Python — Data Science

◆Python◆Intermediate🎯Free Tools

Introduction

Python is the dominant language for data science thanks to three core libraries: NumPy for numerical computation, Pandas for data manipulation, and Matplotlib for visualization. Together they form the foundation of nearly every data workflow.

The typical data science workflow is: load data, clean and transform it, explore patterns with statistics and plots, build models, and communicate results. Jupyter notebooks provide an interactive environment for each step.

NumPy Arrays

NumPy provides the ndarray, a fast, fixed-type multidimensional array. Vectorized operations on NumPy arrays are 10-100x faster than equivalent Python loops because they run in compiled C code.

numpy_basics.py

Python

1	import numpy as np
2
3	# Creating arrays
4	a = np.array([1, 2, 3, 4, 5]) # from list
5	b = np.zeros((3, 4)) # 3x4 zeros
6	c = np.ones((2, 3, 4)) # 3D ones
7	d = np.arange(0, 10, 0.5) # like range() but float
8	e = np.linspace(0, 1, 100) # 100 evenly spaced [0,1]
9	f = np.random.randn(3, 4) # 3x4 normal distribution
10
11	# Shape and dtype
12	print(a.shape) # (5,)
13	print(f.shape) # (3, 4)
14	print(a.dtype) # int64
15	print(b.dtype) # float64
16
17	# Reshaping
18	matrix = np.arange(12).reshape(3, 4)
19	print(matrix)
20	# [[ 0 1 2 3]
21	# [ 4 5 6 7]
22	# [ 8 9 10 11]]
23
24	# Indexing and slicing
25	print(matrix[0, :]) # first row → [0 1 2 3]
26	print(matrix[:, 2]) # third column → [2 6 10]
27	print(matrix[1:3, 1:3]) # submatrix → [[5 6] [9 10]]

numpy_ops.py

Python

1	# Vectorized operations — no loops needed
2	a = np.array([1, 2, 3, 4])
3	b = np.array([10, 20, 30, 40])
4
5	print(a + b) # [11 22 33 44]
6	print(a * b) # [10 40 90 160]
7	print(a ** 2) # [1 4 9 16]
8	print(np.sqrt(a)) # [1.0 1.414 1.732 2.0]
9
10	# Aggregations
11	data = np.random.randn(1000)
12	print(np.mean(data)) # ~0.0
13	print(np.std(data)) # ~1.0
14	print(np.median(data)) # ~0.0
15	print(np.percentile(data, [25, 50, 75])) # quartiles
16
17	# Broadcasting — operations between different shapes
18	matrix = np.arange(12).reshape(3, 4)
19	row = np.array([1, 0, 1, 0])
20	print(matrix + row) # adds row to each row of matrix
21
22	# Boolean indexing
23	data = np.array([1, 5, 3, 8, 2, 9, 4])
24	mask = data > 4
25	print(data[mask]) # [5 8 9]
26	print(np.sum(mask)) # 3 elements > 4
27
28	# Linear algebra
29	A = np.array([[1, 2], [3, 4]])
30	B = np.array([[5, 6], [7, 8]])
31	print(A @ B) # matrix multiply
32	print(np.linalg.inv(A)) # inverse
33	print(np.linalg.det(A)) # determinant

ℹ

info

Always prefer vectorized NumPy operations over Python loops. If you find yourself writing a for-loop over array elements, there is almost certainly a NumPy function that does it faster.

Pandas DataFrames

Pandas builds on NumPy to provide labeled, heterogeneous tabular data via DataFrame and Series. It is the primary tool for data cleaning, transformation, and exploration.

pandas_basics.py

Python

1	import pandas as pd
2
3	# Creating DataFrames
4	df = pd.DataFrame({
5	"name": ["Alice", "Bob", "Charlie", "Diana"],
6	"age": [28, 35, 42, 31],
7	"city": ["NYC", "SF", "NYC", "LA"],
8	"salary": [85000, 120000, 95000, 110000],
9	})
10
11	# From CSV
12	# df = pd.read_csv("data.csv")
13	# From JSON
14	# df = pd.read_json("data.json")
15	# From Excel
16	# df = pd.read_excel("data.xlsx")
17
18	# Basic inspection
19	print(df.shape) # (4, 4)
20	print(df.head(2)) # first 2 rows
21	print(df.dtypes) # column types
22	print(df.describe()) # summary statistics
23	print(df.info()) # non-null counts and types

