Spaces:
Build error
Build error
Upload app.py
Browse files
app.py
CHANGED
@@ -1,15 +1,42 @@
|
|
1 |
-
import streamlit as st
|
2 |
-
import datasets
|
3 |
from datasets import load_dataset
|
4 |
-
import
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
|
6 |
-
def
|
7 |
-
|
8 |
-
|
9 |
|
|
|
10 |
|
11 |
-
|
12 |
-
df
|
13 |
-
st.write("loading dataset")
|
14 |
st.dataframe(df)
|
15 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
from datasets import load_dataset
|
2 |
+
import streamlit as st
|
3 |
+
import pandas as pd
|
4 |
+
import re
|
5 |
+
import nltk
|
6 |
+
from wordcloud import WordCloud, STOPWORDS
|
7 |
+
from nltk.corpus import stopwords
|
8 |
+
nltk.download("stopwords")
|
9 |
+
stop = stopwords.words('english')
|
10 |
+
|
11 |
+
dataset = load_dataset("huggingartists/gorillaz")
|
12 |
+
df = pd.DataFrame.from_dict(dataset["train"])
|
13 |
+
|
14 |
+
st.dataframe(df)
|
15 |
+
st.write("Removed special characters")
|
16 |
|
17 |
+
def standardize(text, remove_digits=True):
|
18 |
+
text=re.sub('[^a-zA-Z\d\s]', '',text)
|
19 |
+
text = text.lower()
|
20 |
|
21 |
+
return text
|
22 |
|
23 |
+
df.text = df.text.apply(lambda x: ' '.join([word for word in x.split() if word not in (stop)]))
|
24 |
+
df.text=df.text.apply(standardize)
|
|
|
25 |
st.dataframe(df)
|
26 |
+
|
27 |
+
words = df.text.str.split(expand=True).unstack().value_counts()
|
28 |
+
st.bar_chart(words[20:40])
|
29 |
+
st.set_option('deprecation.showPyplotGlobalUse', False)
|
30 |
+
|
31 |
+
import matplotlib.pyplot as plt
|
32 |
+
def word_cloud(content, title):
|
33 |
+
wc = WordCloud(background_color='white', max_words=200,
|
34 |
+
stopwords=STOPWORDS, max_font_size=50)
|
35 |
+
wc.generate(" ".join(content.index.values))
|
36 |
+
fig = plt.figure(figsize=(16, 13))
|
37 |
+
plt.title(title, fontsize=20)
|
38 |
+
plt.imshow(wc.recolor(colormap='Pastel2', random_state=42), alpha=0.98)
|
39 |
+
plt.axis('off')
|
40 |
+
st.pyplot()
|
41 |
+
|
42 |
+
word_cloud(words, "Word Cloud")
|