feat: word frequency endpoint with stop word removal
This commit is contained in:
@@ -14,7 +14,9 @@ httplib2==0.31.1
|
|||||||
idna==3.11
|
idna==3.11
|
||||||
itsdangerous==2.2.0
|
itsdangerous==2.2.0
|
||||||
Jinja2==3.1.6
|
Jinja2==3.1.6
|
||||||
|
joblib==1.5.3
|
||||||
MarkupSafe==3.0.3
|
MarkupSafe==3.0.3
|
||||||
|
nltk==3.9.2
|
||||||
numpy==2.4.1
|
numpy==2.4.1
|
||||||
pandas==2.3.3
|
pandas==2.3.3
|
||||||
proto-plus==1.27.0
|
proto-plus==1.27.0
|
||||||
@@ -27,10 +29,12 @@ pyparsing==3.3.1
|
|||||||
python-dateutil==2.9.0.post0
|
python-dateutil==2.9.0.post0
|
||||||
python-dotenv==1.2.1
|
python-dotenv==1.2.1
|
||||||
pytz==2025.2
|
pytz==2025.2
|
||||||
|
regex==2026.1.15
|
||||||
requests==2.32.5
|
requests==2.32.5
|
||||||
rsa==4.9.1
|
rsa==4.9.1
|
||||||
six==1.17.0
|
six==1.17.0
|
||||||
soupsieve==2.8.1
|
soupsieve==2.8.1
|
||||||
|
tqdm==4.67.1
|
||||||
typing_extensions==4.15.0
|
typing_extensions==4.15.0
|
||||||
tzdata==2025.3
|
tzdata==2025.3
|
||||||
uritemplate==4.2.0
|
uritemplate==4.2.0
|
||||||
|
|||||||
@@ -1,5 +1,7 @@
|
|||||||
from flask import Flask, jsonify, request
|
from flask import Flask, jsonify, request
|
||||||
from flask_cors import CORS
|
from flask_cors import CORS
|
||||||
|
import nltk
|
||||||
|
from nltk.corpus import stopwords
|
||||||
import pandas as pd
|
import pandas as pd
|
||||||
|
|
||||||
app = Flask(__name__)
|
app = Flask(__name__)
|
||||||
@@ -11,6 +13,9 @@ CORS(app, resources={r"/*": {"origins": "http://localhost:5173"}})
|
|||||||
posts_df = None
|
posts_df = None
|
||||||
comments_df = None
|
comments_df = None
|
||||||
|
|
||||||
|
nltk.download('stopwords')
|
||||||
|
EXCLUDE_WORDS = set(stopwords.words('english'))
|
||||||
|
|
||||||
@app.route('/upload', methods=['POST'])
|
@app.route('/upload', methods=['POST'])
|
||||||
def upload_data():
|
def upload_data():
|
||||||
if "posts" not in request.files or "comments" not in request.files:
|
if "posts" not in request.files or "comments" not in request.files:
|
||||||
@@ -76,5 +81,30 @@ def comments_per_day():
|
|||||||
|
|
||||||
return jsonify(comments_per_day.to_dict(orient='records')), 200
|
return jsonify(comments_per_day.to_dict(orient='records')), 200
|
||||||
|
|
||||||
|
@app.route('/stats/word_frequencies', methods=['GET'])
|
||||||
|
def word_frequencies():
|
||||||
|
if posts_df is None:
|
||||||
|
return jsonify({"error": "No data uploaded"}), 400
|
||||||
|
|
||||||
|
try:
|
||||||
|
all_text = " ".join(posts_df['content'].fillna(''))
|
||||||
|
words = all_text.split()
|
||||||
|
word_freq = {}
|
||||||
|
for word in words:
|
||||||
|
clean_word = ''.join(c.lower() for c in word if c.isalnum())
|
||||||
|
if clean_word and clean_word not in EXCLUDE_WORDS:
|
||||||
|
word_freq[clean_word] = word_freq.get(clean_word, 0) + 1
|
||||||
|
|
||||||
|
sorted_words = sorted(word_freq.items(), key=lambda item: item[1], reverse=True)
|
||||||
|
|
||||||
|
# Get top 100 words and their frequencies and return as list of dicts
|
||||||
|
sorted_words = [{"word": word, "frequency": freq} for word, freq in sorted_words]
|
||||||
|
except ValueError as e:
|
||||||
|
return jsonify({"error": f"Malformed or missing data: {str(e)}"}), 400
|
||||||
|
except Exception as e:
|
||||||
|
return jsonify({"error": f"An unexpected error occurred: {str(e)}"}), 500
|
||||||
|
|
||||||
|
return jsonify(sorted_words[:100]), 200
|
||||||
|
|
||||||
if __name__ == "__main__":
|
if __name__ == "__main__":
|
||||||
app.run(debug=True)
|
app.run(debug=True)
|
||||||
Reference in New Issue
Block a user