Spotify Music Data

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

genre_counts = spotify['top genre'].value_counts()
genre_counts.head(5)

import matplotlib.pyplot as plt

genre_counts.head(5).plot(kind='bar')
plt.title("Top 5 Genres from 2010 to 2019")
plt.xlabel("Genre")
plt.ylabel("Count")
plt.show()

artist_counts = spotify['artist'].value_counts()
artist_counts.head(5)

import matplotlib.pyplot as plt

artist_counts.head(5).plot(kind='bar')
plt.title("Top 5 Artist from 2010 to 2019")
plt.xlabel("Artist")
plt.ylabel("Count")
plt.show()

annual_pop = spotify.groupby('year')['pop'].mean()

import matplotlib.pyplot as plt

annual_pop.plot(marker='o')
plt.title("Average Track Popularity by Year")
plt.xlabel("Year")
plt.ylabel("Average Popularity")
plt.xticks(annual_pop.index)

plt.grid(alpha=0.3)
plt.show()

import matplotlib.pyplot as plt

features = ['bpm', 'dnce', 'nrgy']
annual_feats = spotify.groupby('year')[features].mean()

annual_feats.plot(marker='o')
plt.title("Mean Audio Features by Year")
plt.xlabel("Year")
plt.ylabel("Feature Value")
plt.xticks(annual_feats.index)
plt.legend(title="Feature")
plt.grid(alpha=0.3)
plt.show()

import matplotlib.pyplot as plt

features = ['live', 'acous']
annual_feats = spotify.groupby('year')[features].mean()

annual_feats.plot(marker='o')
plt.title("Mean Audio Features by Year")
plt.xlabel("Year")
plt.ylabel("Feature Value")
plt.xticks(annual_feats.index)
plt.legend(title="Feature")
plt.grid(alpha=0.3)
plt.show()

import matplotlib.pyplot as plt

features = ['val', 'spch']
annual_feats = spotify.groupby('year')[features].mean()

annual_feats.plot(marker='o')
plt.title("Mean Audio Features by Year")
plt.xlabel("Year")
plt.ylabel("Feature Value")
plt.xticks(annual_feats.index)
plt.legend(title="Feature")
plt.grid(alpha=0.3)
plt.show()

import matplotlib.pyplot as plt

spotify['dur_s'] = spotify['dur'] / 1000

annual_duration = spotify.groupby('year')['dur_s'].sum()

annual_duration.plot(kind='bar')
plt.title("Total Duration of Top Tracks by Year (seconds)")
plt.xlabel("Year")
plt.ylabel("Total Seconds")
plt.show()

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report, accuracy_score

spotify = pd.read_csv('spotify_top_music.csv')

X = spotify.iloc[:, 3:14]
y = spotify['top genre']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

clf = RandomForestClassifier(random_state=42)

clf.fit(X_train, y_train)

y_pred = clf.predict(X_test)

accuracy = accuracy_score(y_test, y_pred)
report = classification_report(y_test, y_pred)

print(f"Accuracy: {accuracy:.4f}")
print("\nClassification Report:")
print(report)

import pandas as pd
import matplotlib.pyplot as plt
from sklearn.metrics import classification_report

TOP_N = 3

labels = sorted(y.unique()) 
metric = 'f1-score'

report_df = pd.DataFrame(
 classification_report(
 y_test, y_pred,
 labels = labels,
 target_names = labels,
 output_dict = True,
 zero_division= 0
 )
).T


top_df = (
 report_df.loc[labels, [metric, 'precision', 'recall']]
 .sort_values(metric, ascending=False)
 .head(TOP_N)
 .round(3)
)

print(f"Top {TOP_N} genres by {metric}:")
display(top_df)

fig, ax = plt.subplots(figsize=(6, 4))
ax.bar(top_df.index, top_df[metric]) 
ax.set_title(f"Top {TOP_N} Genres by {metric.capitalize()}")
ax.set_ylabel(metric.capitalize())
ax.set_xlabel("Genre")
ax.set_xticklabels(top_df.index, rotation=45, ha='right')
plt.tight_layout()
plt.show()