mrputils 0.3.0

This is a util module to help with movie revenue prediction

Movie Revenue Prediction 🎬

Mission: Given the characteristics of a movie (director, actors, budget…), predict the revenue it will generateDataset: Imdb (link).

🚩Data

350 k+ movies Multiple countries and languages Data fetched from www.themoviedb.org.

Technology: Tensorflow, Steamlit, Python, NLP

🚩 Zagros PDE Team 🌄

Amir Shamsa Syed Aaquib Hussain Mehdi Paydayesh Abdurraouf Aljaber

🚩Learn more

Link to the detialed documnetation

Link to the final presentation

Trello project managment

💖This has been a cool project 😆 in this bootcamp!

Requirements

The major libraries used in these projects are:

1. numpy,
2. pandas,
3. seaborn,
4. matplotlib,
5. missingno,
6. random,
7. re
8. nltk
9. sklearn
10. tensorflow
11. xgboost
12. lightgbm

rand_state=100 RANDOMSEED = 100 DISPLAY_WIDTH = 400 DISPLAYMAX_COLUMNS = 25 #endregion

#region settings random.seed(RANDOMSEED) pd.set_option('display.width', DISPLAY_WIDTH) pd.set_option('display.max_columns', DISPLAYMAX_COLUMNS) import warnings warnings.filterwarnings('ignore') warnings.filterwarnings(action='once')

#endregion

File structure

Part 0: importing libararies

Part 1: define functions (methods)

Part 2: define processing functions (methods)

Part 3: QCs

Part 4: defining the features and targets

Part 5: making the pipeline

Part 6: cross validation and bagging regressor

Part 7: model selection

Part 8: gridSearch and hyperparameters testing

Part 9: TPOT testing

Part 10: stacking

Part 11: model performance and learning curve

Part 12: movie revenue prediction

Part 13: model B - creating a model to find similar movies using KNN

Part 14: model C - Creating a model to predict the movie popularity

Part 15: model D - scraping new movie data for testing the model