In Python, handling CSV files is straightforward using the built-in csv module for reading and writing tabular data, or pandas for advanced analysis—essential for data processing tasks like importing/exporting datasets in interviews.

# Reading CSV with csv module (basic)
import csv
with open('data.csv', 'r') as file:
    reader = csv.reader(file)
    data = list(reader)  # data = [['Name', 'Age'], ['Alice', '30'], ['Bob', '25']]

# Writing CSV with csv module
import csv
with open('output.csv', 'w', newline='') as file:
    writer = csv.writer(file)
    writer.writerow(['Name', 'Age'])  # Header
    writer.writerows([['Alice', 30], ['Bob', 25]])  # Data rows

# Advanced: Reading with pandas (handles headers, missing values)
import pandas as pd
df = pd.read_csv('data.csv')  # df = DataFrame with columns 'Name', 'Age'
print(df.head())  # Output: First 5 rows preview

# Writing with pandas
df.to_csv('output.csv', index=False)  # Saves without row indices

#python #csv #pandas #datahandling #fileio #interviewtips

👉 @DataScience4

Top 100 Data Analysis Commands & Functions

#DataAnalysis #Pandas #DataLoading #Inspection

Part 1: Pandas - Data Loading & Inspection

#1. pd.read_csv()
Reads a comma-separated values (csv) file into a Pandas DataFrame.

import pandas as pd
from io import StringIO

csv_data = "col1,col2,col3\n1,a,True\n2,b,False"
df = pd.read_csv(StringIO(csv_data))
print(df)

col1 col2   col3
0     1    a   True
1     2    b  False

#2. df.head()
Returns the first n rows of the DataFrame (default is 5).

import pandas as pd
df = pd.DataFrame({'A': range(10), 'B': list('abcdefghij')})
print(df.head(3))

A  B
0  0  a
1  1  b
2  2  c

#3. df.tail()
Returns the last n rows of theDataFrame (default is 5).

import pandas as pd
df = pd.DataFrame({'A': range(10), 'B': list('abcdefghij')})
print(df.tail(3))

A  B
7  7  h
8  8  i
9  9  j

#4. df.info()
Prints a concise summary of a DataFrame, including data types and non-null values.

import pandas as pd
import numpy as np
df = pd.DataFrame({'A': [1, 2, np.nan], 'B': ['x', 'y', 'z']})
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3 entries, 0 to 2
Data columns (total 2 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   A       2 non-null      float64
 1   B       3 non-null      object 
dtypes: float64(1), object(1)
memory usage: 176.0+ bytes

#5. df.describe()
Generates descriptive statistics for numerical columns.

import pandas as pd
df = pd.DataFrame({'A': [1, 2, 3, 4, 5]})
print(df.describe())

A
count  5.000000
mean   3.000000
std    1.581139
min    1.000000
25%    2.000000
50%    3.000000
75%    4.000000
max    5.000000

#6. df.shape
Returns a tuple representing the dimensionality (rows, columns) of the DataFrame.

import pandas as pd
df = pd.DataFrame({'A': [1, 2], 'B': [3, 4], 'C': [5, 6]})
print(df.shape)

(2, 3)

#7. df.columns
Returns the column labels of the DataFrame.

import pandas as pd
df = pd.DataFrame({'Name': ['Alice'], 'Age': [30]})
print(df.columns)

Index(['Name', 'Age'], dtype='object')

#8. df.dtypes
Returns the data types of each column.

import pandas as pd
df = pd.DataFrame({'A': [1, 2], 'B': [1.1, 2.2], 'C': ['x', 'y']})
print(df.dtypes)

A      int64
B    float64
C     object
dtype: object

#9. df['col'].value_counts()
Returns a Series containing counts of unique values in a column.

import pandas as pd
df = pd.DataFrame({'Fruit': ['Apple', 'Banana', 'Apple', 'Orange', 'Banana', 'Apple']})
print(df['Fruit'].value_counts())

Apple     3
Banana    2
Orange    1
Name: Fruit, dtype: int64

#10. df['col'].unique()
Returns an array of the unique values in a column.

import pandas as pd
df = pd.DataFrame({'Fruit': ['Apple', 'Banana', 'Apple', 'Orange']})
print(df['Fruit'].unique())

['Apple' 'Banana' 'Orange']

#11. df['col'].nunique()
Returns the number of unique values in a column.

import pandas as pd
df = pd.DataFrame({'Fruit': ['Apple', 'Banana', 'Apple', 'Orange']})
print(df['Fruit'].nunique())

