Data Analytics

I have sent you some real and important questions based on my reading of the book "Pandas Cookbook 2025".

1. What is the output of this code?

import pandas as pd
s = pd.Series([1, 2, 3], index=['a', 'b', 'c'])
print(s.reindex(['c', 'a', 'd']))

A. Series with values [3, 1, NaN] B. Series with values [3, 1] C. KeyError D. Series with values [1, 3, NaN] Correct answer: A. 2. What does this code produce?

import pandas as pd
df = pd.DataFrame({'a': [1, 2], 'b': [3, 4]})
print(df.assign(c=lambda x: x['a'] + x['b'])['c'].iloc[1])

A. 3 B. 4 C. 5 D. 6 Correct answer: C. 3. What is the result?

import pandas as pd
df = pd.DataFrame({'a': [1, 2, 3]})
df.loc[df['a'] > 1, 'a'] = 0
print(df['a'].tolist())

A. [1, 2, 3] B. [1, 0, 0] C. [0, 0, 0] D. [1, 2, 0] Correct answer: B. 4. What does this output?

import pandas as pd
s = pd.Series([10, 20, 30], index=[2, 0, 1])
print(s.sort_index().iloc[0])

A. 10 B. 20 C. 30 D. IndexError Correct answer: B. 5. What is returned?

import pandas as pd
df = pd.DataFrame({'a': [1, 1, 2]})
print(df['a'].value_counts().loc[1])

A. 1 B. 2 C. 3 D. KeyError Correct answer: B. 6. What does this code output?

import pandas as pd
s = pd.Series([1, 2, 3])
print(s.map({1: 'a', 2: 'b'}).isna().sum())

A. 0 B. 1 C. 2 D. 3 Correct answer: B. 7. What is the result?

import pandas as pd
df = pd.DataFrame({'a': [1, None, 3]})
print(df['a'].astype('Int64').isna().sum())

A. 0 B. 1 C. 2 D. Raises error Correct answer: B. 8. What does this produce?

import pandas as pd
df = pd.DataFrame({'a': [1, 2], 'b': [3, 4]})
print(df.filter(regex='a').shape)

A. (1, 2) B. (2, 1) C. (2, 2) D. (1, 1) Correct answer: B. 9. What is printed?

import pandas as pd
s = pd.Series(['1', '2', '3'])
print(s.str.cat(sep='-'))

A. 1-2-3 B. ['1-2-3'] C. Series D. Error Correct answer: A. 10. What does this code return?

import pandas as pd
df = pd.DataFrame({'a': [1, 2, 3]})
print(df.sample(n=1).shape)

A. (3, 1) B. (1, 3) C. (1, 1) D. Depends on random seed Correct answer: C. 11. What is the result?

import pandas as pd
s = pd.Series([1, 2, 3, 4])
print(s.rolling(2).sum().iloc[-1])

A. 4 B. 5 C. 6 D. NaN Correct answer: B. 12. What does this output?

import pandas as pd
df = pd.DataFrame({'a': [1, 2, 3]})
print(df.eval('b = a * 2').shape)

A. (3, 1) B. (3, 2) C. (1, 3) D. Error Correct answer: B. 13. What is returned?

import pandas as pd
df = pd.DataFrame({'a': [1, 2, 3]})
print(df.query('a % 2 == 0')['a'].iloc[0])

A. 1 B. 2 C. 3 D. KeyError Correct answer: B. 14. What does this code output?

import pandas as pd
s = pd.Series([1, 2, 3])
print(s.to_frame().shape)

A. (1, 3) B. (3, 1) C. (3, 3) D. (1, 1) Correct answer: B. 15. What is the result?

import pandas as pd
df = pd.DataFrame({'a': [1, 2]})
print(df.T.shape)

A. (2, 1) B. (1, 2) C. (2, 2) D. (1, 1) Correct answer: B. 16. What does this print?

import pandas as pd
df = pd.DataFrame({'a': [1, 2, 3]})
print(df.shift(1)['a'].isna().sum())

