|
|
|
"""Lyrics5.ipynb |
|
|
|
Automatically generated by Colaboratory. |
|
|
|
Original file is located at |
|
https://colab.research.google.com/drive/1eEWnqPJ4BuKnMDL-kK9b2-vvMJ6_HTyS |
|
""" |
|
|
|
!pip install keras |
|
|
|
!pip install keras_preprocessing |
|
import keras_preprocessing |
|
|
|
!pip install pad_sequences |
|
import pad_sequences |
|
|
|
import pandas as pd |
|
import numpy as np |
|
import seaborn as sns |
|
import matplotlib.pyplot as plt |
|
from wordcloud import WordCloud, STOPWORDS, ImageColorGenerator |
|
import string, os |
|
import tensorflow as tf |
|
|
|
|
|
from keras_preprocessing.sequence import pad_sequences |
|
from tensorflow.keras.layers import Embedding, Dropout, LSTM, Dense, Bidirectional |
|
from keras.preprocessing.text import Tokenizer |
|
from keras.callbacks import EarlyStopping |
|
from keras.models import Sequential |
|
|
|
import matplotlib.pyplot as plt |
|
import seaborn as sns |
|
|
|
df = pd.read_csv('/content/drive/MyDrive/Colab Notebooks/lyrics-data.csv') |
|
|
|
df.head() |
|
|
|
df.drop(['ALink', 'SName','SLink'],axis=1,inplace=True) |
|
|
|
df.shape |
|
|
|
df['language'].value_counts() |
|
|
|
df = df[df['language']=='en'] |
|
|
|
df = df[:350] |
|
|
|
df.shape |
|
|
|
df['Number_of_words'] = df['Lyric'].apply(lambda x:len(str(x).split())) |
|
df.head() |
|
|
|
df['Number_of_words'].describe() |
|
|
|
import matplotlib.pyplot as plt |
|
plt.style.use('ggplot') |
|
plt.figure(figsize=(12,6)) |
|
sns.distplot(df['Number_of_words'],kde = False,color="red",bins=200) |
|
plt.title("Frequency distribution of number of words for each text extracted", size=20) |
|
|
|
tokenizer = Tokenizer() |
|
tokenizer.fit_on_texts(df['Lyric'].astype(str).str.lower()) |
|
|
|
total_words = len(tokenizer.word_index)+1 |
|
tokenized_sentences = tokenizer.texts_to_sequences(df['Lyric'].astype(str)) |
|
tokenized_sentences[0] |
|
|
|
input_sequences = list() |
|
for i in tokenized_sentences: |
|
for t in range(1, len(i)): |
|
n_gram_sequence = i[:t+1] |
|
input_sequences.append(n_gram_sequence) |
|
|
|
|
|
max_sequence_len = max([len(x) for x in input_sequences]) |
|
input_sequences = np.array(pad_sequences(input_sequences, maxlen=max_sequence_len, padding='pre')) |
|
|
|
input_sequences[:10] |
|
|
|
X, labels = input_sequences[:,:-1],input_sequences[:,-1] |
|
y = tf.keras.utils.to_categorical(labels, num_classes=total_words) |
|
|
|
model = Sequential() |
|
model.add(Embedding(total_words, 40, input_length=max_sequence_len-1)) |
|
model.add(Bidirectional(LSTM(250))) |
|
model.add(Dropout(0.1)) |
|
model.add(Dense(total_words, activation='softmax')) |
|
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy']) |
|
earlystop = EarlyStopping(monitor='loss', min_delta=0, patience=3, verbose=0, mode='auto') |
|
history = model.fit(X, y, epochs=10, verbose=1, callbacks=[earlystop]) |
|
|
|
plt.plot(history.history['accuracy'], label='train acc') |
|
plt.legend() |
|
plt.show() |
|
plt.savefig('AccVal_acc') |
|
|
|
def complete_this_song(seed_text, next_words): |
|
for _ in range(next_words): |
|
token_list = tokenizer.texts_to_sequences([seed_text])[0] |
|
token_list = pad_sequences([token_list], maxlen=max_sequence_len-1, padding='pre') |
|
|
|
predict_x=model.predict(token_list, verbose=0) |
|
classes_x=np.argmax(predict_x,axis=1) |
|
output_word = "" |
|
for word, index in tokenizer.word_index.items(): |
|
if index == classes_x: |
|
output_word = word |
|
break |
|
seed_text += " " + output_word |
|
return seed_text |
|
|
|
complete_this_song("the sky is blue", 40) |
|
|
|
!pip install keras.models |
|
|
|
from tensorflow.keras.models import load_model |
|
model.save('/content/drive/MyDrive/Colab Notebooks/song_lyrics_generator.h5') |
|
|
|
import tensorflow as tf |
|
|
|
from tensorflow.keras.models import load_model |
|
song_lyrics_generator= tf.keras.models.load_model('/content/drive/MyDrive/Colab Notebooks/song_lyrics_generator.h5') |
|
|
|
!pip install gradio |
|
import gradio as gr |
|
|
|
interface = gr.Interface(fn= complete_this_song, |
|
inputs= ['text', gr.inputs.Slider(0,250, label='No. of words')], |
|
outputs='text') |
|
|
|
interface.launch() |
