100 Python Interview Questions &

Answers for Data Analyst and

Data Science

1. Question: Reverse a string

Answer:
s = 'hello'
print(s[::-1])

2. Question: Check if a number is prime

Answer:
n=7
print(all(n % i != 0 for i in range(2,
int(n**0.5) + 1)))

3. Question: Find factorial using recursion

SONIYA KAUSHIK | in
 Answer:
def fact(n):
return 1 if n == 0 else n * fact(n-1)
print(fact(5))

4. Question: Check palindrome string

Answer:
s = 'madam'
print(s == s[::-1])

5. Question: Find largest number in a list

Answer:
nums = [1, 5, 2]
print(max(nums))

6. Question: Swap two variables

SONIYA KAUSHIK | in
 Answer:
a, b = 5, 10
a, b = b, a
print(a, b)

7. Question: Count vowels in a string

Answer:
s = 'hello'
print(sum(1 for ch in s if ch in 'aeiou'))

8. Question: Check Armstrong number

Answer:
n = 153
print(sum(int(d) ** 3 for d in str(n)) == n)

9. Question: Generate Fibonacci series

SONIYA KAUSHIK | in
 Answer:
a, b = 0, 1
for _ in range(5):
print(a)
a, b = b, a + b

10. Question: Find GCD of two numbers

Answer:
import math
print([Link](12, 15))

11. Question: Check anagram

Answer:
s1, s2 = 'listen', 'silent'
print(sorted(s1) == sorted(s2))

SONIYA KAUSHIK | in
12. Question: Reverse words in a sentence
Answer:
s = 'hello world'
print(' '.join([Link]()[::-1]))

13. Question: Find duplicates in a list

Answer:
nums = [1, 2, 2, 3]
print([x for x in set(nums) if [Link](x)
> 1])

14. Question: Find second largest number in

a list
Answer:
nums = [1, 2, 3, 4]
print(sorted(set(nums))[-2])

SONIYA KAUSHIK | in
15. Question: Check if string contains only
digits
Answer:
print('123'.isdigit())

16. Question: Flatten nested list

Answer:
nested = [[1, 2], [3, 4]]
flat = [x for sub in nested for x in sub]
print(flat)

17. Question: Sort dictionary by values

Answer:
d = {'a': 2, 'b': 1}
print(dict(sorted([Link](), key=lambda x:
x[1])))

SONIYA KAUSHIK | in
18. Question: Count words in a string
Answer:
s = 'this is test'
print(len([Link]()))

19. Question: Check leap year

Answer:
y = 2024
print(y % 4 == 0 and (y % 100 != 0 or y %
400 == 0))

20. Question: Merge two dictionaries

Answer:
d1 = {'a': 1}
d2 = {'b': 2}
[Link](d2)
print(d1)
SONIYA KAUSHIK | in
21. Question: Group words by first letter
Answer:
from collections import defaultdict
words =
["apple","ant","banana","ball","cat","car"]
grouped = defaultdict(list)
for word in words:
grouped[word[0]].append(word)
print(dict(grouped))

22. Question: Find all pairs in list whose sum

equals target
Answer:
nums = [1,2,3,4,5,6,7]
target = 8

SONIYA KAUSHIK | in
 pairs = [(a,b) for i,a in enumerate(nums) for
b in nums[i+1:] if a+b==target]
print(pairs)

23. Question: Convert list of tuples into

dictionary
Answer:
pairs = [("a",1),("b",2),("c",3)]
print(dict(pairs))

24. Question: Find top 3 most frequent

elements in a list
Answer:
from collections import Counter
nums = [1,2,2,3,3,3,4,4,4,4,5]
print(Counter(nums).most_common(3))

SONIYA KAUSHIK | in
25. Question: Transpose a matrix
Answer:
matrix = [[1,2,3],[4,5,6],[7,8,9]]
transpose = [[row[i] for row in matrix] for i
in range(len(matrix[0]))]
print(transpose)

26. Question: Implement stack using Python

list
Answer:
stack = []
[Link](10)
[Link](20)
print([Link]())

27. Question: Implement queue using

[Link]

SONIYA KAUSHIK | in
 Answer:
from collections import deque
queue = deque()
[Link](10)
[Link](20)
print([Link]())

