python_deom.py

# JSON File Loading
data_json = pd.read_json("file_name.json")

# SQL Database Loading
import sqlite3
connection_db = sqlite3.connect("database_name.db")

query1 = 'SELECT col_name FROM row_name' # to just display 1 column
query2 = 'SELECT * FROM row_name' # to display all colums

data_sql = pd.read_sql(query1, connection_db)
data_sql = pd.read_sql(query2, connection_db)

import pandas as pd
import numpy as np

# Excel File Loading
data_xl = pd.read_excel(r"C:\Users\ASUS\OneDrive\Documents\PythonForDS\IPL.xlsx", sheet_name = "IPL Matches")
print(data_xl.head())
data_xl1 = pd.read_excel(r"C:\Users\ASUS\OneDrive\Documents\PythonForDS\IPL.xlsx", sheet_name = "IPL Deliveries")
print(data_xl.head())

# TXT File Loading
data_txt = pd.read_csv("students.txt", header = 0, sep = ',')
print(data_txt)
data_txt1 = pd.read_csv("employee.txt", header = 0, sep = ',')
print(data_txt1)
data_txt2 = pd.read_csv("department.txt", header = 0, sep = ',')
print(data_txt2)

# CSV File Loading and Reading
data = pd.read_csv("percent-bachelors-degrees-women-usa.csv")
print(data)
print(data.columns)
print(data.columns.to_list())

# Head Functionality
print(data.head())
print(data.head(10))

# Tail Functionality
print(data.tail())
print(data.tail(10))

# Info Funtion
print(data.info())

# Drop all missing values
print(data.dropna())

# Fill all missing values
print(data.fillna("NULL"))

# Drop Duplicates
print(data.drop_duplicates())

# Access specific Row
print(data.iloc[29])
print(data.iloc[2:10]) # Rows from 2 to 9 (10 not included)

# Access specific Column
print(data['Biology'])
print(data.loc[:,'Biology']) # All Rows, Biology Column
print(data.loc[:,'Architecture':'Physical Sciences']) # All Rows, Architectur to Physical Sciences Column

# Accessing just the specific value in Row and Column
print(data.loc[10, 'Engineering'])
# Both Together (loc & iloc)
print(data.loc[10:20,'Business':'English']) # Rows (10 to 20), Columns (Business to English)

# Data Aggregation {Sorting, Filtering, Grouping}
# Data Sorting
print(data.sort_values(by='Art and Performance', ascending=True)) # Values arranged in Ascending
print(data_txt.sort_values(by='SchoolID', ascending=False)) # Values arranged in Descending
print(data_txt1.sort_values(by='Salary', ascending=False)) # Values arranged in Descending
print(data_txt1.sort_values(by='Age', ascending=False)) # Values arranged in Descending

# Data Grouping
print(data_txt.groupby("Country").count()) # Country wise count 
print(data_txt1.groupby("Dept")["Salary"].mean()) # Dept wise Avg Salry
print(data_txt1.groupby("Dept")["Salary"].max()) # Dept wise Max Salary

# Data Filtering
print(data_txt1[data_txt1["Salary"] > 50000]) # Salary > 50k
print(data_txt1[(data_txt1["Salary"] > 50000) & (data_txt1["Salary"] < 70000)]) # Salary between 50k and 70k
print(data_txt1[data_txt1["Age"].isin([27,29])]) # Employees whise age is 27 and 29

# Descriptive Statistics
print(data.describe()) # Gives stats related info

# Mean
print("Mean of the Data:", np.mean(data))

# Median
print("Median of the Data:", np.median(data))

# Varaince
print("Variance of the Data:", np.var(data))

# Standard Deviation (SD)
print("SD of the Data:", np.std(data))

# Mode (uses scipy and not numpy)
from scipy import stats
print("Mode of the Data:", stats.mode(data))

# Data Merging
print(pd.merge(data_txt1, data_txt2, on='Dept', how='inner')) # Inner Join
print(pd.merge(data_txt1, data_txt2, on='Dept', how='left')) # Left Join
print(pd.merge(data_txt1, data_txt2, on='Dept', how='right')) # Right Join

print(pd.merge(data_txt1, data_txt2, how= 'cross')) # Cross Join

# Left Anti Join
print(pd.merge(data_txt1, data_txt2, on='Dept', how='left', indicator=True)
        .query("_merge == 'left_only'")
        .drop('_merge', axis=1))

# Right Anti Join
print(pd.merge(data_txt1, data_txt2, on='Dept', how='right', indicator=True)
        .query("_merge == 'right_only'")
        .drop('_merge', axis=1))

# Data Visualization
import matplotlib.pyplot as plt

x_values = [1,2,3,4,5,6,7,8,9,10]
y_values = [2,4,6,8,10,12,14,16,18,20]

cat = ["Cat", "Dog", "Horse", "Mouse"]
cat_values = [10, 20, 100, 5]

# Line Graph
plt.plot(x_values,y_values, color = 'green')
plt.xlabel("X axis")
plt.ylabel("Y axis")
plt.title("Line Graph Representation")
plt.show()

# Scatter Graph
plt.scatter(x_values,y_values, color = 'green')
plt.xlabel("X axis")
plt.ylabel("Y axis")
plt.title("Scatter Graph Representation")
plt.show()

# Bar Chart
plt.bar(cat, cat_values, color = 'green')
plt.xlabel("X axis - Aniaml")
plt.ylabel("Y axis - Animal Weight")
plt.title("Bar Graph Representation of Aniaml Weight")
plt.show()

# Histograms
x_normal = np.random.normal(0,1,100)
plt.hist(x_normal, color='green')
plt.xlabel("X axis")
plt.ylabel("Y axis")
plt.title("Histogram Representation")
plt.show()

# Population Distribution
from scipy.stats import norm
x_val = np.arange(-4, 4, 0.01)
y_val = norm.pdf(x_val)

counts, bins, ignored = plt.hist(x_normal, 30, density=True, color='green', label='Sampling Distribution')

plt.plot(x_val, y_val, color='y', linewidth=2.5, label='Population Distribution')

plt.title("Population Distribution")
plt.xlabel("X axis")
plt.ylabel("Y axis")
plt.legend()
plt.show()