Python Scripts For Beginners: Cryptography

1. Read a CSV File

import pandas as pd
data = pd.read_csv('data.csv')
print(data)

Reads and prints a CSV file using pandas.

2. Write Data to a CSV File

import pandas as pd
data = {'Name': ['John', 'Anna'], 'Age': [28, 24]}
df = pd.DataFrame(data)
df.to_csv('output.csv', index=False)

Writes data to a CSV file.

3. Read an Excel File

import pandas as pd
data = pd.read_excel('data.xlsx')
print(data)

Reads and prints an Excel file.

4. Write Data to an Excel File

import pandas as pd
data = {'Name': ['John', 'Anna'], 'Age': [28, 24]}
df = pd.DataFrame(data)
df.to_excel('output.xlsx', index=False)

Writes data to an Excel file.

5. Read a JSON File

import json
with open('data.json', 'r') as file:
    data = json.load(file)
print(data)

Reads and prints a JSON file.

6. Write Data to a JSON File

import json
data = {'Name': 'John', 'Age': 28}
with open('output.json', 'w') as file:
    json.dump(data, file)

Writes data to a JSON file.

7. Read a Text File

with open('data.txt', 'r') as file:
    content = file.read()
print(content)

Reads and prints a text file.

8. Write Data to a Text File

with open('output.txt', 'w') as file:
    file.write("Hello, World!")

Writes data to a text file.

9. Append Data to a Text File

with open('output.txt', 'a') as file:
    file.write("\nAppended Line")

Appends data to a text file.

10. Read Data from a Database (SQLite)

import sqlite3
conn = sqlite3.connect('database.db')
cursor = conn.cursor()
cursor.execute("SELECT * FROM table_name")
data = cursor.fetchall()
print(data)
conn.close()

Reads and prints data from an SQLite database.

11. Write Data to a Database (SQLite)

import sqlite3
conn = sqlite3.connect('database.db')
cursor = conn.cursor()
cursor.execute("CREATE TABLE IF NOT EXISTS table_name (id INTEGER PRIMARY KEY, name TEXT)")
cursor.execute("INSERT INTO table_name (name) VALUES ('John')")
conn.commit()
conn.close()

Writes data to an SQLite database.

12. Filter Data in a DataFrame

import pandas as pd
data = pd.read_csv('data.csv')
filtered_data = data[data['Age'] > 30]
print(filtered_data)

Filters rows in a DataFrame based on a condition.

13. Group Data in a DataFrame

import pandas as pd
data = pd.read_csv('data.csv')
grouped_data = data.groupby('Category').sum()
print(grouped_data)

Groups data in a DataFrame by a column and performs aggregation.

14. Merge Two DataFrames

import pandas as pd
df1 = pd.read_csv('data1.csv')
df2 = pd.read_csv('data2.csv')
merged_df = pd.merge(df1, df2, on='ID')
print(merged_df)

Merges two DataFrames based on a common column.

15. Pivot Table

import pandas as pd
data = pd.read_csv('data.csv')
pivot_table = data.pivot_table(values='Value', index='Date', columns='Category')
print(pivot_table)

Creates a pivot table from a DataFrame.

16. Drop Duplicate Rows

import pandas as pd
data = pd.read_csv('data.csv')
unique_data = data.drop_duplicates()
print(unique_data)

Drops duplicate rows from a DataFrame.

17. Fill Missing Values

import pandas as pd
data = pd.read_csv('data.csv')
filled_data = data.fillna(method='ffill')
print(filled_data)

Fills missing values in a DataFrame using forward fill.

18. Drop Rows with Missing Values

import pandas as pd
data = pd.read_csv('data.csv')
cleaned_data = data.dropna()
print(cleaned_data)

Drops rows with missing values from a DataFrame.

19. Save DataFrame to Parquet

import pandas as pd

data = pd.read_csv('data.csv')
data.to_parquet('data.parquet')

Saves a DataFrame to a Parquet file.

20. Read Parquet File

import pandas as pd

data = pd.read_parquet('data.parquet')
print(data)

Reads and prints data from a Parquet file.

