File size: 2,855 Bytes
54b5359
 
 
 
 
 
 
ea492b0
 
54b5359
 
ea492b0
548c423
b587838
548c423
 
ea492b0
 
 
54b5359
738d8c0
54b5359
 
888a131
54b5359
 
 
888a131
 
 
 
 
 
 
 
ea492b0
 
 
 
54b5359
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
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
from huggingface_hub import Repository, HfApi
import os
tqdm.pandas()

# Authentifizierung (stellen Sie sicher, dass Ihr Hugging Face Token gesetzt ist)
api = HfApi(
    endpoint="https://huggingface.co/spaces/Add1E/SpotifyHitPrediction",
    token=os.getenv("token")
)

# Erstellen oder Klonen Sie ein Repository (wenn noch nicht vorhanden)
repo = Repository(local_dir="SpotifyHitPrediction", clone_from="Add1E/SpotifyHitPrediction")

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


def addToCsvAndTrain(trainset):
    trainset = [
        [trainset[0],trainset[1],trainset[2],trainset[3],trainset[4],trainset[5],trainset[6],trainset[7],
         trainset[8],trainset[9],trainset[10],trainset[11],trainset[12],trainset[13]
         ]
    ]
    neues_df = pd.DataFrame(trainset, columns= data.columns)
    df = pd.concat([data, neues_df], ignore_index=True)
    df.to_csv('SpotifyHitPrediction/top50.csv', index=False)
    repo.git_add('top50.csv')
    repo.git_commit("Add top50.csv")
    repo.git_push()


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)