marrcco/Movie-Recommendation-Model

Stars
2
Language
Jupyter Notebook
Created about 4 years ago
Updated over 3 years ago

marrcco/Movie-Recommendation-Model

marrcco

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Recommendation Systems in the world of machine learning have become very popular and are a huge advantage to tech giants like Netflix, Amazon and many more to target their content to a specific audience. These recommendation engines are so strong in their predictions that they can dynamically alter the state of what the user sees on their page based on the user’s interaction with the app. This project includes: Web Scraping, Data Cleansing, Building Model, Program execution and Comparing results

GoogleMaps_Crawler

Google Maps Crawler takes Google Maps List and it scrape elements from all items such as: title, rating, reviews, location url, website,etc.

wikipedia_api

Wikipedia API let's you send requests via python and get data about daily page views per date for specified article, monthly page views for specified articles, or top n articles per day for specified country.

instagram_scraper_and_sentiment_analysis

Instagram Comments Sentiment Analysis

sql_examples

Here you can find examples of my SQL Queries.

BI-Dashboards

Here you can find examples of BI Dashboards from my previous projects. I've used Google Data Studio and Tableau to build dashboards. Logo of company is hidden because of privacy reasons.

Youtube_Comments_Scraper

This repository is for my youtube automation tool for scraping comments from videos.

Sentiment-Analysis-IMDB-Reviews

In this notebook you'll see: How to use Selenium to scrape movies reviews from IMDB How to clean the data What is Sentiment Analysis How to use natural language processing (NLP) techniques

Jupyter Notebook

Stroke-Prediction-Analysis

In this notebook we'll deal with analyzing all factors that can lead to stroke. We'll compare what has more impact on stroke and after that we'll build a model to predict whether patient suffers of stroke. This is a classification problem and later we'll se which models we are going to use.

Jupyter Notebook

COVID-19-Analysis

Since the first reports of cases from Wuhan, a city in the Hubei Province of China, at the end of 2019, more than 80,000 COVID-19 cases have been reported in China; these include all laboratory-confirmed cases as well as clinically diagnosed cases in the Hubei Province. A joint World Health Organization (WHO)-China fact-finding mission estimated that the epidemic in China peaked between late January and early February 2020. The majority of reports have been from Hubei and surrounding provinces, but numerous cases have been reported in other provinces and municipalities throughout China. To get to know this virus better, I think it's important that we all invest the effort and resources we have. I'm glad to see so many Data Scientists here sharing their visualizations and analysis.

Jupyter Notebook

interstellar_imdb_analysis

The idea that I came up with for this article is Reviews Sentiment Analysis. So, first of all, we’ll have to collect the reviews data. We’ll do this by scraping the movie reviews from IMDb. After this, we’ll have to do some Data Cleansing and Exploratory Data Analysis. Then, we’ll move to Sentiment Analysis and Data Storytelling.

Jupyter Notebook