3

#12. df.isnull()
Returns a DataFrame of boolean values indicating missing values.

import pandas as pd
import numpy as np
df = pd.DataFrame({'A': [1, np.nan], 'B': [np.nan, 'x']})
print(df.isnull())

A      B
0  False   True
1   True  False

#13. df.isnull().sum()
Returns the number of missing values in each column.

import pandas as pd
import numpy as np
df = pd.DataFrame({'A': [1, np.nan, 3, np.nan], 'B': [5, 6, 7, 8]})
print(df.isnull().sum())

A    2
B    0
dtype: int64

#14. df.to_csv()
Writes the DataFrame to a comma-separated values (csv) file.

import pandas as pd
df = pd.DataFrame({'A': [1, 2], 'B': [3, 4]})
csv_output = df.to_csv(index=False)
print(csv_output)

A,B
1,3
2,4

#15. df.copy()
Creates a deep copy of a DataFrame.

import pandas as pd
df1 = pd.DataFrame({'A': [1]})
df2 = df1.copy()
df2.loc[0, 'A'] = 99
print(f"Original df1:\n{df1}")
print(f"Copied df2:\n{df2}")

Original df1:
   A
0  1
Copied df2:
    A
0  99

---
#DataAnalysis #Pandas #Selection #Indexing

Part 2: Pandas - Data Selection & Indexing

#16. df['col']
Selects a single column as a Series.

import pandas as pd
df = pd.DataFrame({'Name': ['Alice', 'Bob'], 'Age': [30, 25]})
print(df['Name'])

0    Alice
1      Bob
Name: Name, dtype: object

#17. df[['col1', 'col2']]
Selects multiple columns as a new DataFrame.

import pandas as pd
df = pd.DataFrame({'Name': ['Alice'], 'Age': [30], 'City': ['New York']})
print(df[['Name', 'City']])

Name       City
0  Alice   New York

#18. df.loc[]
Accesses a group of rows and columns by label(s) or a boolean array.

import pandas as pd
df = pd.DataFrame({'A': [1, 2, 3]}, index=['x', 'y', 'z'])
print(df.loc['y'])

A    2
Name: y, dtype: int64

#19. df.iloc[]
Accesses a group of rows and columns by integer position(s).

import pandas as pd
df = pd.DataFrame({'A': [10, 20, 30]})
print(df.iloc[1])

A    20
Name: 1, dtype: int64

#20. df[df['col'] > value]
Selects rows based on a boolean condition (boolean indexing).

import pandas as pd
df = pd.DataFrame({'Age': [22, 35, 18, 40]})
print(df[df['Age'] > 30])

Age
1   35
3   40

#21. df.set_index()
Sets the DataFrame index using existing columns.

import pandas as pd
df = pd.DataFrame({'Country': ['USA', 'UK'], 'Code': [1, 44]})
df_indexed = df.set_index('Country')
print(df_indexed)

Code
Country      
USA         1
UK         44

#22. df.reset_index()
Resets the index of the DataFrame and uses the default integer index.

import pandas as pd
df = pd.DataFrame({'Code': [1, 44]}, index=['USA', 'UK'])
df_reset = df.reset_index()
print(df_reset)

index  Code
0   USA     1
1    UK    44

#23. df.at[]
Accesses a single value by row/column label pair. Faster than .loc.

import pandas as pd
df = pd.DataFrame({'A': [1, 2, 3]}, index=['x', 'y', 'z'])
print(df.at['y', 'A'])

2

#24. df.iat[]
Accesses a single value by row/column integer position. Faster than .iloc.

import pandas as pd
df = pd.DataFrame({'A': [10, 20, 30]})
print(df.iat[1, 0])

20

#25. df.sample()
Returns a random sample of items from an axis of object.

import pandas as pd
df = pd.DataFrame({'A': range(10)})
print(df.sample(n=3))

A
8  8
2  2
5  5
(Note: Output rows will be random)

---
#DataAnalysis #Pandas #DataCleaning #Manipulation

Part 3: Pandas - Data Cleaning & Manipulation

#26. df.dropna()
Removes missing values.

import pandas as pd
import numpy as np
df = pd.DataFrame({'A': [1, np.nan, 3]})
print(df.dropna())

A
0  1.0
2  3.0

#27. df.fillna()
Fills missing (NA/NaN) values using a specified method.

import pandas as pd
import numpy as np
df = pd.DataFrame({'A': [1, np.nan, 3]})
print(df.fillna(0))

