Data Science Interview Questions #dataanlysis #datascience #eda #ai #ml #coding

🔍 Python Data Analysis Interview Questions (with Answers & Intuition)
💡 Whether you're preparing for a data science interview or brushing up your analysis skills, these Python-based Q&As are essential! Swipe 👉 for concepts, code, and clarity.

📘 Slide 1: Data Structures in Python
Q1: What are the main data structures in Python, and how do you choose between them?
List: Ordered, mutable → use for sequences.
Tuple: Ordered, immutable → use for fixed data.
Dict: Key-value pairs → best for mappings.
Set: Unique unordered items → ideal for membership checks.

📘 Slide 2: Handling Missing Data
Q2: How do you handle missing data in a DataFrame?
dropna() when data is plentiful
fillna() to impute
interpolate() for time series

📘 Slide 3: .loc[] vs .iloc[]
Q3: .loc[] → label-based
.iloc[] → integer-based

📘 Slide 4: Merging DataFrames
Q4: Merge/join datasets:
Join types: inner, outer, left, right

📘 Slide 5: NumPy Essentials
Q5: Must-know functions:

📘 Slide 6: Line Chart with Matplotlib

📘 Slide 7: Series vs DataFrame
Series = 1D labeled array
DataFrame = 2D labeled data (like a table)

📘 Slide 8: Handling Categorical Data

LabelEncoder() # ordinal

📘 Slide 9: Train-Test Split

✅ Prevents overfitting
✅ Evaluates generalization
📘 Slide 10: Feature Scaling

Use StandardScaler, MinMaxScaler to:
Normalize feature ranges
Improve gradient descent

📘 Slide 11: Imbalanced Data
📌 Try:
SMOTE / Oversampling
Undersampling
class_weight='balanced' in models

📘 Slide 12: L1 vs L2 Regularization
L1 (Lasso): Feature selection (sparse models)
L2 (Ridge): Penalizes large weights (prevents overfitting)

📘 Slide 13: groupby() in Pandas

Perfect for aggregation!

📘 Slide 14: Large Dataset Strategies
Generators
Dask / Vaex for out-of-core

📘 Slide 15: Common Cleaning Tasks
Handle nulls
Remove duplicates
Detect outliers
Normalize column types
✅ Save & Share this guide to level up your data science prep!