28. Question: Generate random numbers

without random module
Answer:
import time
def pseudo_random(seed=1):
seed = (seed*9301+49297) % 233280
return seed/233280.0
print(pseudo_random(int([Link]())))

29. Question: Convert string to title case

SONIYA KAUSHIK | in
 Answer:
text = "data science with python"
print([Link]())

30. Question: Remove punctuation from

string
Answer:
import string
text = "Hello, World! Data@Science."
clean = "".join(c for c in text if c not in
[Link])
print(clean)

31. Question: Load CSV in pandas and

display first 10 rows
Answer:
import pandas as pd

SONIYA KAUSHIK | in
 df = pd.read_csv("[Link]")
print([Link](10))

32. Question: Select rows where column

value > 100
Answer:
print(df[df["Sales"] > 100])

33. Question: Drop rows with missing values

Answer:
print([Link]())

34. Question: Fill missing values with column

mean
Answer:
df["Sales"].fillna(df["Sales"].mean(),
inplace=True)

SONIYA KAUSHIK | in
35. Question: Merge two DataFrames on a
column
Answer:
df1 = [Link]({"ID":[1,2],"Name":
["A","B"]})
df2 = [Link]({"ID":[1,2],"Age":
[25,30]})
merged = [Link](df1,df2,on="ID")
print(merged)

36. Question: Group data by column and

calculate mean
Answer:
print([Link]("Category")
["Sales"].mean())

SONIYA KAUSHIK | in
37. Question: Sort DataFrame by multiple
columns
Answer:
print(df.sort_values(by=
["Category","Sales"], ascending=[True,False]))

38. Question: Apply custom function to

column
Answer:
df["Discounted"] =
df["Sales"].apply(lambda x: x*0.9)

39. Question: Find number of unique values

in a column
Answer:
print(df["CustomerID"].nunique())

SONIYA KAUSHIK | in
40. Question: Rename multiple columns in
DataFrame
Answer:
[Link](columns=
{"Sales":"Total_Sales","Date":"Order_Date"},
inplace=True)

41. Question: Create a NumPy array of zeros

Answer:
import numpy as np
arr = [Link]((3,3))
print(arr)

42. Question: Create a NumPy array from 1

to 10
Answer:
arr = [Link](1,11)
print(arr)
SONIYA KAUSHIK | in
43. Question: Reshape 1D NumPy array to 2D
Answer:
arr = [Link](1,7).reshape(2,3)
print(arr)

44. Question: Find max and min in NumPy

array
Answer:
arr = [Link]([3,7,1,9,2])
print([Link](), [Link]())

45. Question: Compute mean, median, std of

array
Answer:
arr = [Link]([1,2,3,4,5,6])
print([Link](), [Link](arr), [Link]())
SONIYA KAUSHIK | in
46. Question: Slice first 3 elements of array
Answer:
arr = [Link]([10,20,30,40,50])
print(arr[:3])

47. Question: Find index of max in NumPy

array
Answer:
arr = [Link]([4,8,2,9,6])
print([Link]())

48. Question: Create diagonal matrix in

NumPy
Answer:
arr = [Link]([1,2,3])
print(arr)
SONIYA KAUSHIK | in
49. Question: Multiply two NumPy arrays
element-wise
Answer:
a = [Link]([1,2,3])
b = [Link]([4,5,6])
print(a*b)

50. Question: Perform matrix multiplication

Answer:
a = [Link]([[1,2],[3,4]])
b = [Link]([[5,6],[7,8]])
print([Link](a,b))

51. Question: Create random NumPy array of

shape 2x3
Answer:
SONIYA KAUSHIK | in
 arr = [Link](2,3)
print(arr)

52. Question: Normalize a NumPy array

Answer:
arr = [Link]([10,20,30])
norm = ([Link]())/([Link]()-[Link]())
print(norm)

53. Question: Get unique values from NumPy

array
Answer:
arr = [Link]([1,2,2,3,3,3,4])
print([Link](arr))

54. Question: Replace negative values with

zero
SONIYA KAUSHIK | in
 Answer:
arr = [Link]([-2,5,-7,8])
arr[arr < 0] = 0
print(arr)

55. Question: Check for NaN in NumPy array

Answer:
arr = [Link]([1,[Link],3])
print([Link](arr))

56. Question: Convert NumPy array to

Python list
Answer:
arr = [Link]([1,2,3])
print([Link]())

