def predict_artist(lyrics):
# TODO transform (stem) the lyrics
lyrics = transformLyrics(lyrics)
# TODO predict the artist for the lyrics. Note that predict will
# interpret the argument as a list.
prediction = pipeline.predict([lyrics])
# TODO return a string naming the predicted artist.
return 'Predicted Artist: %s' % prediction
def predict_artist(lyrics):
lyrics = transformLyrics(lyrics)
print 'predicting artist for %s' % lyrics
prediction = pipeline.predict([lyrics])
# TODO instead of returning a string, render the prediction.html template.
# TODO
d = {'lyrics': lyrics, 'artist': prediction[0]}
return render_template('prediction.html', d=d)
def predict_artist():
# TODO get the lyrics from the body of the POST request
lyrics = transformLyrics(lyrics)
print 'predicting artist for %s' % lyrics
prediction = pipeline.predict([lyrics])
d = {'lyrics': lyrics, 'artist': prediction[0]}
return render_template('prediction.html', d=d)
def predict_artist(lyrics):
# TODO transform (stem) the lyrics
lyrics = transformLyrics(lyrics)
# TODO predict the artist for the lyrics. Note that predict will
# interpret the argument as a list.
prediction = pipeline.predict([lyrics])
# TODO return a string naming the predicted artist.
return 'Predicted Artist: %s' % prediction
def predict_artist(lyrics):
lyrics = transformLyrics(lyrics)
print "predicting artist for %s" % lyrics
prediction = pipeline.predict([lyrics])
# TODO instead of returning a string, render the prediction.html template.
# TODO
d = {"lyrics": lyrics, "artist": prediction[0]}
return render_template("prediction.html", d=d)
def predictArtist(self, lyrics):
"""Returns an artist name given sample song lyrics.
Applies the Million Song Dataset stemming routine to
the lyrics (pre-processing), vectorizes the lyrics,
and runs them through the MultinomialNB classifier.
Returns the artist name associated with the predicted
label.
"""
transformed_lyrics = transformLyrics(lyrics)
return ""
def predictArtist(self,lyrics):
"""Returns an artist name given sample song lyrics.
Applies the Million Song Dataset stemming routine to
the lyrics (pre-processing), vectorizes the lyrics,
and runs them through the MultinomialNB classifier.
Returns the artist name associated with the predicted
label.
"""
transformed_lyrics = transformLyrics(lyrics)
return ""
def predict_artist():
# TODO get the lyrics from the body of the POST request
lyrics = request.form['lyrics']
lyrics = transformLyrics(lyrics)
print 'predicting artist for %s' % lyrics
prediction = pipeline.predict([lyrics])
d = {
'lyrics': lyrics,
'artist': prediction[0]
}
return render_template('prediction.html', d=d)
def predict_artist(lyrics):
lyrics = transformLyrics(lyrics)
print 'predicting artist for %s' % lyrics
prediction = pipeline.predict([lyrics])
# TODO instead of returning a string, render the prediction.html template.
# TODO create a dictionary containing the keys 'lyrics' and 'artists' that
# TODO will be used to complete the template.
d = {
'lyrics': lyrics,
'artist': prediction[0]
}
return render_template('prediction.html', d=d)
def predictArtist(self,lyrics):
"""Returns an artist name given sample song lyrics.
Applies the Million Song Dataset stemming routine to
the lyrics (pre-processing), vectorizes the lyrics,
and runs them through the MultinomialNB classifier.
Returns the artist name associated with the predicted
label.
"""
transformed_lyrics = transformLyrics(lyrics)
df = pd.DataFrame({'Lyrics':[transformed_lyrics]})
X = self.vectorizer.transform(df['Lyrics'])
y = self.clf.predict(X)
for artist, label in self.artistLabels.items():
if label == y:
return artist
return "Artist Not Found (predicted label %d)"%(y)
def predictArtist(self, lyrics):
"""Returns an artist name given sample song lyrics.
Applies the Million Song Dataset stemming routine to
the lyrics (pre-processing), vectorizes the lyrics,
and runs them through the MultinomialNB classifier.
Returns the artist name associated with the predicted
label.
"""
transformed_lyrics = transformLyrics(lyrics)
df = pd.DataFrame({'Lyrics': [transformed_lyrics]})
X = self.vectorizer.transform(df['Lyrics'])
y = self.clf.predict(X)
for artist, label in self.artistLabels.items():
if label == y:
return artist
return "Artist not found (prdeict label %d" % y
def predict_artist(lyrics):
lyrics = transformLyrics(lyrics)
print 'predicting artist for %s' % lyrics
prediction = pipeline.predict([lyrics])
return 'Predicted Artist: %s' % prediction
def predict_artist(lyrics):
lyrics = transformLyrics(lyrics)
print 'predicting artist for %s' % lyrics
prediction = pipeline.predict([lyrics])
return 'Predicted Artist: %s' % prediction