pandas_select.py

Python

1	# Selection and filtering
2	print(df["name"]) # Series
3	print(df[["name", "age"]]) # DataFrame subset
4
5	# loc — label-based
6	print(df.loc[0:2, "name":"city"]) # rows 0-2, name through city
7
8	# iloc — integer position
9	print(df.iloc[0:2, 0:3]) # first 2 rows, first 3 columns
10
11	# Boolean filtering
12	seniors = df[df["age"] > 35]
13	nyc = df[df["city"] == "NYC"]
14	complex_filter = df[(df["age"] > 30) & (df["salary"] > 100000)]
15
16	# Query syntax
17	result = df.query("age > 30 and city == 'NYC'")
18
19	# Adding columns
20	df["bonus"] = df["salary"] * 0.1
21	df["senior"] = df["age"] > 35
22
23	# apply — row or column-wise operations
24	df["name_upper"] = df["name"].str.upper()
25	df["age_group"] = df["age"].apply(lambda x: "senior" if x > 35 else "junior")

pandas_group.py

Python

1	# Grouping and aggregation
2	city_stats = df.groupby("city").agg(
3	avg_age=("age", "mean"),
4	avg_salary=("salary", "mean"),
5	count=("name", "count"),
6	).reset_index()
7	print(city_stats)
8	# city avg_age avg_salary count
9	# 0 LA 31.0 110000.0 1
10	# 1 NYC 35.0 90000.0 2
11	# 2 SF 35.0 120000.0 1
12
13	# Multiple groupby columns
14	# df.groupby(["city", "senior"]).agg(...)
15
16	# Sorting
17	print(df.sort_values("salary", ascending=False))
18	print(df.sort_values(["city", "salary"], ascending=[True, False]))
19
20	# Merging
21	employees = pd.DataFrame({
22	"name": ["Alice", "Bob"],
23	"dept": ["Engineering", "Marketing"],
24	})
25	merged = pd.merge(df, employees, on="name", how="left")
26
27	# Pivot tables
28	pivot = df.pivot_table(
29	values="salary",
30	index="city",
31	aggfunc=["mean", "count"],
32	)

Data Cleaning

cleaning.py

Python

1	import pandas as pd
2	import numpy as np
3
4	# Load messy data
5	df = pd.read_csv("sales.csv")
6
7	# Check for missing values
8	print(df.isnull().sum())
9
10	# Drop rows with missing values
11	df_clean = df.dropna(subset=["revenue", "date"])
12
13	# Fill missing values
14	df["category"] = df["category"].fillna("Unknown")
15	df["price"] = df["price"].fillna(df["price"].median())
16
17	# Remove duplicates
18	df = df.drop_duplicates(subset=["order_id"])
19
20	# Fix data types
21	df["date"] = pd.to_datetime(df["date"])
22	df["price"] = pd.to_numeric(df["price"], errors="coerce")
23
24	# String cleanup
25	df["product"] = df["product"].str.strip().str.lower()
26
27	# Outlier detection with IQR
28	Q1 = df["price"].quantile(0.25)
29	Q3 = df["price"].quantile(0.75)
30	IQR = Q3 - Q1
31	lower = Q1 - 1.5 * IQR
32	upper = Q3 + 1.5 * IQR
33	df = df[(df["price"] >= lower) & (df["price"] <= upper)]
34
35	# Rename columns
36	df = df.rename(columns={"price": "unit_price", "qty": "quantity"})
37
38	# Replace values
39	df["status"] = df["status"].replace({
40	"cancelled": "canceled",
41	"shipped": "completed",
42	})

✓

best practice

Always inspect your data before cleaning. Use df.info(), df.describe(), and df.isnull().sum() to understand what you are working with before making changes.

Matplotlib Plotting

plotting.py

Python

1	import matplotlib.pyplot as plt
2	import numpy as np
3
4	# Line plot
5	x = np.linspace(0, 10, 100)
6	plt.figure(figsize=(10, 6))
7	plt.plot(x, np.sin(x), label="sin(x)", color="#3776AB")
8	plt.plot(x, np.cos(x), label="cos(x)", color="#FF6B35")
9	plt.title("Trigonometric Functions")
10	plt.xlabel("x")
11	plt.ylabel("y")
12	plt.legend()
13	plt.grid(True, alpha=0.3)
14	plt.savefig("trig_plot.png", dpi=150, bbox_inches="tight")
15	plt.close()
16
17	# Bar chart
18	categories = ["A", "B", "C", "D"]
19	values = [23, 45, 56, 78]
20	plt.figure(figsize=(8, 5))
21	plt.bar(categories, values, color="#3776AB")
22	plt.title("Category Values")
23	plt.savefig("bar_chart.png")
24	plt.close()
25
26	# Histogram
27	data = np.random.randn(1000)
28	plt.figure(figsize=(8, 5))
29	plt.hist(data, bins=30, edgecolor="white", alpha=0.7, color="#3776AB")
30	plt.title("Normal Distribution")
31	plt.savefig("histogram.png")
32	plt.close()
33
34	# Scatter plot
35	x = np.random.randn(200)
36	y = 2 * x + np.random.randn(200) * 0.5
37	plt.figure(figsize=(8, 6))
38	plt.scatter(x, y, alpha=0.5, c="#3776AB", s=20)
39	plt.title("Scatter Plot with Correlation")
40	plt.savefig("scatter.png")
41	plt.close()