A. 0 B. 1 C. 2 D. 3 Correct answer: B. 17. What is the output?

import pandas as pd
df = pd.DataFrame({'a': [1, 2, 3]})
print(df.duplicated().any())

A. True B. False C. None D. Error Correct answer: B. 18. What does this code return?

import pandas as pd
s = pd.Series([3, 1, 2])
print(s.rank().tolist())

A. [3, 1, 2] B. [1, 2, 3] C. [3.0, 1.0, 2.0] D. [3.0, 1.0, 2.0] sorted Correct answer: C. 19. What is printed?

import pandas as pd
df = pd.DataFrame({'a': [1, 2, 3]})
print(df.memory_usage(deep=True).iloc[1] > 0)

A. True B. False C. None D. Error Correct answer: A. 20. What does this produce?

import pandas as pd
df = pd.DataFrame({'a': [1, 2, 3]})
print(df.select_dtypes(include='int').shape)

A. (3, 0) B. (0, 1) C. (3, 1) D. (1, 3) Correct answer: C.

1. What is the result of the following code?

import pandas as pd
s = pd.Series([10, 20, 30], index=[1, 2, 3])
print(s[1])

A. 10 B. 20 C. 30 D. KeyError Correct answer: A. 2. What will this code output?

import pandas as pd
s = pd.Series([10, 20, 30])
print(s.iloc[1])

A. 10 B. 20 C. 30 D. IndexError Correct answer: B. 3. What does this print?

import pandas as pd
df = pd.DataFrame({"a": [1, 2], "b": [3, 4]})
print(df.shape)

A. (4,) B. (2, 2) C. (1, 4) D. (2,) Correct answer: B. 4. What is returned by this expression?

df["a"]

A. DataFrame B. Series C. list D. ndarray Correct answer: B. 5. What does this code output?

import pandas as pd
df = pd.DataFrame({"a": [1, 2], "b": [3, 4]})
print(df[["a"]].shape)

A. (2,) B. (1, 2) C. (2, 1) D. (4, 1) Correct answer: C. 6. What is the result?

import pandas as pd
s = pd.Series([1, 2, 3])
print(s > 1)

A. [False, True, True] B. Series of booleans C. ndarray of booleans D. True Correct answer: B. 7. What does this code produce?

import pandas as pd
s = pd.Series([1, 2, 3])
print(s[s > 1])

A. Series [2, 3] B. Series [False, True, True] C. [2, 3] D. IndexError Correct answer: A. 8. What is the output?

import pandas as pd
df = pd.DataFrame({"a": [1, 2], "b": [3, 4]})
print(df.iloc[0, 1])

A. 1 B. 2 C. 3 D. 4 Correct answer: C. 9. What does this select?

df.loc[:, "a"]

A. First row B. First column as Series C. First column as DataFrame D. Entire DataFrame Correct answer: B. 10. What will this code output?

import pandas as pd
df = pd.DataFrame({"a": [1, 2, 3]})
print(len(df))

A. 1 B. 2 C. 3 D. Error Correct answer: C. 11. What is returned?

df.values

A. Series B. DataFrame C. NumPy ndarray D. list Correct answer: C. 12. What does this code output?

import pandas as pd
df = pd.DataFrame({"a": [1, 2, 3]})
print(df.index)

A. [0, 1, 2] B. list C. RangeIndex D. ndarray Correct answer: C. 13. What is the result?

df.columns

A. list B. Series C. Index D. dict Correct answer: C. 14. What does this return?

df.dtypes

A. dict B. Series C. DataFrame D. ndarray Correct answer: B. 15. What is printed?

import pandas as pd
s = pd.Series([1, None, 3])
print(s.isna().sum())

A. 0 B. 1 C. 2 D. 3 Correct answer: B. 16. What does this code output?

import pandas as pd
s = pd.Series([1, None, 3])
print(s.dropna().values)

