Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: zero-shot-classification
|
| 3 |
+
---
|
| 4 |
+
# Install transformers library
|
| 5 |
+
!pip install transformers
|
| 6 |
+
|
| 7 |
+
# Import necessary libraries
|
| 8 |
+
import pandas as pd
|
| 9 |
+
from transformers import pipeline
|
| 10 |
+
from google.colab import files
|
| 11 |
+
|
| 12 |
+
# Upload the file
|
| 13 |
+
uploaded = files.upload()
|
| 14 |
+
|
| 15 |
+
# Load the dataset
|
| 16 |
+
file_name = 'publications.csv' # Use the file name as uploaded
|
| 17 |
+
df = pd.read_csv(file_name)
|
| 18 |
+
|
| 19 |
+
# Display the first few rows of the dataset
|
| 20 |
+
df.head()
|
| 21 |
+
|
| 22 |
+
# Load the zero-shot classification pipeline
|
| 23 |
+
classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
|
| 24 |
+
|
| 25 |
+
# Define the categories
|
| 26 |
+
candidate_labels = ["World", "Sports", "Business", "Science and Technology", "Entertainment", "Lifestyle"]
|
| 27 |
+
|
| 28 |
+
# Classify each news article
|
| 29 |
+
results = []
|
| 30 |
+
|
| 31 |
+
for article in df['headline']:
|
| 32 |
+
result = classifier(article, candidate_labels)
|
| 33 |
+
category = result['labels'][0]
|
| 34 |
+
results.append(category)
|
| 35 |
+
|
| 36 |
+
# Add the results to the DataFrame
|
| 37 |
+
df['category'] = results
|
| 38 |
+
|
| 39 |
+
# Display the categorized DataFrame
|
| 40 |
+
df.head(10)
|