abdelrhmanelkhouly Goto Github PK

abdelrhmanelkhouly-abdelrhmanelkhouly-gru_rec_py_torch_sequential_recommender_system.

arabic-dialect-classifiction

in this project we use ML and Deep learning models to classify arabic dialect

bert_transformer_my_work_on_sentiment_analysis_of_google_play_reviews

In this notebook we used Bert transformer using tensorflow

data_camp_projects

e_commerce_item_recommender

there are 3 notebooks first one Matrix Factorization with all event, Second on view event only, Third is sequential recommender

firstjavatask

google_play_reviews_analysis_using_cnn

In this notebook we used CNN on our text data (sentiment analysis) we first done some data preprocessing

google_play_reviews_sentiment_analysis

graduation project

handson-ml2

A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.

iti_java_tasks

java_projects

javatask2

jjjjjjjjjjjj

linear-algebra-_-pca

netflix-dashboard

Interactive dashboard for Netflix Movies and TV Shows dataset

nlp-101-iti-course

NLP course for ITI AI-Pro track

nlp_sms_spam_classifier_pyspark

NLP and PySpark Project using TF_IDF, Tokenizer and some NLP package Project is to create a Spam filter using NaiveBayes classifier.  NLP Project using PySpark.  Preprocessing Data and Clean it.  Using TF_IDF, Tokenizer, NaiveBayes classifier model.  Accuracy F1_Score.

nlp_text_representation

In Natural Language Processing (NLP) the conversion of raw-text to numerical form is called Text Representation and believe me this step is one of the most important steps in the NLP pipeline as if we feed in poor features in ML Model, we will get poor results. In computer science, this is often called “garbage in, garbage out.” I observed in NLP feeding a good text representation to an ordinary algorithm will get you much farther compared to applying a topnotch algorithm to an ordinary text representation. In this notebook, I will discuss various text-representation schemes with their advantages and disadvantages so that you can choose one of the schemes which suit your task most. Our main objective is to transform a given text into numerical form so that it can be fed into NLP and ML algorithms.

numerical_optimization-

pyspark-

it some work and practise on pyspark (big_data)

sentiment_analysis_using_lstm

In this notebook i used LSTM(Long Short-Term Memory

seoul-bike-rental-prediction

one step of achievements on kaggle competetions the fourth place in seoul-bike-rental-prediction competition

single-object-traching-md-net

single object tracking on vot2015 dataset using MD Net

titanic-competition-

tweets_sentiment_analysis

In this notebook I used 2 different text representation teqniques (cout_vectorizer , TF-IDF) , with 2 diff ML models (logestic regression , SVM classifier) , and at least i used CNN technique

web_scrapping_using-selenium-jumia-

in this notebook i have scrapped all elements and links and new,old prices from jumia web site