series
s = pd.Series([1, 3, 5, np.nan, 6, 8])
print(s)

# DataFrame from NumPy array
dates = pd.date_range("20230101", periods=6)
df = pd.DataFrame(np.random.randn(6, 4), index=dates, columns=list("ABCD"))
print(df)

# DataFrame from dictionary
df2 = pd.DataFrame({
    "A": 1.0,
    "B": pd.Timestamp("20230102"),
    "C": pd.Series(1, index=list(range(4)), dtype="float32"),
    "D": np.array([3]*4, dtype="int32"),
    "E": pd.Categorical(["test", "train", "test", "train"]),
    "F": "foo",
})
print(df2)
print(df2.dtypes)

3. Viewing Data

print(df.head())  # Top 5 rows
print(df.tail(3))  # Last 3 rows

4. Selecting Columns

print(df["A"])       # Single column
print(df[["A", "B"]]) # Multiple columns

5. Selecting Rows

print(df.loc[dates[0]])        # Row by label
print(df.iloc[0:3, 0:2])       # Row and column by integer position

6. Boolean Indexing

print(df[df["A"] > 0])  # Rows where column A > 0
print(df[df > 0])         # All positive values

7. Setting Values

df.iloc[0, 1] = 100
df.loc[:, "B"] = np.array([1]*6)
print(df)

8. Handling Missing Data

df2 = df.copy()
df2.iloc[0, 0] = np.nan
print(df2.dropna())  # Drop rows with NaN
print(df2.fillna(0)) # Fill NaN with 0

9. Operations & Descriptive Statistics

print(df.mean())      # Column-wise mean
print(df.cumsum())    # Cumulative sum
print(df.describe())  # Summary statistics

10. Apply & Map

df2 = df.apply(np.cumsum)
print(df2)

df["A"] = df["A"].map(lambda x: x*2)
print(df)

11. Sorting

df.sort_index(axis=1, ascending=False, inplace=True)  # Sort columns
df.sort_values(by="B", ascending=True, inplace=True)    # Sort rows by column B
print(df)

12. Merging & Concatenating

df1 = pd.DataFrame(np.random.randn(3, 4), columns=list("ABCD"))
df2 = pd.DataFrame(np.random.randn(3, 4), columns=list("ABCD"))
result = pd.concat([df1, df2])
print(result)

13. Grouping

df = pd.DataFrame({
    "A": ["foo", "bar", "foo", "bar"],
    "B": ["one", "one", "two", "two"],
    "C": np.random.randn(4),
    "D": np.random.randn(4)
})
grouped = df.groupby("A").sum()
print(grouped)