21. Convert DataFrame to JSON

import pandas as pd
data = pd.read_csv('data.csv')
json_data = data.to_json()
print(json_data)

Converts a DataFrame to a JSON string.

22. Convert JSON to DataFrame

import pandas as pd
import json
with open('data.json', 'r') as file:
    data = json.load(file)
df = pd.json_normalize(data)
print(df)

Converts JSON data to a DataFrame.

23. Calculate Statistics of a DataFrame

import pandas as pd
data = pd.read_csv('data.csv')
print(data.describe())

Calculates and prints basic statistics of a DataFrame.

24. Normalize Data

import pandas as pd
from sklearn.preprocessing import MinMaxScaler

data = pd.read_csv('data.csv')
scaler = MinMaxScaler()
normalized_data = scaler.fit_transform(data[['Value']])
print(normalized_data)

Normalizes data using Min-Max scaling.

25. Standardize Data

import pandas as pd
from sklearn.preprocessing import StandardScaler

data = pd.read_csv('data.csv')
scaler = StandardScaler()
standardized_data = scaler.fit_transform(data[['Value']])
print(standardized_data)

Standardizes data to have a mean of 0 and a standard deviation of 1.

26. Load Data from API

import requests

response = requests.get('https://api.example.com/data')
data = response.json()
print(data)

Fetches and prints data from an API.

27. Save DataFrame to SQL Database

import pandas as pd
import sqlite3

data = pd.read_csv('data.csv')
conn = sqlite3.connect('database.db')
data.to_sql('table_name', conn, if_exists='replace', index=False)
conn.close()

Saves a DataFrame to an SQL database.

28. Load DataFrame from SQL Database

import pandas as pd
import sqlite3

conn = sqlite3.connect('database.db')
data = pd.read_sql('SELECT * FROM table_name', conn)
print(data)
conn.close()

Loads data from an SQL database into a DataFrame.

29. Write Data to XML

import pandas as pd
data = pd.read_csv('data.csv')
data.to_xml('data.xml')

Writes a DataFrame to an XML file.

30. Read Data from XML

import pandas as pd
data = pd.read_xml('data.xml')
print(data)

Reads and prints data from an XML file.

31. Create a DataFrame from Scratch

import pandas as pd
data = {'Name': ['John', 'Anna'], 'Age': [28, 24]}
df = pd.DataFrame(data)
print(df)

Creates a DataFrame from scratch.

32. Flatten Nested JSON

import pandas as pd
import json

with open('nested_data.json', 'r') as file:
    data = json.load(file)

df = pd.json_normalize(data, sep='_')
print(df)

Flattens nested JSON data into a DataFrame.

33. Merge DataFrames with Different Indexes

import pandas as pd

df1 = pd.DataFrame({'A': [1, 2]}, index=['a', 'b'])
df2 = pd.DataFrame({'B': [3, 4]}, index=['b', 'c'])
merged_df = df1.join(df2)
print(merged_df)

Merges DataFrames with different indexes.

34. Append Rows to DataFrame

import pandas as pd

data1 = pd.DataFrame({'Name': ['John'], 'Age': [28]})
data2 = pd.DataFrame({'Name': ['Anna'], 'Age': [24]})
appended_data = data1.append(data2, ignore_index=True)
print(appended_data)

Appends rows to a DataFrame.

35. Remove Columns from DataFrame

import pandas as pd

data = pd.read_csv('data.csv')
cleaned_data = data.drop(columns=['UnwantedColumn'])
print(cleaned_data)

Removes specified columns from a DataFrame.

36. Rename Columns in DataFrame

import pandas as pd

data = pd.read_csv('data.csv')
data.rename(columns={'OldName': 'NewName'}, inplace=True)
print(data)

Renames columns in a DataFrame.

37. Create DataFrame with MultiIndex

import pandas as pd

arrays = [['A', 'A', 'B', 'B'], [1, 2, 1, 2]]
index = pd.MultiIndex.from_arrays(arrays, names=('Letter', 'Number'))
data = pd.DataFrame({'Value': [10, 20, 30, 40]}, index=index)
print(data)

Creates a DataFrame with a MultiIndex.

