Kashif Aziz kashaziz

## scrapingexample.py
'''
Example of web scraping using Python and BeautifulSoup.

Sraping ESPN College Football data
http://www.espn.com/college-sports/football/recruiting/databaseresults/_/sportid/24/class/2006/sort/school/starsfilter/GT/ratingfilter/GT/statuscommit/Commitments/statusuncommit/Uncommited

The script will loop through a defined number of pages to extract footballer data.
'''

from bs4 import BeautifulSoup

## dropbox_file_renamer.py
# input name of image folder
image_folder = str(input("Enter folder name to fetch images: ")).lower()

# instantiate Dropbox connection
dbx = dropbox.Dropbox('dropbox access token')

# proceed if image folder exists in Dropbox
if dbx.files_get_metadata(image_folder).path_lower == image_folder:

    # iterate through the files inside Dropbox folder

## gist:48c8ca6996ac32e9c143db3231864c54
""" Perform sentiment analysis on product reviews of Amazon product """
import requests
from bs4 import BeautifulSoup
from textblob import TextBlob

def analyze_product_reviews(url):
    response = requests.get(url)
    soup = BeautifulSoup(response.content, 'html.parser')

    reviews = soup.find_all('div', {'data-hook': 'review-collapsed'})

## house_prices_prediction_linear_regression.py
"""
This script utilizes machine learning techniques to predict house prices based on various input features.
It performs data preprocessing, splits the data into training and testing sets, trains a linear regression model,
evaluates its performance using  mean squared error (MSE) and R-squared.
"""

import pandas as pd
import numpy as np
from sklearn.preprocessing import OneHotEncoder
from sklearn.model_selection import train_test_split

## logistic_regression_customer_prediction.py
"""
This Python script demonstrates the usage of logistic regression to predict whether customers will make the next purchase on an e-commerce site.
The code performs the following steps:

1. Load and Preprocess Data:
    - Loads an e-commerce dataset containing customer features such as 'time_on_site', 'total_spent', 'is_returning_customer', and 'will_make_next_purchase'.
    - Splits the data into training and testing sets.

2. Model Training:
    - Creates a logistic regression model using scikit-learn.

## decision_tree_customer_buying_prediction.py
"""
This Python script showcases the application of decision trees in the context of e-commerce data analysis.
"""

# Import necessary libraries
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score, confusion_matrix
from sklearn.tree import export_text

## fraud_live_data.csv
TransactionAmount	TransactionTime	MerchantInfo	LocationInfo	UserInfo	DeviceInfo
68.2	01/03/2023 14:30	LocalShop3	CityA	JohnDoe123	Mobile
95.4	02/03/2023 9:45	LocalShop2	CityB	AliceSmith456	Desktop
110.8	03/03/2023 16:15	OnlineStore1	CityC	BobJohnson789	Tablet
45.6	04/03/2023 12:00	OnlineStore1	CityA	EveWilliams123	Mobile
75.3	05/03/2023 10:30	OnlineStore2	CityB	CharlieBrown456	Desktop
	'''
	Example of web scraping using Python and BeautifulSoup.

	Sraping ESPN College Football data
	http://www.espn.com/college-sports/football/recruiting/databaseresults/_/sportid/24/class/2006/sort/school/starsfilter/GT/ratingfilter/GT/statuscommit/Commitments/statusuncommit/Uncommited

	The script will loop through a defined number of pages to extract footballer data.
	'''

	from bs4 import BeautifulSoup
	# input name of image folder
	image_folder = str(input("Enter folder name to fetch images: ")).lower()

	# instantiate Dropbox connection
	dbx = dropbox.Dropbox('dropbox access token')

	# proceed if image folder exists in Dropbox
	if dbx.files_get_metadata(image_folder).path_lower == image_folder:

	# iterate through the files inside Dropbox folder
	""" Perform sentiment analysis on product reviews of Amazon product """
	import requests
	from bs4 import BeautifulSoup
	from textblob import TextBlob

	def analyze_product_reviews(url):
	response = requests.get(url)
	soup = BeautifulSoup(response.content, 'html.parser')

	reviews = soup.find_all('div', {'data-hook': 'review-collapsed'})
	"""
	This script utilizes machine learning techniques to predict house prices based on various input features.
	It performs data preprocessing, splits the data into training and testing sets, trains a linear regression model,
	evaluates its performance using mean squared error (MSE) and R-squared.
	"""

	import pandas as pd
	import numpy as np
	from sklearn.preprocessing import OneHotEncoder
	from sklearn.model_selection import train_test_split
	"""
	This Python script demonstrates the usage of logistic regression to predict whether customers will make the next purchase on an e-commerce site.
	The code performs the following steps:

	1. Load and Preprocess Data:
	- Loads an e-commerce dataset containing customer features such as 'time_on_site', 'total_spent', 'is_returning_customer', and 'will_make_next_purchase'.
	- Splits the data into training and testing sets.

	2. Model Training:
	- Creates a logistic regression model using scikit-learn.
	"""
	This Python script showcases the application of decision trees in the context of e-commerce data analysis.
	"""

	# Import necessary libraries
	import pandas as pd
	from sklearn.model_selection import train_test_split
	from sklearn.tree import DecisionTreeClassifier
	from sklearn.metrics import accuracy_score, confusion_matrix
	from sklearn.tree import export_text
	TransactionAmount TransactionTime MerchantInfo LocationInfo UserInfo DeviceInfo
	68.2 01/03/2023 14:30 LocalShop3 CityA JohnDoe123 Mobile
	95.4 02/03/2023 9:45 LocalShop2 CityB AliceSmith456 Desktop
	110.8 03/03/2023 16:15 OnlineStore1 CityC BobJohnson789 Tablet
	45.6 04/03/2023 12:00 OnlineStore1 CityA EveWilliams123 Mobile
	75.3 05/03/2023 10:30 OnlineStore2 CityB CharlieBrown456 Desktop