Pandas for data science

 

• Handles missing data (NaN, NA, NaT easily).
• Flexible size mutability (insert/delete columns).
• Automatic data alignment (aligns labels automatically).
• Powerful groupby engine (split-apply-combine operations).
• Easy data conversion (converts structures to DataFrames).
• Smart indexing (label-based slicing and subsetting).
• Intuitive data merging (easy joining of datasets).
• Flexible reshaping (pivoting and restructuring data).
• Hierarchical axis labeling (multiple labels per tick).
• Robust I/O tools (loads CSV, Excel, HDF5).
• Time-series ready (date shifting and frequency conversion).

• Series: One-dimensional array-like structure.
• DataFrame: Two-dimensional, size-mutable tabular structure.

1.

import pandas as pd
s = pd.Series([1, 3, 5, 7, 9])
print(s)

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




2. 

data = {'Name': ['John', 'Anna', 'Peter', 'Linda'],

        'Age': [28, 34, 29, 32]}

df = pd.DataFrame(data)

print(df)

    Name  Age
0   John   28
1   Anna   34
2  Peter   29
3  Linda   32



3. 

# Creating a DataFrame from a dictionary.
import pandas as pd

data = {
    'Name': ['Alice', 'Bob', 'Charlie'],
    'Age': [25, 30, 35],
    'City': ['New York', 'Paris', 'London']
}

df = pd.DataFrame(data)
print(df)

      Name  Age      City
0    Alice   25  New York
1      Bob   30     Paris
2  Charlie   35    London

4. # To look at the first few rows of a DataFrame. print(df.head()) # First five rows

      Name  Age      City
0    Alice   25  New York
1      Bob   30     Paris
2  Charlie   35    London



5.
# To access a column in the DataFrame.
ages = df['Age']
print(ages)
print(df['Name'])  # Displays the 'Name' column

0    25
1    30
2    35
Name: Age, dtype: int64
0      Alice
1        Bob
2    Charlie
Name: Name, dtype: object


6.

subset = df[0:2]  # First two rows
print(subset)


    Name  Age      City
0  Alice   25  New York
1    Bob   30     Paris


7.


filtered_df = df[df['Age'] > 30]  # Rows where age is greater than 30
print(filtered_df)

      Name  Age    City
2  Charlie   35  London



8. 

df['AgeInTenYears'] = df['Age'] + 10
print(df)

      Name  Age      City  AgeInTenYears
0    Alice   25  New York             35
1      Bob   30     Paris             40
2  Charlie   35    London             45



9.
print(df.describe())

        Age  AgeInTenYears
count   3.0            3.0
mean   30.0           40.0
std     5.0            5.0
min    25.0           35.0
25%    27.5           37.5
50%    30.0           40.0
75%    32.5           42.5
max    35.0           45.0


10.
f.rename(columns={'AgeYears': 'Age'}, inplace=True)
#print(df['Age'].mean())  # Average age


11.
df
print(df['Age'].mean())  # Average age

30.0


12. 
df.plot(kind='line')
<Axes: >





df['Age'].plot(kind='bar')
<Axes: >



# Select rows where 'Age' is greater than 30
print(df[df['Age'] > 30])

filtered_df = df[df['Age'] > 30]  # Rows where age is greater than 30
print(filtered_df)

     Name   Age    City  AgeInTenYears
2  Charlie  35.0  London             45
      Name   Age    City  AgeInTenYears
2  Charlie  35.0  London             45

#DATA CLEANING #Drop Rows With Missing Values import pandas as pd # Define a dictionary with Indian employee data containing missing values (None) data = { "Employee": ["Aarav", "Priya", "Rahul", "Ananya", "Kabir"], "Salary_LPA": [12.0, None, 18.5, 9.0, 15.0], # Priya's salary is missing "City": ["Mumbai", "Delhi", None, "Bangalore", None], # Rahul and Kabir have missing cities } df = pd.DataFrame(data) print("Original Data:\n", df) print() # Use dropna() to remove rows that contain any missing values df_cleaned = df.dropna() print("Cleaned Data (Rows with any missing values removed):\n", df_cleaned)

Original Data:
   Employee  Salary_LPA       City
0    Aarav        12.0     Mumbai
1    Priya         NaN      Delhi
2    Rahul        18.5       None
3   Ananya         9.0  Bangalore
4    Kabir        15.0       None

Cleaned Data (Rows with any missing values removed):
   Employee  Salary_LPA       City
0    Aarav        12.0     Mumbai
3   Ananya         9.0  Bangalore

#Fill Missing Values import pandas as pd # define a dictionary with sample data which includes some missing values data = { 'A': [1, 2, 3, None, 5], 'B': [None, 2, 3, 4, 5], 'C': [1, 2, None, None, 5] } df = pd.DataFrame(data) print("Original Data:\n", df) # filling NaN values with 0 df.fillna(0, inplace=True) print("\nData after filling NaN with 0:\n", df)

Original Data:
      A    B    C
0  1.0  NaN  1.0
1  2.0  2.0  2.0
2  3.0  3.0  NaN
3  NaN  4.0  NaN
4  5.0  5.0  5.0

Data after filling NaN with 0:
      A    B    C
0  1.0  0.0  1.0
1  2.0  2.0  2.0
2  3.0  3.0  0.0
3  0.0  4.0  0.0
4  5.0  5.0  5.0

import pandas as pd # define a dictionary with sample data which includes some missing values data = { 'A': [1, 2, 3, None, 5], 'B': [None, 2, 3, 4, 5], 'C': [1, 2, None, None, 5] } df = pd.DataFrame(data) print("Original Data:\n", df) # filling NaN values with the mean of each column df.fillna(df.mean(), inplace=True) print("\nData after filling NaN with mean:\n", df)

Original Data:
      A    B    C
0  1.0  NaN  1.0
1  2.0  2.0  2.0
2  3.0  3.0  NaN
3  NaN  4.0  NaN
4  5.0  5.0  5.0

Data after filling NaN with mean:
       A    B         C
0  1.00  3.5  1.000000
1  2.00  2.0  2.000000
2  3.00  3.0  2.666667
3  2.75  4.0  2.666667
4  5.00  5.0  5.000000



import pandas as pd

# sample data
data = {
    'A': [1, 2, 2, 3, 3, 4],
    'B': [5, 6, 6, 7, 8, 8]
}
df = pd.DataFrame(data)

print("Original DataFrame:\n", df.to_string(index=False))

# detect duplicates
print("\nDuplicate Rows:\n", df[df.duplicated()].to_string(index=False))

# remove duplicates based on column 'A'
df.drop_duplicates(subset=['A'], keep='first', inplace=True)

print("\nDataFrame after removing duplicates based on column 'A':\n", df.to_string(index=False))

Original DataFrame:
  A  B
 1  5
 2  6
 2  6
 3  7
 3  8
 4  8

Duplicate Rows:
  A  B
 2  6

DataFrame after removing duplicates based on column 'A':
  A  B
 1  5
 2  6
 3  7
 4  8