38. Reshape DataFrame

import pandas as pd

data = pd.read_csv('data.csv')
reshaped_data = data.melt(id_vars=['ID'], value_vars=['Value1', 'Value2'])
print(reshaped_data)

Reshapes a DataFrame using melt.

39. Pivot DataFrame

import pandas as pd

data = pd.read_csv('data.csv')
pivoted_data = data.pivot(index='ID', columns='Category', values='Value')
print(pivoted_data)

Creates a pivot table from a DataFrame.

40. Save DataFrame to HDF5

import pandas as pd

data = pd.read_csv('data.csv')
data.to_hdf('data.h5', key='df', mode='w')

Saves a DataFrame to an HDF5 file.

41. Read HDF5 File

import pandas as pd

data = pd.read_hdf('data.h5', key='df')
print(data)

Reads data from an HDF5 file into a DataFrame.

42. Handle Missing Data with Interpolation

import pandas as pd

data = pd.read_csv('data.csv')
interpolated_data = data.interpolate()
print(interpolated_data)

Handles missing data by interpolation.

43. Calculate Correlation Matrix

import pandas as pd

data = pd.read_csv('data.csv')
correlation_matrix = data.corr()
print(correlation_matrix)

Calculates the correlation matrix of a DataFrame.

44. Create Random DataFrame

import pandas as pd
import numpy as np

data = pd.DataFrame(np.random.randn(5, 3), columns=['A', 'B', 'C'])
print(data)

Creates a DataFrame with random values.

45. Normalize Columns in DataFrame

import pandas as pd
from sklearn.preprocessing import MinMaxScaler

data = pd.read_csv('data.csv')
scaler = MinMaxScaler()
data[['Value']] = scaler.fit_transform(data[['Value']])
print(data)

Normalizes specific columns in a DataFrame.

46. Standardize Columns in DataFrame

import pandas as pd
from sklearn.preprocessing import StandardScaler

data = pd.read_csv('data.csv')
scaler = StandardScaler()
data[['Value']] = scaler.fit_transform(data[['Value']])
print(data)

Standardizes specific columns in a DataFrame.

47. Convert DataFrame to Dictionary

import pandas as pd

data = pd.read_csv('data.csv')
dict_data = data.to_dict()
print(dict_data)

Converts a DataFrame to a dictionary.

48. Load Data from a Web API

import requests

response = requests.get('https://api.example.com/data')
data = response.json()
print(data)

Loads data from a web API into a Python dictionary.

49. Save DataFrame to Google Sheets

import pandas as pd
import gspread
from oauth2client.service_account import ServiceAccountCredentials

scope = ["https://spreadsheets.google.com/feeds", "https://www.googleapis.com/auth/drive"]
creds = ServiceAccountCredentials.from_json_keyfile_name('credentials.json', scope)
client = gspread.authorize(creds)
sheet = client.open('SheetName').sheet1

data = pd.read_csv('data.csv')
sheet.update([data.columns.values.tolist()] + data.values.tolist())

Saves a DataFrame to a Google Sheet.

50. Read Data from Google Sheets

import gspread
from oauth2client.service_account import ServiceAccountCredentials

scope = ["https://spreadsheets.google.com/feeds", "https://www.googleapis.com/auth/drive"]
creds = ServiceAccountCredentials.from_json_keyfile_name('credentials.json', scope)
client = gspread.authorize(creds)
sheet = client.open('SheetName').sheet1

data = sheet.get_all_records()
print(data)

Reads data from a Google Sheet into a Python list.

51. Read SQL Data with SQLAlchemy

import pandas as pd
from sqlalchemy import create_engine

engine = create_engine('sqlite:///database.db')
data = pd.read_sql('SELECT * FROM table_name', engine)
print(data)

Reads data from a SQL database using SQLAlchemy.