A
0  1.0
1  0.0
2  3.0

#28. df.astype()
Casts a pandas object to a specified dtype.

import pandas as pd
df = pd.DataFrame({'A': [1.1, 2.7, 3.5]})
df['A'] = df['A'].astype(int)
print(df)

A
0  1
1  2
2  3

#29. df.rename()
Alters axes labels.

import pandas as pd
df = pd.DataFrame({'a': [1], 'b': [2]})
df_renamed = df.rename(columns={'a': 'A', 'b': 'B'})
print(df_renamed)

A  B
0  1  2

#30. df.drop()
Drops specified labels from rows or columns.

import pandas as pd
df = pd.DataFrame({'A': [1], 'B': [2], 'C': [3]})
df_dropped = df.drop(columns=['B'])
print(df_dropped)

A  C
0  1  3

#31. pd.to_datetime()
Converts argument to datetime.

import pandas as pd
s = pd.Series(['2023-01-01', '2023-01-02'])
dt_s = pd.to_datetime(s)
print(dt_s)

0   2023-01-01
1   2023-01-02
dtype: datetime64[ns]

#32. df.apply()
Applies a function along an axis of the DataFrame.

import pandas as pd
df = pd.DataFrame({'A': [1, 2, 3]})
df['B'] = df['A'].apply(lambda x: x * 2)
print(df)

A  B
0  1  2
1  2  4
2  3  6

#33. df['col'].map()
Maps values of a Series according to an input mapping or function.

import pandas as pd
df = pd.DataFrame({'Gender': ['M', 'F', 'M']})
df['Gender_Full'] = df['Gender'].map({'M': 'Male', 'F': 'Female'})
print(df)

Gender Gender_Full
0      M        Male
1      F      Female
2      M        Male

#34. df.replace()
Replaces values given in to_replace with value.

import pandas as pd
df = pd.DataFrame({'Score': [10, -99, 15, -99]})
df_replaced = df.replace(-99, 0)
print(df_replaced)

Score
0     10
1      0
2     15
3      0

#35. df.duplicated()
Returns a boolean Series denoting duplicate rows.

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

0    False
1    False
2     True
dtype: bool

#36. df.drop_duplicates()
Returns a DataFrame with duplicate rows removed.

import pandas as pd
df = pd.DataFrame({'A': [1, 2, 1], 'B': ['a', 'b', 'a']})
print(df.drop_duplicates())

A  B
0  1  a
1  2  b

#37. df.sort_values()
Sorts by the values along either axis.

import pandas as pd
df = pd.DataFrame({'Age': [25, 22, 30]})
print(df.sort_values(by='Age'))

Age
1   22
0   25
2   30

#38. df.sort_index()
Sorts object by labels (along an axis).

import pandas as pd
df = pd.DataFrame({'A': [1, 2, 3]}, index=[10, 5, 8])
print(df.sort_index())

A
5  2
8  3
10 1

#39. pd.cut()
Bins values into discrete intervals.

import pandas as pd
ages = pd.Series([22, 35, 58, 8, 42])
age_bins = pd.cut(ages, bins=[0, 18, 35, 60], labels=['Child', 'Adult', 'Senior'])
print(age_bins)

0     Adult
1     Adult
2    Senior
3     Child
4    Senior
dtype: category
Categories (3, object): ['Child' < 'Adult' < 'Senior']

#40. pd.qcut()
Quantile-based discretization function (bins into equal-sized groups).

import pandas as pd
data = pd.Series([1, 2, 3, 4, 5, 6, 7, 8, 9, 10])
quartiles = pd.qcut(data, 4, labels=False)
print(quartiles)

0    0
1    0
2    0
3    1
4    1
5    2
6    2
7    3
8    3
9    3
dtype: int64

#41. s.str.contains()
Tests if a pattern or regex is contained within a string of a Series.

import pandas as pd
s = pd.Series(['apple', 'banana', 'apricot'])
print(s[s.str.contains('ap')])

0      apple
2    apricot
dtype: object

#42. s.str.split()
Splits strings around a given separator/delimiter.

import pandas as pd
s = pd.Series(['a_b', 'c_d'])
print(s.str.split('_', expand=True))

0  1
0  a  b
1  c  d

#43. s.str.lower()
Converts strings in the Series to lowercase.

import pandas as pd
s = pd.Series(['HELLO', 'World'])
print(s.str.lower())

0    hello
1    world
dtype: object

#44. s.str.strip()
Removes leading and trailing whitespace.

import pandas as pd
s = pd.Series(['  hello  ', ' world '])
print(s.str.strip())

