utils.py

from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score
from sklearn.ensemble import RandomForestRegressor
import pandas as pd
from tqdm.auto import tqdm
import streamlit as st
tqdm.pandas()


def predict_popularity(features):
    predictions = [None] * 2
    predictions[0], predictions[1] = rf_model.predict([features]), model.predict([features])
    return predictions




data = pd.read_csv('top50.csv', encoding='ISO-8859-1')
print(data.head())

# Let's also describe the data to get a sense of the distributions
print(data.describe())
# Selecting the features and the target variable
X = data.drop(['Unnamed: 0', 'Track.Name', 'Artist.Name', 'Genre', 'Popularity'], axis=1)
y = data['Popularity']

# Splitting the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Initializing the Linear Regression model
model = LinearRegression()

# Fitting the model
model.fit(X_train, y_train)

# Making predictions
y_pred = model.predict(X_test)

# Calculating the performance metrics
mse = mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)
# Initialize the Random Forest Regressor
rf_model = RandomForestRegressor(n_estimators=100, random_state=42)

# Fitting the model
rf_model.fit(X_train, y_train)

# Making predictions
rf_pred = rf_model.predict(X_test)

# Calculating the performance metrics
rf_mse = mean_squared_error(y_test, rf_pred)
rf_r2 = r2_score(y_test, rf_pred)


# Feature importances
feature_importances = rf_model.feature_importances_

# Create a pandas series with feature importances
importances = pd.Series(feature_importances, index=X.columns)

# Sort the feature importances in descending order
sorted_importances = importances.sort_values(ascending=False)