52. Write Data to Google BigQuery

from google.cloud import bigquery
import pandas as pd

client = bigquery.Client()
data = pd.read_csv('data.csv')
client.load_table_from_dataframe(data, 'project.dataset.table')

Writes a DataFrame to Google BigQuery.

53. Load Data from Google BigQuery

from google.cloud import bigquery

client = bigquery.Client()
query = "SELECT * FROM `project.dataset.table`"
data = client.query(query).to_dataframe()
print(data)

Loads data from Google BigQuery into a DataFrame.

54. Convert DataFrame to HTML

import pandas as pd

data = pd.read_csv('data.csv')
html_data = data.to_html()
print(html_data)

Converts a DataFrame to an HTML table.

55. Read HTML Table into DataFrame

import pandas as pd

data = pd.read_html('table.html')[0]
print(data)

Reads an HTML table into a DataFrame.

56. Export DataFrame to LaTeX

import pandas as pd

data = pd.read_csv('data.csv')
latex_data = data.to_latex()
print(latex_data)

Exports a DataFrame to a LaTeX table format.

57. Create a DataFrame with Date Range

import pandas as pd

date_range = pd.date_range(start='2024-01-01', periods=5)
data = pd.DataFrame({'Date': date_range, 'Value': [10, 20, 30, 40, 50]})
print(data)

Creates a DataFrame with a date range.

58. Filter DataFrame by Date

import pandas as pd

data = pd.read_csv('data.csv', parse_dates=['Date'])
filtered_data = data[data['Date'] > '2024-01-01']
print(filtered_data)

Filters rows in a DataFrame based on a date condition.

59. Aggregate Data by Month

import pandas as pd

data = pd.read_csv('data.csv', parse_dates=['Date'])
monthly_data = data.resample('M', on='Date').sum()
print(monthly_data)

Aggregates data by month.

60. Create a DataFrame from a List of Dictionaries

import pandas as pd

data = [{'Name': 'John', 'Age': 28}, {'Name': 'Anna', 'Age': 24}]
df = pd.DataFrame(data)
print(df)

Creates a DataFrame from a list of dictionaries.

61. Flatten Nested Data in DataFrame

import pandas as pd

data = pd.read_csv('nested_data.csv')
flattened_data = pd.json_normalize(data['nested_column'])
print(flattened_data)

Flattens nested data in a DataFrame column.

62. Create DataFrame with Random Dates

import pandas as pd
import numpy as np

dates = pd.date_range(start='2024-01-01', periods=5)
data = pd.DataFrame({'Date': dates, 'Value': np.random.randn(5)})
print(data)

Creates a DataFrame with random dates and values.

63. Convert DataFrame to NumPy Array

import pandas as pd

data = pd.read_csv('data.csv')
array_data = data.to_numpy()
print(array_data)

Converts a DataFrame to a NumPy array.

64. Load Data from a CSV with Custom Delimiter

import pandas as pd

data = pd.read_csv('data.csv', delimiter=';')
print(data)

Reads a CSV file with a custom delimiter.

65. Handle Outliers in Data

import pandas as pd

data = pd.read_csv('data.csv')
filtered_data = data[data['Value'] < data['Value'].quantile(0.95)]
print(filtered_data)

Removes outliers by filtering extreme values.

66. Merge DataFrames with Outer Join

import pandas as pd

df1 = pd.DataFrame({'ID': [1, 2], 'Value': [10, 20]})
df2 = pd.DataFrame({'ID': [2, 3], 'Value': [30, 40]})
merged_df = pd.merge(df1, df2, on='ID', how='outer')
print(merged_df)

Merges DataFrames with an outer join.

67. Pivot and Aggregate Data

pythonCopier le codeimport pandas as pd

data = pd.read_csv('data.csv')
pivot_data = data.pivot_table(index='Category', values='Value', aggfunc='sum')
print(pivot_data)

Creates a pivot table and aggregates data.

68. Read Data from a Compressed File

import pandas as pd

data = pd.read_csv('data.csv.gz', compression='gzip')
print(data)

Reads data from a compressed CSV file.

