Spaces:
Running
Running
File size: 2,810 Bytes
9a7645a 4b67ac0 9a7645a 4b67ac0 9a7645a 4b67ac0 f41c648 4b67ac0 f41c648 4b67ac0 9a7645a f41c648 4b67ac0 9a7645a |
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 |
import gradio as gr
import joblib
import spacy
import numpy as np
import matplotlib.pyplot as plt
from sklearn.feature_extraction.text import CountVectorizer, TfidfVectorizer
from sklearn.preprocessing import MultiLabelBinarizer
from sklearn.base import BaseEstimator, TransformerMixin
nlp = spacy.load('en_core_web_sm')
tfidf = joblib.load('./tfidf.joblib')
model = joblib.load('./model.joblib')
tags_binarizer = joblib.load('./tags.joblib')
def lemmatize(s: str) -> iter:
# tokenize
doc = nlp(s)
# remove punct and stopwords
tokens = filter(lambda token: not token.is_space and not token.is_punct and not token.is_stop and not token.is_digit, doc)
# lemmatize
return map(lambda token: token.lemma_.lower(), tokens)
def plot(tags, proba):
plt.style.use('dark_background')
plt.rcParams.update({'font.size': 16})
fig, ax = plt.subplots(figsize=(12,9))
ax.barh(tags, proba, align='center', color='darkred')
ax.set_yticks(tags, labels=tags)
ax.invert_yaxis() # labels read top-to-bottom
ax.set_xlabel('Score')
ax.set_title('Score/Tag')
for i, v in enumerate(proba):
ax.text(v - 0.065, i + 0.05, str(round(v, 2)))
plt.xlim(0, 1)
plt.show()
def predict_words(X):
y_bin = model.predict(X)
y_tags = " ".join(tags_binarizer.inverse_transform(y_bin)[0])
return y_tags
def proba_chart(X):
y_proba = model.predict_proba(X)[0]
tags = list(dict(sorted(tags_binarizer.ts.count.items())).keys())
# combine
data = list(zip(tags, y_proba))
# sort
data = sorted(data, key=lambda tag_value: tag_value[1], reverse=True)
# keep values >= min_score
data = list(filter(lambda tag_value: tag_value[1] >= 0.1, data))
# we have our two dimensions for chart
tags, proba = zip(*data)
# build chart
plt.style.use('dark_background')
plt.rcParams.update({'font.size': 16})
fig, ax = plt.subplots(figsize=(12,9))
ax.barh(tags, proba, align='center', color='darkred')
ax.set_yticks(tags, labels=tags)
ax.invert_yaxis() # labels read top-to-bottom
ax.set_xlabel('Score')
ax.set_title('Score/Tag')
for i, v in enumerate(proba):
ax.text(v - 0.065, i + 0.05, str(round(v, 2)))
plt.xlim(0, 1)
return fig
def predict(title: str , post: str):
text = title + " " + post
lemmes = np.array([' '.join(list(lemmatize(text)))])
X = tfidf.transform(lemmes)
# predicted words
words = predict_words(X)
# proba chart
chart = proba_chart(X)
return words, chart
demo = gr.Interface(
fn=predict,
inputs=[
gr.Textbox(label="Title", lines=1, placeholder="Title..."),
gr.Textbox(label="Post", lines=20, placeholder="Post...")],
outputs=[gr.Textbox(label="Tags"), gr.Plot()])
demo.launch() |