SONIYA KAUSHIK | in
57. Question: Filter rows in pandas with
multiple conditions
Answer:
df = [Link]({"A":[1,2,3,4],"B":
[10,20,30,40]})
print(df[(df["A"] > 2) & (df["B"] < 40)])

58. Question: Create pivot table in pandas

Answer:
df = [Link]({"Category":
["A","A","B","B"],"Sales":[100,200,300,400]})
pivot = df.pivot_table(values="Sales",
index="Category", aggfunc="sum")
print(pivot)

59. Question: Get correlation matrix

Answer:
print([Link]())
SONIYA KAUSHIK | in
60. Question: Save DataFrame to CSV
Answer:
df.to_csv("[Link]", index=False)

61. Question: Select specific columns

Answer:
df = [Link]({"A":[1,2,3],"B":
[4,5,6],"C":[7,8,9]})
print(df[["A","C"]])

62. Question: Sort DataFrame by column

descending
Answer:
print(df.sort_values("B", ascending=False))

63. Question: Rename columns

SONIYA KAUSHIK | in
 Answer:
df = [Link](columns=
{"A":"Col1","B":"Col2"})
print(df)

64. Question: Drop rows with missing values

Answer:
df = [Link]({"A":[1,None,3],"B":
[4,5,None]})
print([Link]())

65. Question: Fill missing values with mean

Answer:
df["A"].fillna(df["A"].mean(), inplace=True)
print(df)

66. Question: Convert column to datetime

SONIYA KAUSHIK | in
 Answer:
df = [Link]({"Date":["2023-01-
01","2023-02-01"]})
df["Date"] = pd.to_datetime(df["Date"])
print([Link])

67. Question: Extract year and month from

datetime
Answer:
df["Year"] = df["Date"].[Link]
df["Month"] = df["Date"].[Link]
print(df)

68. Question: Remove duplicate rows

Answer:
df = [Link]({"A":[1,2,2,3],"B":
[4,5,5,6]})

SONIYA KAUSHIK | in
 print(df.drop_duplicates())

69. Question: Group by column and sum

Answer:
df = [Link]({"Category":
["A","A","B"],"Sales":[100,200,300]})
print([Link]("Category")
["Sales"].sum())

70. Question: Apply custom function to

column
Answer:
df = [Link]({"A":[1,2,3]})
df["Square"] = df["A"].apply(lambda x:x**2)
print(df)

71. Question: Merge two DataFrames on key

SONIYA KAUSHIK | in
 Answer:
df1 = [Link]({"ID":[1,2],"Name":
["A","B"]})
df2 = [Link]({"ID":[1,2],"Age":
[25,30]})
print([Link](df1,df2,on="ID"))

72. Question: Concatenate two DataFrames

vertically
Answer:
df1 = [Link]({"A":[1,2]})
df2 = [Link]({"A":[3,4]})
print([Link]([df1,df2]))

73. Question: Find top 2 rows by column

Answer:
df = [Link]({"A":[10,40,30,20]})

SONIYA KAUSHIK | in
 print([Link](2,"A"))

74. Question: Find bottom 2 rows by column

Answer:
print([Link](2,"A"))

75. Question: Count missing values

Answer:
df = [Link]({"A":[1,None,3],"B":
[None,5,6]})
print([Link]().sum())

76. Question: Replace specific value

Answer:
df = [Link]({"A":[1,2,2,3]})
df["A"].replace(2, 99, inplace=True)
print(df)
SONIYA KAUSHIK | in
77. Question: Convert categorical to dummy
variables
Answer:
df = [Link]({"Fruit":
["Apple","Banana","Apple"]})
print(pd.get_dummies(df, columns=
["Fruit"]))

78. Question: Calculate cumulative sum

Answer:
df = [Link]({"Sales":
[100,200,300]})
df["Cumulative"] = df["Sales"].cumsum()
print(df)

79. Question: Calculate percentage of total

Answer:
SONIYA KAUSHIK | in
 df["Percentage"] =
df["Sales"]/df["Sales"].sum()*100
print(df)

80. Question: Detect outliers using IQR

Answer:
Q1 = df["Sales"].quantile(0.25)
Q3 = df["Sales"].quantile(0.75)
IQR = Q3 - Q1
outliers = df[(df["Sales"] < Q1 - 1.5*IQR) |
(df["Sales"] > Q3 + 1.5*IQR)]
print(outliers)

