Spaces:
Runtime error
Runtime error
File size: 3,140 Bytes
ec35913 |
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 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 |
import pandas as pd
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.compose import make_column_transformer
from sklearn.model_selection import GroupShuffleSplit
from tensorflow import keras
from tensorflow.keras import layers
from tensorflow.keras import callbacks
spotify = pd.read_csv('../input/dl-course-data/spotify.csv')
X = spotify.copy().dropna()
y = X.pop('track_popularity')
artists = X['track_artist']
features_num = ['danceability', 'energy', 'key', 'loudness', 'mode',
'speechiness', 'acousticness', 'instrumentalness',
'liveness', 'valence', 'tempo', 'duration_ms']
features_cat = ['playlist_genre']
preprocessor = make_column_transformer(
(StandardScaler(), features_num),
(OneHotEncoder(), features_cat),
)
# We'll do a "grouped" split to keep all of an artist's songs in one
# split or the other. This is to help prevent signal leakage.
def group_split(X, y, group, train_size=0.75):
splitter = GroupShuffleSplit(train_size=train_size)
train, test = next(splitter.split(X, y, groups=group))
return (X.iloc[train], X.iloc[test], y.iloc[train], y.iloc[test])
X_train, X_valid, y_train, y_valid = group_split(X, y, artists)
X_train = preprocessor.fit_transform(X_train)
X_valid = preprocessor.transform(X_valid)
y_train = y_train / 100 # popularity is on a scale 0-100, so this rescales to 0-1.
y_valid = y_valid / 100
input_shape = [X_train.shape[1]]
print("Input shape: {}".format(input_shape))
model = keras.Sequential([
layers.Dense(1, input_shape=input_shape),
])
model.compile(
optimizer='adam',
loss='mae',
)
history = model.fit(
X_train, y_train,
validation_data=(X_valid, y_valid),
batch_size=512,
epochs=50,
verbose=0, # suppress output since we'll plot the curves
)
history_df = pd.DataFrame(history.history)
history_df.loc[0:, ['loss', 'val_loss']].plot()
print("Minimum Validation Loss: {:0.4f}".format(history_df['val_loss'].min()));
model = keras.Sequential([
layers.Dense(128, activation='relu', input_shape=input_shape),
layers.Dense(64, activation='relu'),
layers.Dense(1)
])
model.compile(
optimizer='adam',
loss='mae',
)
history = model.fit(
X_train, y_train,
validation_data=(X_valid, y_valid),
batch_size=512,
epochs=50,
)
history_df = pd.DataFrame(history.history)
history_df.loc[:, ['loss', 'val_loss']].plot()
print("Minimum Validation Loss: {:0.4f}".format(history_df['val_loss'].min()));
early_stopping = callbacks.EarlyStopping(
patience=5,
min_delta=0.001,
restore_best_weights=True,
)
model = keras.Sequential([
layers.Dense(128, activation='relu', input_shape=input_shape),
layers.Dense(64, activation='relu'),
layers.Dense(1)
])
model.compile(
optimizer='adam',
loss='mae',
)
history = model.fit(
X_train, y_train,
validation_data=(X_valid, y_valid),
batch_size=512,
epochs=50,
callbacks=[early_stopping]
)
history_df = pd.DataFrame(history.history)
history_df.loc[:, ['loss', 'val_loss']].plot()
print("Minimum Validation Loss: {:0.4f}".format(history_df['val_loss'].min()));
|