69. Save DataFrame to Compressed File

import pandas as pd

data = pd.read_csv('data.csv')
data.to_csv('data_compressed.csv.gz', compression='gzip')

Saves a DataFrame to a compressed CSV file.

70. Create DataFrame with MultiIndex

import pandas as pd

arrays = [['A', 'A', 'B', 'B'], [1, 2, 1, 2]]
index = pd.MultiIndex.from_arrays(arrays, names=('Letter', 'Number'))
data = pd.DataFrame({'Value': [10, 20, 30, 40]}, index=index)
print(data)

Creates a DataFrame with a MultiIndex.

71. Calculate Rolling Statistics

import pandas as pd

data = pd.read_csv('data.csv', parse_dates=['Date'])
data.set_index('Date', inplace=True)
rolling_mean = data['Value'].rolling(window=3).mean()
print(rolling_mean)

Calculates rolling statistics for a DataFrame column.

72. Visualize Data with Matplotlib

import pandas as pd
import matplotlib.pyplot as plt

data = pd.read_csv('data.csv')
data.plot(x='Date', y='Value', kind='line')
plt.show()

Visualizes data with a line plot.

73. Handle Categorical Data

import pandas as pd

data = pd.read_csv('data.csv')
data['Category'] = data['Category'].astype('category')
print(data['Category'].cat.codes)

Converts categorical data to numerical codes.

74. Merge DataFrames with Different Column Names

import pandas as pd

df1 = pd.DataFrame({'ID': [1, 2], 'Value1': [10, 20]})
df2 = pd.DataFrame({'ID': [1, 2], 'Value2': [30, 40]})
merged_df = pd.merge(df1, df2, left_on='ID', right_on='ID')
print(merged_df)

Merges DataFrames with different column names.

75. Apply Function to DataFrame

import pandas as pd

data = pd.read_csv('data.csv')
data['Value'] = data['Value'].apply(lambda x: x * 2)
print(data)

Applies a function to a DataFrame column.

76. Create DataFrame with Date Range and Frequency

import pandas as pd

date_range = pd.date_range(start='2024-01-01', periods=10, freq='D')
data = pd.DataFrame({'Date': date_range, 'Value': range(10)})
print(data)

Creates a DataFrame with a date range and specified frequency.

77. Load Data from YAML

import pandas as pd
import yaml

with open('data.yaml', 'r') as file:
    data = yaml.safe_load(file)
df = pd.DataFrame(data)
print(df)

Loads data from a YAML file into a DataFrame.

78. Save DataFrame to YAML

import pandas as pd
import yaml

data = pd.read_csv('data.csv')
data_dict = data.to_dict(orient='records')

with open('data.yaml', 'w') as file:
    yaml.dump(data_dict, file)

Saves a DataFrame to a YAML file.

79. Handle Missing Data with Backward Fill

import pandas as pd

data = pd.read_csv('data.csv')
filled_data = data.fillna(method='bfill')
print(filled_data)

Handles missing data by backward fill.

80. Handle Missing Data with Mean Imputation

import pandas as pd
from sklearn.impute import SimpleImputer

data = pd.read_csv('data.csv')
imputer = SimpleImputer(strategy='mean')
data[['Value']] = imputer.fit_transform(data[['Value']])
print(data)

Imputes missing data with the mean of the column.

81. Create DataFrame with Hierarchical Index

import pandas as pd

arrays = [['A', 'A', 'B', 'B'], [1, 2, 1, 2]]
index = pd.MultiIndex.from_arrays(arrays, names=('Letter', 'Number'))
data = pd.DataFrame({'Value': [10, 20, 30, 40]}, index=index)
print(data)

Creates a DataFrame with a hierarchical index.

82. Filter Data by Multiple Conditions

import pandas as pd

data = pd.read_csv('data.csv')
filtered_data = data[(data['Age'] > 30) & (data['Value'] < 50)]
print(filtered_data)

Filters DataFrame rows based on multiple conditions.