0    hello
1    world
dtype: object

#45. s.dt.year
Extracts the year from a datetime Series.

import pandas as pd
s = pd.to_datetime(pd.Series(['2023-01-01', '2024-05-10']))
print(s.dt.year)

0    2023
1    2024
dtype: int64

---
#DataAnalysis #Pandas #Grouping #Aggregation

Part 4: Pandas - Grouping & Aggregation

#46. df.groupby()
Groups a DataFrame using a mapper or by a Series of columns.

import pandas as pd
df = pd.DataFrame({'Team': ['A', 'B', 'A', 'B'], 'Points': [10, 8, 12, 6]})
grouped = df.groupby('Team')
print(grouped)

<pandas.core.groupby.generic.DataFrameGroupBy object at 0x...>

#47. groupby.agg()
Aggregates using one or more operations over the specified axis.

import pandas as pd
df = pd.DataFrame({'Team': ['A', 'B', 'A', 'B'], 'Points': [10, 8, 12, 6]})
agg_df = df.groupby('Team').agg(['mean', 'sum'])
print(agg_df)

Points     
        mean  sum
Team             
A         11   22
B          7   14

#48. groupby.size()
Computes group sizes.

import pandas as pd
df = pd.DataFrame({'Team': ['A', 'B', 'A', 'B', 'A']})
print(df.groupby('Team').size())

Team
A    3
B    2
dtype: int64

#49. groupby.count()
Computes the count of non-NA cells for each group.

import pandas as pd
import numpy as np
df = pd.DataFrame({'Team': ['A', 'B', 'A'], 'Score': [1, np.nan, 3]})
print(df.groupby('Team').count())

Score
Team       
A         2
B         0

#50. groupby.mean()
Computes the mean of group values.

import pandas as pd
df = pd.DataFrame({'Team': ['A', 'B', 'A', 'B'], 'Points': [10, 8, 12, 6]})
print(df.groupby('Team').mean())

Points
Team        
A         11
B          7

#51. groupby.sum()
Computes the sum of group values.

import pandas as pd
df = pd.DataFrame({'Team': ['A', 'B', 'A', 'B'], 'Points': [10, 8, 12, 6]})
print(df.groupby('Team').sum())

Points
Team        
A         22
B         14

#52. groupby.min()
Computes the minimum of group values.

import pandas as pd
df = pd.DataFrame({'Team': ['A', 'B', 'A', 'B'], 'Points': [10, 8, 12, 6]})
print(df.groupby('Team').min())

Points
Team        
A         10
B          6

#53. groupby.max()
Computes the maximum of group values.

import pandas as pd
df = pd.DataFrame({'Team': ['A', 'B', 'A', 'B'], 'Points': [10, 8, 12, 6]})
print(df.groupby('Team').max())

Points
Team        
A         12
B          8

#54. df.pivot_table()
Creates a spreadsheet-style pivot table as a DataFrame.

import pandas as pd
df = pd.DataFrame({'A': ['foo', 'foo', 'bar'], 'B': ['one', 'two', 'one'], 'C': [1, 2, 3]})
pivot = df.pivot_table(values='C', index='A', columns='B')
print(pivot)

B    one  two
A            
bar  3.0  NaN
foo  1.0  2.0

#55. pd.crosstab()
Computes a cross-tabulation of two (or more) factors.

import pandas as pd
df = pd.DataFrame({'A': ['foo', 'foo', 'bar'], 'B': ['one', 'two', 'one']})
crosstab = pd.crosstab(df.A, df.B)
print(crosstab)

B    one  two
A            
bar    1    0
foo    1    1

---
#DataAnalysis #Pandas #Merging #Joining

Part 5: Pandas - Merging & Concatenating

#56. pd.merge()
Merges DataFrame or named Series objects with a database-style join.

import pandas as pd
df1 = pd.DataFrame({'key': ['A', 'B'], 'val1': [1, 2]})
df2 = pd.DataFrame({'key': ['A', 'B'], 'val2': [3, 4]})
merged = pd.merge(df1, df2, on='key')
print(merged)

key  val1  val2
0   A     1     3
1   B     2     4

#57. pd.concat()
Concatenates pandas objects along a particular axis.

import pandas as pd
df1 = pd.DataFrame({'A': [1, 2]})
df2 = pd.DataFrame({'A': [3, 4]})
concatenated = pd.concat([df1, df2])
print(concatenated)

A
0  1
1  2
0  3
1  4

#58. df.join()
Joins columns with other DataFrame(s) on index or on a key column.