Upload 2 files
Browse files- goodies/data.csv +2 -2
- goodies/sentiment.py +30 -2
goodies/data.csv
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bed21061c54fb40693e1879336dfd2be7f1583089ed286fe395e44e3fda1762
|
| 3 |
+
size 11088805
|
goodies/sentiment.py
CHANGED
|
@@ -6,13 +6,14 @@ from bs4 import BeautifulSoup
|
|
| 6 |
import pandas as pd
|
| 7 |
import altair as alt
|
| 8 |
from collections import OrderedDict
|
| 9 |
-
import nltk
|
| 10 |
from nltk.tokenize import sent_tokenize
|
| 11 |
|
|
|
|
|
|
|
| 12 |
nltk.download('punkt')
|
| 13 |
|
| 14 |
# Load model and tokenizer
|
| 15 |
-
model_name = '
|
| 16 |
model = AutoModelForSequenceClassification.from_pretrained(model_name)
|
| 17 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 18 |
|
|
@@ -85,6 +86,21 @@ def classify_sentences(text):
|
|
| 85 |
st.title("Sentiment Classification from URL")
|
| 86 |
|
| 87 |
url = st.text_input("Enter URL:")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 88 |
if url:
|
| 89 |
text = get_text_from_url(url)
|
| 90 |
if text:
|
|
@@ -140,3 +156,15 @@ if url:
|
|
| 140 |
|
| 141 |
else:
|
| 142 |
st.write("Could not extract text from the provided URL.")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
import pandas as pd
|
| 7 |
import altair as alt
|
| 8 |
from collections import OrderedDict
|
|
|
|
| 9 |
from nltk.tokenize import sent_tokenize
|
| 10 |
|
| 11 |
+
# Load the punkt tokenizer from nltk
|
| 12 |
+
import nltk
|
| 13 |
nltk.download('punkt')
|
| 14 |
|
| 15 |
# Load model and tokenizer
|
| 16 |
+
model_name = 'dejanseo/sentiment'
|
| 17 |
model = AutoModelForSequenceClassification.from_pretrained(model_name)
|
| 18 |
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
| 19 |
|
|
|
|
| 86 |
st.title("Sentiment Classification from URL")
|
| 87 |
|
| 88 |
url = st.text_input("Enter URL:")
|
| 89 |
+
|
| 90 |
+
# Additional information
|
| 91 |
+
st.markdown("""
|
| 92 |
+
Multi-label sentiment classification model developed by [Dejan Marketing](https://dejanmarketing.com/).
|
| 93 |
+
|
| 94 |
+
The model is designed to be deployed in an automated pipeline capable of classifying text sentiment for thousands (or even millions) of text chunks or as a part of a scraping pipeline.
|
| 95 |
+
|
| 96 |
+
This is a demo model which may occassionally misclasify some texts. In a typical commercial project, a larger model is deployed for the task, and in special cases, a domain-specific model is developed for the client.
|
| 97 |
+
|
| 98 |
+
# Engage Our Team
|
| 99 |
+
Interested in using this in an automated pipeline for bulk query processing?
|
| 100 |
+
|
| 101 |
+
Please [book an appointment](https://dejanmarketing.com/conference/) to discuss your needs.
|
| 102 |
+
""")
|
| 103 |
+
|
| 104 |
if url:
|
| 105 |
text = get_text_from_url(url)
|
| 106 |
if text:
|
|
|
|
| 156 |
|
| 157 |
else:
|
| 158 |
st.write("Could not extract text from the provided URL.")
|
| 159 |
+
|
| 160 |
+
# Additional information at the end
|
| 161 |
+
st.markdown("""
|
| 162 |
+
Multi-label sentiment classification model developed by [Dejan Marketing](https://dejanmarketing.com/).
|
| 163 |
+
|
| 164 |
+
The model is designed to be deployed in an automated pipeline capable of classifying text sentiment for thousands (or even millions) of text chunks or as a part of a scraping pipeline. This is a demo model which may occassionally misclasify some texts. In a typical commercial project, a larger model is deployed for the task, and in special cases, a domain-specific model is developed for the client.
|
| 165 |
+
|
| 166 |
+
### Engage Our Team
|
| 167 |
+
Interested in using this in an automated pipeline for bulk query processing?
|
| 168 |
+
|
| 169 |
+
Please [book an appointment](https://dejanmarketing.com/conference/) to discuss your needs.
|
| 170 |
+
""")
|