Python Pandas Series

 # Pandas is a Python library for data manipulation and analysis.

# Mainly used in data science, analysis, and machine learning workflows.

# Used in Structured tabular data

import pandas as pd

import numpy as np

# ── 1. Creating a Series ──────────────────────────────────────────────────────

# A Series is a 1D labeled array — like a single column in a spreadsheet

# ── Syntax ────────────────────────────────────────────────────────────────────

# pd.Series(data, index, dtype, name)

# data → list, dict, scalar, or NumPy array (required)

# index → custom labels, default: 0, 1, 2... (optional)

# dtype → force data type e.g. float, str (optional)

# name → name for the Series (optional)

# pd.Series([10, 20, 30]) # from list, default index

# pd.Series([10, 20, 30], index=["a", "b", "c"]) # custom index

# pd.Series({"a": 10, "b": 20}) # from dict

# pd.Series(5, index=["x", "y", "z"]) # scalar repeated

# pd.Series([1, 2, 3], dtype=float, name="nums") # with dtype and name

s = pd.Series([10, 20, 30, 40, 50])

print(s)

# 0 10

# 1 20

# 2 30

# 3 40

# 4 50

# dtype: int64

# ── 2. Series with Custom Index ───────────────────────────────────────────────

# Labels replace default 0,1,2... index

s = pd.Series([10, 20, 30], index=["a", "b", "c"])

print(s)

# a 10

# b 20

# c 30

# dtype: int64

# ── 3. Series from a Dictionary ───────────────────────────────────────────────

# Keys become the index, values become the data

data = {"Alice": 90, "Bob": 85, "Carol": 92}

s = pd.Series(data)

print(s)

# Alice 90

# Bob 85

# Carol 92

# dtype: int64

# ── 4. Series from a Scalar ───────────────────────────────────────────────────

# Single value repeated for each index label

s = pd.Series(7, index=["x", "y", "z"])

print(s)

# x 7

# y 7

# z 7

# dtype: int64

# ── 5. Series from NumPy Array ────────────────────────────────────────────────

arr = np.array([1.1, 2.2, 3.3])

s = pd.Series(arr, index=["p", "q", "r"])

print(s)

# p 1.1

# q 2.2

# r 3.3

# dtype: float64

# ── 6. Accessing Elements ─────────────────────────────────────────────────────

s = pd.Series([10, 20, 30, 40, 50], index=["a", "b", "c", "d", "e"])

print(s["a"]) # 10 → by label

print(s[0]) # 10 → by position

print(s["b":"d"]) # b 20, c 30, d 40 → label slice (inclusive)

print(s[1:4]) # b 20, c 30, d 40 → position slice (exclusive end)

print(s[["a", "c", "e"]]) # 10, 30, 50 → multiple labels

# ── 7. Series Attributes ──────────────────────────────────────────────────────

s = pd.Series([10, 20, 30, 40, 50])

print(s.values) # [10 20 30 40 50] → NumPy array of values

print(s.index) # RangeIndex(start=0, stop=5, step=1)

print(s.dtype) # int64

print(s.shape) # (5,)

print(s.size) # 5 → total elements

print(s.name) # None → no name assigned yet

s.name = "Scores"

print(s.name) # Scores

# ── 8. Boolean Filtering ──────────────────────────────────────────────────────

s = pd.Series([10, 20, 30, 40, 50], index=["a", "b", "c", "d", "e"])

print(s > 25)

# a False

# b False

# c True

# d True

# e True

print(s[s > 25])

# c 30

# d 40

# e 50

print(s[s % 20 == 0]) # b 20, d 40 → divisible by 20

# ── 9. Arithmetic Operations ──────────────────────────────────────────────────

# Operations are aligned by index

s1 = pd.Series([1, 2, 3], index=["a", "b", "c"])

s2 = pd.Series([10, 20, 30], index=["a", "b", "c"])

print(s1 + s2) # a 11, b 22, c 33

print(s1 * s2) # a 10, b 40, c 90

print(s2 / s1) # a 10.0, b 10.0, c 10.0

# Mismatched index → NaN where labels don't align

s3 = pd.Series([100, 200], index=["a", "x"])

print(s1 + s3)

# a 101.0

# b NaN

# c NaN

# x NaN

# ── 10. Common Series Methods ─────────────────────────────────────────────────

s = pd.Series([30, 10, 50, 20, 40])

print(s.sum()) # 150 → total

print(s.mean()) # 30.0 → average

print(s.min()) # 10 → minimum

print(s.max()) # 50 → maximum

print(s.std()) # 15.81 → standard deviation

print(s.sort_values()) # sorted ascending: 10,20,30,40,50

print(s.sort_index()) # sorted by index: 0,1,2,3,4

print(s.value_counts()) # count of each unique value

print(s.describe())

# count 5.0

# mean 30.0

# std 15.81

# min 10.0

# 25% 20.0

# 50% 30.0

# 75% 40.0

# max 50.0

# ── 11. Handling Missing Values ───────────────────────────────────────────────

s = pd.Series([10, None, 30, None, 50])

print(s.isnull()) # False True False True False → True where NaN

print(s.notnull()) # True False True False True

print(s.dropna()) # 0 10.0, 2 30.0, 4 50.0 → removes NaN

print(s.fillna(0)) # replaces NaN with 0 → 10,0,30,0,50

print(s.fillna(s.mean())) # replaces NaN with mean → 10,30,30,30,50