A. [1, None, 3] B. [None] C. [1, 3] D. Error Correct answer: C. 17. What does this expression return?

df.head(1)

A. First column B. First row as Series C. First row as DataFrame D. Entire DataFrame Correct answer: C. 18. What is the output?

import pandas as pd
df = pd.DataFrame({"a": [1, 2, 3]})
print(df.tail(1)["a"].iloc[0])

A. 1 B. 2 C. 3 D. Error Correct answer: C. 19. What happens here?

df["c"] = df["a"] * 2

A. Raises KeyError B. Modifies column a C. Adds new column c D. No effect Correct answer: C. 20. What does this code output?

import pandas as pd
df = pd.DataFrame({"a": [1, 2, 3]})
print(df.sum().iloc[0])

A. 1 B. 3 C. 6 D. Error Correct answer: C. 21. What does df.mean() return? A. scalar B. Series C. DataFrame D. ndarray Correct answer: B. 22. What is the result?

df["a"].dtype

A. int B. numpy.int64 C. object D. float Correct answer: B. 23. What does this code do?

df = df.rename(columns={"a": "x"})

A. Renames index B. Renames column a to x C. Deletes column a D. Copies DataFrame only Correct answer: B. 24. What does this expression return?

df.loc[df["a"] > 1, :]

A. Boolean Series B. Filtered DataFrame C. Filtered Series D. Error Correct answer: B. 25. What is printed?

import pandas as pd
df = pd.DataFrame({"a": [1, 2, 3]})
print(df.empty)

A. True B. False C. None D. Error Correct answer: B. https://t.me/DataAnalyticsX 😱

25. What is the main advantage of using pd.Index.get_indexer when mixing selection styles? A. Improved readability B. Lazy evaluation C. Better performance by avoiding intermediate objects D. Automatic type conversion Correct answer: C. https://t.me/DataAnalyticsX ✅

1. What is the primary purpose of the pandas library? A. Working with unstructured multimedia data B. Creating and manipulating structured tabular data C. Building machine learning models D. Visualizing neural networks Correct answer: B. 2. Which pandas object is one-dimensional and enforces a homogeneous data type? A. DataFrame B. Index C. Series D. Panel Correct answer: C. 3. How can a pd.Series be best compared to an Excel structure? A. Entire worksheet B. Row C. Column D. Pivot table Correct answer: C. 4. Which object in pandas represents labels for rows or columns? A. Series B. DataFrame C. Index D. ndarray Correct answer: C. 5. What happens if no index is provided when creating a pd.Series? A. An error is raised B. A random index is created C. A RangeIndex starting at 0 is created D. Index values must be inferred manually Correct answer: C. 6. Which argument is used to explicitly set the data type of a pd.Series? A. type= B. data_type= C. dtype= D. astype= Correct answer: C. 7. What is the default value of the name attribute of a pd.Series if not provided? A. Empty string B. Undefined C. None D. "Series" Correct answer: C. 8. Which structure allows heterogeneous column data types? A. Series B. Index C. ndarray D. DataFrame Correct answer: D. 9. When constructing a DataFrame from a dictionary, what do the dictionary keys represent? A. Row labels B. Index levels C. Column labels D. Data types Correct answer: C. 10. Which attribute returns the number of rows in a pd.Series? A. size B. shape C. len() D. index Correct answer: B. 11. What does the pd.Series.shape attribute return? A. An integer B. A list C. A one-element tuple D. A two-element tuple Correct answer: C. 12. Which attribute of a DataFrame returns a Series of column data types? A. dtype B. dtypes C. types D. schema Correct answer: B. 13. What does len(df) return for a DataFrame? A. Number of columns B. Total number of elements C. Number of rows D. Size of memory used Correct answer: C. 14. In basic DataFrame selection using df["a"], what is returned? A. A DataFrame B. A scalar C. A NumPy array D. A Series Correct answer: D. 15. What does df[["a"]] return? A. A Series B. A DataFrame C. A scalar D. A NumPy array Correct answer: B. 16. When using [] with a Series that has a non-default integer index, selection is done by: A. Position B. Order of insertion C. Label D. Data type Correct answer: C. 17. Which method should be used for explicit position-based selection in a Series? A. loc B. at C. iloc D. ix Correct answer: C. 18. What does ser.iloc[1] return? A. All rows with label 1 B. The value at position 1 C. A slice of the Series D. A DataFrame Correct answer: B. 19. How many indexers are required when using DataFrame.iloc? A. One B. Two C. Three D. Unlimited Correct answer: B. 20. What does df.iloc[:, 0] return? A. First row B. First column as a Series C. First column as a DataFrame D. Entire DataFrame Correct answer: B. 21. Which method performs label-based selection in a Series? A. iloc B. at C. loc D. take Correct answer: C. 22. What is a key difference between slicing with loc and iloc? A. loc excludes the stop value B. iloc includes labels C. loc includes the stop label D. iloc works only with strings Correct answer: C. 23. Which operation may raise a KeyError when using loc? A. Slicing with ordered unique labels B. Selecting existing labels C. Slicing with non-unique unordered labels D. Selecting with lists Correct answer: C. 24. In a DataFrame, df.loc["Jack", :] selects: A. All rows named Jack B. All columns named Jack C. All columns for the row labeled Jack D. Only numeric columns Correct answer: C.

