Pinned Repositories
DSI_minicourse
The complete name of the course is Python, Data Science & Machine Learning Mini-Course and the instructor of this course is Andrew Jones. The course cover following sections: (1) Python Basics, (2) Introduction to Pandas for data analysis using sales data, (3) Prime Number finder along with some aggregate functions, (4) Machine learning Basics, (5) Overview of scikit-learn library for machine learning in python, (6) Random Forest algorithm ( Theory+ Practical implementation) and Decision Tree (Theory). In the pratical implementation of RF, the instructor taught superbly to build, train, and test the ML model in python that can predict how long it will take certain video game players to complete a particular challenge in their game which is based on their level and the amount of ammo their character has.
ML_WebApp_on_IRIS_Classifier
This web application is built using streamlit. The app uses machine learning model to classify the iris flowers. Moreover, this web app is deployed on Heroku.
MNIST_Digit_Classification_using_CNN_and_Gradio_based_UI
This Python application is based on Hand Written Digits. Tensorflow and Gradio were used as the key requirements for coding. TensorFlow is a free and open-source software library for machine learning. It can be used across a range of tasks but has a particular focus on training and inference of deep neural networks. Gradio allows you to quickly create customizable UI components around your TensorFlow or PyTorch models, or even arbitrary Python functions.
NLP-implementation-on-whastapp-chats-using-python
This notebook was built to analyze Whatsapp conversations using the steps below: Step 1: Detecting {Date} and {Time} tokens Step 2: Detecting the {Author} token Step 3: Extracting and Combining tokens Step 4: Parsing the entire file and handling Multi-Line Messages For further steps, we need to perform Exploratory data analysis (EDA) Step 5: Performing EDA for analyzing chat data Step 6: Overall statistics of WhatsApp chat including Total number of messages, media messages(Omitted) & Total number of URLs Step 7: Extracting basic statistics for each Author (user) Step 8: Word cloud of most used words in chat Step 9: Total number of messages sent by each user Step 10: Total messages sent on each day of the week Step 11: Most active author of the chat Step 12: Most active day in a week In next steps, Time series analysis will be performed on chat data Step 13: Time whenever the chat was highly active Step 14: Date on which the chat was highly active Step 15: Converting 12-hour formate to 24 hours will help us for better analysis Step 16: Most suitable hour of the day whenever there will be more chances of getting a response from user
NLP_TKINTER_GUI_USING_PYCHARM
The project is based on three different phases: 1. Text extraction, 2. Preprocessing/ Text cleaning (includes Tokenization, POS tagging, Stopwords filtering, Lemmatization, TF/IDF) , 3. Word expansion and matching
TESLA-Stock-Price-Prediction-Using-Facebook-Prophet
This repository aims to build a Facebook Prophet Machine learning model that can forecast the price of Tesla 30 days in advance. The effectiveness of the model is also evaluated by looking at Tesla's prior performance using data visualization methods.
Web-scraping-using-python-and-beautifulsoup
This notebook includes data scraping. For this beautifulsoup and selinium is used. It takes a website URL as an input and extracts the information listed below as an output from that webpage. For this beautifulsoup and selinium is used 1. Specific HTML tags along with titles and meta description 2. Extract specific tags, heading tags from h1-h6 along with titles and meta description 3. Extracting ALT tags 4. For counting words inside a web page 5. Inspection of broken links inside a webpage 6. Extracting the source code of the webpage
KashmalaJamshaid's Repositories
KashmalaJamshaid/Web-scraping-using-python-and-beautifulsoup
This notebook includes data scraping. For this beautifulsoup and selinium is used. It takes a website URL as an input and extracts the information listed below as an output from that webpage. For this beautifulsoup and selinium is used 1. Specific HTML tags along with titles and meta description 2. Extract specific tags, heading tags from h1-h6 along with titles and meta description 3. Extracting ALT tags 4. For counting words inside a web page 5. Inspection of broken links inside a webpage 6. Extracting the source code of the webpage
KashmalaJamshaid/NLP-implementation-on-whastapp-chats-using-python
This notebook was built to analyze Whatsapp conversations using the steps below: Step 1: Detecting {Date} and {Time} tokens Step 2: Detecting the {Author} token Step 3: Extracting and Combining tokens Step 4: Parsing the entire file and handling Multi-Line Messages For further steps, we need to perform Exploratory data analysis (EDA) Step 5: Performing EDA for analyzing chat data Step 6: Overall statistics of WhatsApp chat including Total number of messages, media messages(Omitted) & Total number of URLs Step 7: Extracting basic statistics for each Author (user) Step 8: Word cloud of most used words in chat Step 9: Total number of messages sent by each user Step 10: Total messages sent on each day of the week Step 11: Most active author of the chat Step 12: Most active day in a week In next steps, Time series analysis will be performed on chat data Step 13: Time whenever the chat was highly active Step 14: Date on which the chat was highly active Step 15: Converting 12-hour formate to 24 hours will help us for better analysis Step 16: Most suitable hour of the day whenever there will be more chances of getting a response from user
KashmalaJamshaid/DSI_minicourse
The complete name of the course is Python, Data Science & Machine Learning Mini-Course and the instructor of this course is Andrew Jones. The course cover following sections: (1) Python Basics, (2) Introduction to Pandas for data analysis using sales data, (3) Prime Number finder along with some aggregate functions, (4) Machine learning Basics, (5) Overview of scikit-learn library for machine learning in python, (6) Random Forest algorithm ( Theory+ Practical implementation) and Decision Tree (Theory). In the pratical implementation of RF, the instructor taught superbly to build, train, and test the ML model in python that can predict how long it will take certain video game players to complete a particular challenge in their game which is based on their level and the amount of ammo their character has.
KashmalaJamshaid/ML_WebApp_on_IRIS_Classifier
This web application is built using streamlit. The app uses machine learning model to classify the iris flowers. Moreover, this web app is deployed on Heroku.
KashmalaJamshaid/MNIST_Digit_Classification_using_CNN_and_Gradio_based_UI
This Python application is based on Hand Written Digits. Tensorflow and Gradio were used as the key requirements for coding. TensorFlow is a free and open-source software library for machine learning. It can be used across a range of tasks but has a particular focus on training and inference of deep neural networks. Gradio allows you to quickly create customizable UI components around your TensorFlow or PyTorch models, or even arbitrary Python functions.
KashmalaJamshaid/NLP_TKINTER_GUI_USING_PYCHARM
The project is based on three different phases: 1. Text extraction, 2. Preprocessing/ Text cleaning (includes Tokenization, POS tagging, Stopwords filtering, Lemmatization, TF/IDF) , 3. Word expansion and matching
KashmalaJamshaid/TESLA-Stock-Price-Prediction-Using-Facebook-Prophet
This repository aims to build a Facebook Prophet Machine learning model that can forecast the price of Tesla 30 days in advance. The effectiveness of the model is also evaluated by looking at Tesla's prior performance using data visualization methods.