subplots.py

Python

1	# Subplots — multiple charts in one figure
2	fig, axes = plt.subplots(2, 2, figsize=(12, 10))
3
4	# Top-left: line plot
5	axes[0, 0].plot(x, np.sin(x), color="#3776AB")
6	axes[0, 0].set_title("Sine Wave")
7
8	# Top-right: bar chart
9	axes[0, 1].bar(["A", "B", "C"], [3, 7, 5], color="#FF6B35")
10	axes[0, 1].set_title("Bar Chart")
11
12	# Bottom-left: histogram
13	axes[1, 0].hist(np.random.randn(500), bins=25, color="#3776AB")
14	axes[1, 0].set_title("Distribution")
15
16	# Bottom-right: scatter
17	axes[1, 1].scatter(np.random.randn(100), np.random.randn(100), alpha=0.6)
18	axes[1, 1].set_title("Scatter")
19
20	plt.tight_layout()
21	plt.savefig("subplots.png", dpi=150)
22	plt.close()
23
24	# Pandas integration — plot directly from DataFrame
25	df.groupby("city")["salary"].mean().plot(
26	kind="bar", title="Average Salary by City", figsize=(8, 5)
27	)
28	plt.tight_layout()
29	plt.savefig("pandas_plot.png")
30	plt.close()

Complete Workflow

workflow.py

Python

1	# End-to-end data analysis workflow
2	import pandas as pd
3	import numpy as np
4	import matplotlib.pyplot as plt
5
6	# 1. Load data
7	df = pd.read_csv("sales_2024.csv", parse_dates=["date"])
8
9	# 2. Initial exploration
10	print(f"Shape: {df.shape}")
11	print(f"Columns: {df.columns.tolist()}")
12	print(f"Missing:\n{df.isnull().sum()}")
13	print(f"Date range: {df['date'].min()} to {df['date'].max()}")
14
15	# 3. Clean data
16	df = df.dropna(subset=["revenue"])
17	df = df[df["revenue"] > 0]
18	df["month"] = df["date"].dt.to_period("M")
19
20	# 4. Transform and analyze
21	monthly = df.groupby("month").agg(
22	total_revenue=("revenue", "sum"),
23	avg_order=("revenue", "mean"),
24	num_orders=("revenue", "count"),
25	).reset_index()
26	monthly["month_str"] = monthly["month"].astype(str)
27
28	# 5. Visualize
29	fig, ax1 = plt.subplots(figsize=(12, 6))
30	ax1.bar(monthly["month_str"], monthly["total_revenue"], color="#3776AB", alpha=0.7)
31	ax1.set_xlabel("Month")
32	ax1.set_ylabel("Total Revenue", color="#3776AB")
33	ax1.tick_params(axis="y", labelcolor="#3776AB")
34	ax1.set_xticklabels(monthly["month_str"], rotation=45)
35
36	ax2 = ax1.twinx()
37	ax2.plot(monthly["month_str"], monthly["num_orders"], color="#FF6B35", marker="o")
38	ax2.set_ylabel("Number of Orders", color="#FF6B35")
39	ax2.tick_params(axis="y", labelcolor="#FF6B35")
40
41	plt.title("Monthly Revenue and Orders")
42	plt.tight_layout()
43	plt.savefig("monthly_report.png", dpi=150)
44	plt.close()
45
46	# 6. Export results
47	monthly.to_csv("monthly_summary.csv", index=False)
48	print("Report generated: monthly_report.png")

ℹ

info

In Jupyter notebooks, add %matplotlib inline at the top to display plots directly in the notebook. Use %timeit to benchmark code and %load_ext autoreload to auto-reload changed modules.

$Blueprint — Engineering Documentation·Section ID: PYTHON-DS·Revision: 1.0

X GitHub YouTube Instagram Facebook Discord Telegram Buy me a coffee Sponsor