83. Calculate Percentage Change

import pandas as pd

data = pd.read_csv('data.csv', parse_dates=['Date'])
data.set_index('Date', inplace=True)
data['Percentage Change'] = data['Value'].pct_change()
print(data)

Calculates the percentage change of a DataFrame column.

84. Create DataFrame with Random Integers

import pandas as pd
import numpy as np

data = pd.DataFrame({'Value': np.random.randint(0, 100, size=10)})
print(data)

Creates a DataFrame with random integers.

85. Create DataFrame with Sequential Dates

import pandas as pd

dates = pd.date_range(start='2024-01-01', periods=10)
data = pd.DataFrame({'Date': dates, 'Value': range(10)})
print(data)

Creates a DataFrame with sequential dates.

86. Save DataFrame to Feather Format

import pandas as pd

data = pd.read_csv('data.csv')
data.to_feather('data.feather')

Saves a DataFrame to a Feather file.

87. Read Feather File

import pandas as pd

data = pd.read_feather('data.feather')
print(data)

Reads data from a Feather file into a DataFrame.

88. Export DataFrame to CSV with Custom Header

import pandas as pd

data = pd.read_csv('data.csv')
data.to_csv('output.csv', header=['Column1', 'Column2'], index=False)

Exports a DataFrame to CSV with a custom header.

89. Create DataFrame from SQL Query

import pandas as pd
import sqlite3

conn = sqlite3.connect('database.db')
query = "SELECT Name, Age FROM users WHERE Age > 25"
data = pd.read_sql(query, conn)
print(data)
conn.close()

Creates a DataFrame from an SQL query.

90. Convert DataFrame to SQLite Table

import pandas as pd
import sqlite3

data = pd.read_csv('data.csv')
conn = sqlite3.connect('database.db')
data.to_sql('table_name', conn, if_exists='replace', index=False)
conn.close()

Converts a DataFrame to an SQLite table.

91. Remove Columns with All NaN Values

import pandas as pd

data = pd.read_csv('data.csv')
cleaned_data = data.dropna(axis=1, how='all')
print(cleaned_data)

Removes columns that contain only NaN values.

92. Create DataFrame with Random Normal Data

import pandas as pd
import numpy as np

data = pd.DataFrame({'Value': np.random.randn(10)})
print(data)

Creates a DataFrame with random normally distributed data.

93. Read Data from a Zip File

import pandas as pd
import zipfile

with zipfile.ZipFile('data.zip', 'r') as zip_ref:
    zip_ref.extractall('data_folder')

data = pd.read_csv('data_folder/data.csv')
print(data)

Reads data from a file inside a zip archive.

94. Save DataFrame to Zip File

import pandas as pd
import zipfile

data = pd.read_csv('data.csv')
with zipfile.ZipFile('data.zip', 'w') as zip_ref:
    data.to_csv('data_folder/data.csv', index=False)
    zip_ref.write('data_folder/data.csv')

Saves a DataFrame to a file inside a zip archive.

95. Convert DataFrame to Python List

import pandas as pd

data = pd.read_csv('data.csv')
data_list = data.values.tolist()
print(data_list)

Converts a DataFrame to a Python list.

96. Perform DataFrame Operations in Parallel

import pandas as pd
from joblib import Parallel, delayed

data = pd.read_csv('data.csv')

def process_row(row):
    return row * 2

results = Parallel(n_jobs=-1)(delayed(process_row)(row) for row in data['Value'])
print(results)

Performs operations on a DataFrame in parallel.

97. Create DataFrame from JSON File

import pandas as pd

data = pd.read_json('data.json')
print(data)

Creates a DataFrame from a JSON file.

98. Save DataFrame to JSON File

import pandas as pd

data = pd.read_csv('data.csv')
data.to_json('data.json')

Saves a DataFrame to a JSON file.

99. Load Data from Parquet File

import pandas as pd

data = pd.read_parquet('data.parquet')
print(data)

Loads data from a Parquet file into a DataFrame.

100. Save DataFrame to Parquet File

import pandas as pd

data = pd.read_csv('data.csv')
data.to_parquet('data.parquet')

Saves a DataFrame to a Parquet file.