Spaces:
Runtime error
Runtime error
Zaman, Shaheer Shaheer
commited on
Commit
•
414b5fe
1
Parent(s):
90fc317
first commit
Browse files- .gitignore +1 -0
- app.py +87 -0
- requirements.txt +10 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
venv/
|
app.py
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
import pandas as pd
|
3 |
+
import re
|
4 |
+
import nltk
|
5 |
+
from PIL import Image
|
6 |
+
import os
|
7 |
+
import numpy as np
|
8 |
+
import seaborn as sns
|
9 |
+
from wordcloud import WordCloud, STOPWORDS
|
10 |
+
from nltk.corpus import stopwords
|
11 |
+
import datasets
|
12 |
+
from datasets import load_dataset
|
13 |
+
import matplotlib.pyplot as plt
|
14 |
+
import sklearn
|
15 |
+
from sklearn.preprocessing import LabelEncoder
|
16 |
+
sns.set_palette('RdBu')
|
17 |
+
|
18 |
+
#load dataset
|
19 |
+
dataset = load_dataset('merve/poetry', streaming=True)
|
20 |
+
df = pd.DataFrame.from_dict(dataset['train'])
|
21 |
+
|
22 |
+
d = os.path.dirname(__file__) if '__file__' in locals() else os.getcwd()
|
23 |
+
nltk.download('stopwords')
|
24 |
+
stop = stopwords.words('english')
|
25 |
+
|
26 |
+
def standardize(text, remove_digits=True):
|
27 |
+
text = re.sub('[^a-zA-Z\d\s]', '', text)
|
28 |
+
text = text.lower()
|
29 |
+
|
30 |
+
return text
|
31 |
+
|
32 |
+
|
33 |
+
st.set_option('deprecation.showPyplotGlobalUse', False)
|
34 |
+
st.write('Poetry dataset, content character cleaned from special characters and lower cased')
|
35 |
+
df.content = df.content.apply(lambda x: ' '.join(word for word in x.split() if word not in stop))
|
36 |
+
df.content = df.content.apply(standardize)
|
37 |
+
st.dataframe(df)
|
38 |
+
|
39 |
+
st.subheader('Visualization on dataset statistics')
|
40 |
+
|
41 |
+
st.write('Number of peoms written in each type')
|
42 |
+
sns.catplot(x='type', data=df, kind='count')
|
43 |
+
plt.xticks(rotation=0)
|
44 |
+
st.pyplot()
|
45 |
+
|
46 |
+
st.write('Number of poems for each age')
|
47 |
+
sns.catplot(x='age', data=df, kind='count')
|
48 |
+
plt.xticks(rotation=0)
|
49 |
+
st.pyplot()
|
50 |
+
|
51 |
+
st.write("Number of poems for each author")
|
52 |
+
sns.catplot(x="author", data=df, kind="count", aspect = 4)
|
53 |
+
plt.xticks(rotation=90)
|
54 |
+
st.pyplot()
|
55 |
+
|
56 |
+
st.write('Distributions of poem types according to ages and authors, seems that folks in renaissance loved the love themed poems and nature themed poems became popular later')
|
57 |
+
le = LabelEncoder()
|
58 |
+
|
59 |
+
df.author = le.fit_transform(df.author)
|
60 |
+
sns.catplot(x='age', y='author', hue='type', data=df)
|
61 |
+
st.pyplot()
|
62 |
+
|
63 |
+
words = df.content.str.split(expand=True).unstack().value_counts()
|
64 |
+
renaissance = df.content.loc[df.age == 'Renaissance'].str.split(expand=True).unstack().value_counts()
|
65 |
+
modern = df.content.loc[df.age == 'modern'].str.split(expand=True).unstack().value_counts()
|
66 |
+
st.subheader('Visualizing content')
|
67 |
+
mask = np.array(Image.open(os.path.join(d, 'poet.png')))
|
68 |
+
|
69 |
+
import matplotlib.pyplot as plt
|
70 |
+
def word_cloud(content, title):
|
71 |
+
wc = WordCloud(background_color='white',
|
72 |
+
max_words=200,
|
73 |
+
contour_width=3,
|
74 |
+
stopwords=STOPWORDS,
|
75 |
+
max_font_size=50)
|
76 |
+
wc.generate(' '.join(content.index.values))
|
77 |
+
fig = plt.figure(figsize=(10, 10))
|
78 |
+
plt.title(title, fontsize=20)
|
79 |
+
plt.imshow(wc.recolor(colormap='magma', random_state=42), cmap=plt.cm.gray, interpolation = "bilinear", alpha=0.98)
|
80 |
+
plt.axis('off')
|
81 |
+
st.pyplot()
|
82 |
+
|
83 |
+
st.subheader('Most appearing words excluding stopwords n poems according to ages')
|
84 |
+
word_cloud(modern, 'word cloud Renaissance poems')
|
85 |
+
|
86 |
+
st.write('Most appearing words including stopwords')
|
87 |
+
st.bar_chart(words[:50])
|
requirements.txt
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
nltk
|
2 |
+
spacy
|
3 |
+
datasets==1.12.1
|
4 |
+
wordcloud
|
5 |
+
streamlit==0.84.2
|
6 |
+
numpy
|
7 |
+
pandas
|
8 |
+
sklearn
|
9 |
+
pillow
|
10 |
+
seaborn
|