This channels is for Programmers, Coders, Software Engineers. 0️⃣ Python 1️⃣ Data Science 2️⃣ Machine Learning 3️⃣ Data Visualization 4️⃣ Artificial Intelligence 5️⃣ Data Analysis 6️⃣ Statistics 7️⃣ Deep Learning 8️⃣ programming Languages ✅ https://t.me/addlist/8_rRW2scgfRhOTc0 ✅ https://t.me/Codeprogrammer

Take Control of Selling in Amazon! 💫Too many tools, too little time? With dynamic pricing, real-time stock tracking, order monitoring and AI-powered BuyBox hunting, SellerFlash makes selling effortless in Amazon. 💫Say goodbye to manual chaos. With SellerFlash, you will manage listings, inventory, buyer messages and feedback campaigns all from one smart cloud platform designed for Amazon sellers. 👉🏽https://www.sellerflash.com/en/ Sponsored By WaybienAds

Take Control of Selling in Amazon! 💫Too many tools, too little time? With dynamic pricing, real-time stock tracking, order monitoring and AI-powered BuyBox hunting, SellerFlash makes selling effortless in Amazon. 💫Say goodbye to manual chaos. With SellerFlash, you will manage listings, inventory, buyer messages and feedback campaigns all from one smart cloud platform designed for Amazon sellers. 👉🏽https://www.sellerflash.com/en/ Sponsored By WaybienAds

🚀 MEGA SALE: Up to 87% OFF! These are real discounts on products everyone wants: 🎧 Premium wireless headphones 💻 Ultra-slim laptops 📷 Compact pro cameras ⌚ Latest-generation smartwatches 🔊 Smart speakers Everything is now available with massive discounts up to 87%. Perfect if you want to upgrade your gear without overspending. ⏳ Deals are limited once they're gone, they're gone. ⚠️ If you see it in stock, don’t think twice. 👉 Access the deals now #ad InsideAds

200$ to 20k$ SOL Challenge! As promised, i will do another challenge for those who missed the previous one! Last one we completed in 6 days, let’s do this one even quicker! Join my free group Before closing 👇 https://t.me/+DAKLP7eUy9Y3ZjY0 #ad InsideAds

# Select products in 'Electronics' or 'Audio' categories
print("Products in Electronics or Audio:")
print(df_pl.filter(pl.col('category').is_in(['Electronics', 'Audio'])))

# Select products with price between 50 and 200 (inclusive)
print("\nProducts with price between 50 and 200:")
print(df_pl.filter(pl.col('price').is_between(50, 200)))