81. Question: Standardize a numeric column

using z-score
Answer:
df["Zscore"] = (df["Sales"] -
df["Sales"].mean()) / df["Sales"].std()
SONIYA KAUSHIK | in
 print(df)

82. Question: Normalize values between 0

and 1
Answer:
df["Normalized"] = (df["Sales"]-
df["Sales"].min())/(df["Sales"].max()-
df["Sales"].min())
print(df)

83. Question: Split dataset into train and test

Answer:
from sklearn.model_selection import
train_test_split
X = df[["Sales"]]
y = [0,1,0,1]
X_train,X_test,y_train,y_test =
train_test_split(X,y,test_size=0.2,random_stat
SONIYA KAUSHIK | in
e=42)
print(X_train,y_train)

84. Question: Train simple linear regression

Answer:
from sklearn.linear_model import
LinearRegression
X = [Link]([[1],[2],[3],[4]])
y = [Link]([2,4,6,8])
model = LinearRegression()
[Link](X,y)
print(model.coef_, model.intercept_)

85. Question: Make predictions

Answer:
pred = [Link]([[5]])
print(pred)
SONIYA KAUSHIK | in
86. Question: Evaluate regression using R2
score
Answer:
from [Link] import r2_score
y_true = [2,4,6,8]
y_pred = [Link](X)
print(r2_score(y_true,y_pred))

87. Question: Train logistic regression

Answer:
from sklearn.linear_model import
LogisticRegression
X = [Link]([[1],[2],[3],[4]])
y = [Link]([0,0,1,1])
clf = LogisticRegression()
[Link](X,y)
SONIYA KAUSHIK | in
 print([Link]([[2.5]]))

88. Question: Create confusion matrix

Answer:
from [Link] import
confusion_matrix
y_true = [0,0,1,1]
y_pred = [0,1,1,1]
print(confusion_matrix(y_true,y_pred))

89. Question: Calculate accuracy, precision,

recall, f1-score
Answer:
from [Link] import
classification_report
print(classification_report(y_true,y_pred))

SONIYA KAUSHIK | in
90. Question: Perform k-fold cross-
validation
Answer:
from sklearn.model_selection import
cross_val_score
scores = cross_val_score(clf,X,y,cv=3)
print([Link]())

91. Question: Train decision tree classifier

Answer:
from [Link] import
DecisionTreeClassifier
clf = DecisionTreeClassifier()
[Link](X,y)
print([Link]([[2]]))

92. Question: Train random forest classifier

SONIYA KAUSHIK | in
 Answer:
from [Link] import
RandomForestClassifier
clf = RandomForestClassifier()
[Link](X,y)
print([Link]([[3]]))

93. Question: Train support vector machine

classifier
Answer:
from [Link] import SVC
clf = SVC()
[Link](X,y)
print([Link]([[2.5]]))

94. Question: Scale features using

StandardScaler

SONIYA KAUSHIK | in
 Answer:
from [Link] import
StandardScaler
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)
print(X_scaled)

95. Question: Encode categorical using

LabelEncoder
Answer:
from [Link] import
LabelEncoder
fruits = ["Apple","Banana","Apple","Orange"]
encoder = LabelEncoder()
encoded = encoder.fit_transform(fruits)
print(encoded)

SONIYA KAUSHIK | in
96. Question: One-hot

encode categorical feature

Answer:
from [Link] import
OneHotEncoder
encoder = OneHotEncoder(sparse=False)
data = [Link](fruits).reshape(-1,1)
encoded = encoder.fit_transform(data)
print(encoded)

97. Question: Reduce dimensions using PCA

Answer:
from [Link] import PCA
pca = PCA(n_components=2)
X_reduced = pca.fit_transform(X_scaled)
SONIYA KAUSHIK | in
 print(X_reduced)

98. Question: Save trained model with joblib

Answer:
import joblib
[Link](clf,"[Link]")

99. Question: Load trained model with joblib

Answer:
model = [Link]("[Link]")
print([Link]([[2]]))

100. Question: Create pipeline with scaler

and classifier
Answer:
from [Link] import Pipeline

SONIYA KAUSHIK | in
 pipeline = Pipeline([("scaler",
StandardScaler()),("clf",
LogisticRegression())])
[Link](X,y)
print([Link]([[2.5]]))

---

SONIYA KAUSHIK | in