Hidani Hafida | Junior Data Scientist

Hidani Hafida

Junior Data Scientist

Based in Nador, Morocco

About

I graduated from University Mohamed First with a master's degree in data science and intelligent systems. I have a background in computer science and mathematics, and I am passionate about using data-driven insights to address challenging issues and spur innovation. A research internship that involved using OpenStack to establish a cloud architecture is among my experiences. I have also worked on other data science projects, including sentiment analysis, facial expression identification, and product recommendation systems. I am excited to put my abilities to use in a dynamic, team-oriented workplace since I am driven by a desire to keep learning and developing in the field of data science. I am currently looking for an internship in the data science sector.

Skills

Projects

Arabic Sentiment Analysis & Opinion Mining

An advanced natural language processing (NLP) project leveraging deep learning to extract multi-label sentiment and opinions from Arabic text, overcoming the linguistic complexities of the language.

Prediction of MASI Index Performance

Predicted MASI index performance using a decade of macroeconomic data. Trained and compared LSTM, Prophet, and ARIMA models. ARIMA achieved the highest accuracy (RMSE: 78.15), highlighting inflation and exchange rates as key factors.

Estimation of Obesity Levels Based on Lifestyle Data

Cleaned and encoded categorical data on meal frequency and physical activity. Trained and evaluated multiple models including Logistic Regression, SVM, KNN, and Random Forest using accuracy and F1 scores.

Text Emotion Recognition Using TensorFlow-RNN

Emotions are highly valued because they play an important role in human interaction. A model is created and trained to recognize emotions in text using Recurrent Neural Networks. The dataset is divided into six categories: love, fear, joy, sadness, surprise, and anger.

Facial Emotion Recognition Using TensorFlow-CNN

Emotions are highly valued because they play an important role in human interaction. A model is created and trained to recognize real time emotions(Facial Emotion Recognition) using CNN. The dataset is divided into 7 categories: neutral, fear, happy, sadness, surprise, disgust and anger.

Employee Dashboard

Dashboard app created in Python using Streamlit

Breast Cancer Prediction

Using the Wisconsin breast cancer diagnostic dataset for predictive analysis.

Mobile Price Classification

The objective of this project is to develop a classification model for a dataset containing the specifications of 2000 cell phones and to try to predict the best price ranges by applying the KNN algorithm.

Flight Passenger Satisfaction

In this project, we will use the CRISP-DM process to predict a passenger's satisfaction using its attributes. The data set we will be working with contains an airline passenger satisfaction survey. For each passenger we have information about factors of the flight.

Analyze Movie Ratings Data Using a Data Warehouse

This project aims to analyze movie ratings using data warehouse. A data warehouse schema was designed and implemented using a galaxy schema. The ETL process was implemented using Python. Interactive dashboards were created in Power BI to facilitate data exploration and reporting.

Product Recommendation System Using PYSPARK

An overview of a system for recommending products to e-commerce companies is provided.. To gather and analyze user data, the system makes advantage of the Hadoop ecosystem, which also includes HDFS, Hive, Sqoop, and Apache Spark.