#### SQL

-- Select products in 'Electronics' or 'Audio' categories
SELECT *
FROM products
WHERE category IN ('Electronics', 'Audio');

-- Select products with price between 50 and 200 (inclusive)
SELECT *
FROM products
WHERE price BETWEEN 50 AND 200;

# Create 'price_level' based on price and 'stock_status'
def get_price_level(price):
    if price > 200:
        return 'High'
    elif price > 50:
        return 'Medium'
    else:
        return 'Low'

def get_stock_status(stock):
    if stock == 0:
        return 'Out of Stock'
    elif stock < 50:
        return 'Low Stock'
    else:
        return 'In Stock'

result_pd = df_pd.assign(
    price_level=df_pd['price'].apply(get_price_level),
    stock_status=df_pd['stock_quantity'].apply(get_stock_status)
)[['product_name', 'price', 'price_level', 'stock_quantity', 'stock_status']]
print(result_pd)

#### polars

# Create 'price_level' based on price and 'stock_status'
result_pl = df_pl.select(
    'product_name',
    'price',
    pl.when(pl.col('price') > 200).then(pl.lit('High'))
    .when(pl.col('price') > 50).then(pl.lit('Medium'))
    .otherwise(pl.lit('Low'))
    .alias('price_level'),
    'stock_quantity',
    pl.when(pl.col('stock_quantity') == 0).then(pl.lit('Out of Stock'))
    .when(pl.col('stock_quantity') < 50).then(pl.lit('Low Stock'))
    .otherwise(pl.lit('In Stock'))
    .alias('stock_status')
)
print(result_pl)

#### SQL

-- Create price_level and stock_status based on conditions
SELECT
    product_name,
    price,
    CASE
        WHEN price > 200 THEN 'High'
        WHEN price > 50 THEN 'Medium'
        ELSE 'Low'
    END AS price_level,
    stock_quantity,
    CASE
        WHEN stock_quantity = 0 THEN 'Out of Stock'
        WHEN stock_quantity < 50 THEN 'Low Stock'
        ELSE 'In Stock'
    END AS stock_status
FROM products;

--- String Transformations in Select #### pandas

# Select product_name in uppercase and first 3 characters of category
result_pd = df_pd.assign(
    product_name_upper=df_pd['product_name'].str.upper(),
    category_prefix=df_pd['category'].str.slice(0, 3)
)[['product_name', 'product_name_upper', 'category', 'category_prefix']]
print(result_pd)

#### polars

# Select product_name in uppercase and first 3 characters of category
result_pl = df_pl.select(
    'product_name',
    pl.col('product_name').str.to_uppercase().alias('product_name_upper'),
    'category',
    pl.col('category').str.slice(0, 3).alias('category_prefix')
)
print(result_pl)

#### SQL

-- Select product_name in uppercase and first 3 characters of category
SELECT
    product_name,
    UPPER(product_name) AS product_name_upper,
    category,
    SUBSTRING(category, 1, 3) AS category_prefix -- Or LEFT(category, 3) in some SQL dialects
FROM products;

--- Selecting with Advanced Filtering (IN, BETWEEN equivalents) #### pandas

# Select products in 'Electronics' or 'Audio' categories
print("Products in Electronics or Audio:")
print(df_pd[df_pd['category'].isin(['Electronics', 'Audio'])])

# Select products with price between 50 and 200 (inclusive)
print("\nProducts with price between 50 and 200:")
print(df_pd[df_pd['price'].between(50, 200)])

#### polars

Selecting with Transformations and Conditional Logic #### Data Setup #### pandas

import pandas as pd

data = {
    'product_id': [101, 102, 103, 104, 105, 106, 107, 108],
    'product_name': ['Laptop', 'Mouse', 'Keyboard', 'Monitor', 'Webcam', 'Microphone', 'Speakers', 'Charger'],
    'category': ['Electronics', 'Electronics', 'Electronics', 'Electronics', 'Peripherals', 'Peripherals', 'Audio', 'Accessories'],
    'price': [1200.00, 25.00, 75.00, 300.00, 50.00, 80.00, 150.00, 15.00],
    'stock_quantity': [50, 200, 150, 70, 100, 60, 40, 0]
}
df_pd = pd.DataFrame(data)

