# Import the pandas library
import pandas as pd

# Specify the path to your CSV file
filename = "data.csv"

# Read the CSV file into a DataFrame
df = pd.read_csv(filename)

#Checking the first five rows
df.head()

# Import the pandas library 
import pandas as pd

# Specify the path to your Excel file (.xlsx or .xls)
filename = "data.xlsx"

# Read the Excel file into a DataFrame
# Common options you'll use all the time:
df = pd.read_excel(
    filename,
    sheet_name=0,              # 0 = first sheet
    header=0,                  # Row (0-indexed) to use as column names
    skiprows=4,                # Skip first 4 rows
    nrows=1000,                # Load only first 1000 rows
)
# Check the first five rows
df.head()

# Loading a text file in Python

filename = 'huck_finn.txt'                  # Name of the file to open

file = open(filename, mode='r')             # Open file in read mode ('r')
                                            # Use encoding='utf-8' if needed

text = file.read()                          # Read entire content into a string

print(file.closed)                          # False → file is still open

file.close()                                # Always close the file when done!
                                            # Prevents memory leaks & file locks

print(file.closed)                          # Now True → file is safely closed

print(text)                                 # Display the full text content

# Import json module (built-in, no install needed!)
import json

# Or import pandas if you want it directly as a DataFrame
import pandas as pd

# Your JSON file path
filename = "data.json"

# Load JSON file into a Python dictionary/list
with open(filename, "r", encoding="utf-8") as file:
    data = json.load(file)

# Quick look at structure and first few items
print(type(data))        # usually dict or list
print(data.keys() if isinstance(data, dict) else len(data))

# Load the json file
df = pd.read_json(filename)         


df.head()

import requests            # Library for making HTTP requests
import pandas as pd        # Library for data manipulation and analysis

# API endpoint
url = "https://api.example.com/users"

# Send request to API
response = requests.get(url)

# Convert JSON response to Python object
data = response.json()

# Convert the JSON data into a pandas DataFrame
df = pd.DataFrame(data)

# Display the first five rows of the DataFrame
print(df.head())

import requests

# API endpoint
url = "https://api.example.com/data"

# Parameters including the API key for authentication
params = {
    "api_key": "YOUR_API_KEY"  # Replace with your actual API key
}

# Send GET request with parameters
response = requests.get(url, params=params)

# Convert JSON response to Python object
data = response.json()

# Print the data
print(data)

import pickle  # Library for object serialization

# Open the pickle file in read-binary mode
with open("data.pkl", "rb") as file:
    data = pickle.load(file)  # Load the stored Python object

import pandas as pd

# Load a pickled pandas DataFrame
df = pd.read_pickle("data.pkl")

import pandas as pd

# URL of the webpage containing HTML tables
url = "https://example.com/page"

# Read all tables from the webpage
tables = pd.read_html(url)

# Select the first table
df = tables[0]

import pandas as pd

# Read Parquet file into a DataFrame
df = pd.read_parquet("data.parquet")

import pandas as pd

# Read ORC file into a DataFrame
df = pd.read_orc("data.orc")

import pandas as pd

# Read Feather file into a DataFrame
df = pd.read_feather("data.feather")

df.isnull().sum()        # Check missing values
df.dropna()              # Remove rows with missing values
df.fillna(0)             # Replace missing values

df.duplicated()          # Identify duplicates
df.drop_duplicates()     # Remove duplicates

df.dtypes                                                      #identify data types
df["age"] = df["age"].astype(int)               #convert age column to integer data type
df["date"] = pd.to_datetime(df["date"])    #convert date column to date data type

df.columns = df.columns.str.lower().str.replace(" ", "_")

df["gender"] = df["gender"].str.lower()   #convert to lower case
df["name"] = df["name"].str.strip()