Spotify Music Data

import pandas as pd
spotify = pd.read_csv("spotify_top_music.csv", index_col=0)
print(spotify.shape)
spotify.head(100)

#Identify Popular Artists and Genres
# Count the number of songs by each artist
popular_artists = spotify['artist'].value_counts()

# Count the number of songs by genre
popular_genres = spotify['top genre'].value_counts()

print("Most Popular Artists:\n", popular_artists.head(10))
print("Most Popular Genres:\n", popular_genres.head(10))

# Visualize Trends Over Time
import matplotlib.pyplot as plt
import seaborn as sns

# Ensure that only numeric columns are used for calculating mean values
numeric_columns = spotify.select_dtypes(include='number').columns
yearly_trends = spotify.groupby('year')[numeric_columns].mean()

# Visualizing energy, valence, and danceability over time
plt.figure(figsize=(12, 6))
sns.lineplot(data=yearly_trends[['nrgy', 'val', 'dnce']], markers=True)
plt.title("Yearly Trends in Energy, Valence, and Danceability")
plt.ylabel("Average Value")
plt.xlabel("Year")
plt.legend(['Energy', 'Valence', 'Danceability'])
plt.show()

#Predict Song Genre Using a Classifier
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report

# Preparing the dataset
X = spotify.iloc[:, 3:13]  # Features
y = spotify['top genre']   # Target variable

# Splitting the data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# Training the model
clf = RandomForestClassifier(random_state=42)
clf.fit(X_train, y_train)

# Evaluating the model
y_pred = clf.predict(X_test)
print(classification_report(y_test, y_pred))