#### polars

import polars as pl

data = {
    'product_id': [101, 102, 103, 104, 105, 106, 107, 108],
    'product_name': ['Laptop', 'Mouse', 'Keyboard', 'Monitor', 'Webcam', 'Microphone', 'Speakers', 'Charger'],
    'category': ['Electronics', 'Electronics', 'Electronics', 'Electronics', 'Peripherals', 'Peripherals', 'Audio', 'Accessories'],
    'price': [1200.00, 25.00, 75.00, 300.00, 50.00, 80.00, 150.00, 15.00],
    'stock_quantity': [50, 200, 150, 70, 100, 60, 40, 0]
}
df_pl = pl.DataFrame(data)

#### SQL (Conceptual Table Structure and Data)

-- CREATE TABLE products (
--     product_id INT PRIMARY KEY,
--     product_name VARCHAR(255),
--     category VARCHAR(255),
--     price DECIMAL(10, 2),
--     stock_quantity INT
-- );

-- INSERT INTO products VALUES
-- (101, 'Laptop', 'Electronics', 1200.00, 50),
-- (102, 'Mouse', 'Electronics', 25.00, 200),
-- (103, 'Keyboard', 'Electronics', 75.00, 150),
-- (104, 'Monitor', 'Electronics', 300.00, 70),
-- (105, 'Webcam', 'Peripherals', 50.00, 100),
-- (106, 'Microphone', 'Peripherals', 80.00, 60),
-- (107, 'Speakers', 'Audio', 150.00, 40),
-- (108, 'Charger', 'Accessories', 15.00, 0);

--- Creating New Columns with Expressions (SELECT col1, col2 + col3 AS new_col) #### pandas

# Select 'product_name', 'price', and calculate 'total_inventory_value'
result_pd = df_pd.assign(
    total_inventory_value=df_pd['price'] * df_pd['stock_quantity'],
    discounted_price=df_pd['price'] * 0.9
)[['product_name', 'price', 'total_inventory_value', 'discounted_price']]
print(result_pd)

#### polars

# Select 'product_name', 'price', and calculate 'total_inventory_value'
result_pl = df_pl.select(
    'product_name',
    'price',
    (pl.col('price') * pl.col('stock_quantity')).alias('total_inventory_value'),
    (pl.col('price') * 0.9).alias('discounted_price')
)
print(result_pl)

#### SQL

-- Select product_name, price, and calculate total_inventory_value and discounted_price
SELECT
    product_name,
    price,
    price * stock_quantity AS total_inventory_value,
    price * 0.9 AS discounted_price
FROM products;

--- Conditional Column Creation (CASE WHEN equivalent) #### pandas

Machine Learning with Python: Try the bot with a large search database within Petligram

Now you can search Eveything 🎉 Your can search everything by keywords: Channels, Chats, Bots. . . Videos, Music, Images, Files. . . even 🤭 18+ content 😀 Type your interests to explore ! #ad

Is Your Crypto Transfer Secure? Score Your Transfer analyzes wallet activity, flags risky transactions in real time, and generates downloadable compliance reports—no technical skills needed. Protect funds & stay compliant. Sponsored By WaybienAds

Now you can search Eveything 🎉 Your can search everything by keywords: Channels, Chats, Bots. . . Videos, Music, Images, Files. . . even 🤭 18+ content 😀 Type your interests to explore ! #ad

Now you can search Eveything 🎉 Your can search everything by keywords: Channels, Chats, Bots. . . Videos, Music, Images, Files. . . even 🤭 18+ content 😀 Type your interests to explore ! #ad