Skip to content

🎬 IMDb Rating Analysis Project

This notebook orchestrates data preparation, analysis, modeling, and clustering using clean modular functions.

import matplotlib.pyplot as plt
import seaborn as sns

from data_preprocessing import get_prepared_data
from eda import run_all_plots, run_all_descriptive_eda, run_full_eda_pipeline
from hypothesis_tests import run_all_stat_tests
from modeling.clustering import run_kmeans_clustering
from modeling.regression_models import run_regression_models
from modeling.classification_models import run_classification_models

from config import FILENAME
sns.set_theme(style="whitegrid")
plt.figure(figsize=(10, 6))
df = get_prepared_data(FILENAME)
df.head()
run_full_eda_pipeline(df)
run_all_stat_tests(df)
run_regression_models(df)
run_classification_models(df)
run_kmeans_clustering(df)