Spaces:
Sleeping
Sleeping
File size: 3,629 Bytes
7dbb743 344daf4 7dbb743 f8828b6 7dbb743 f8828b6 7dbb743 f8828b6 7dbb743 f8828b6 7dbb743 f8828b6 7dbb743 f8828b6 7dbb743 f8828b6 a9f65b9 f8828b6 7dbb743 f8828b6 7dbb743 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 |
from flask import Flask, render_template, request, redirect, url_for
from joblib import load
import pandas as pd
import re
from customFunctions import *
import json
import datetime
import numpy as np
pd.set_option('display.max_colwidth', 1000)
import torch
# Patch torch.load to always load on CPU
original_torch_load = torch.load
def cpu_load(*args, **kwargs):
return original_torch_load(*args, map_location=torch.device('cpu'), **kwargs)
torch.load = cpu_load
PIPELINES = [
{
'id': 1,
'name': 'Baseline',
'pipeline': load("pipelines/pipeline_ex1_s1.joblib")
},
{
'id': 2,
'name': 'Trained on a FeedForward NN',
'pipeline': load("pipelines/pipeline_ex1_s2.joblib")
},
{
'id': 3,
'name': 'Trained on a CRF',
'pipeline': load("pipelines/pipeline_ex1_s3.joblib")
},
{
'id': 4,
'name': 'Trained on a small dataset',
'pipeline': load("pipelines/pipeline_ex2_s3.joblib")
},
{
'id': 5,
'name': 'Trained on a large dataset',
'pipeline': load("pipelines/pipeline_ex2_s2.joblib")
},
{
'id': 6,
'name': 'Embedded using TFIDF',
'pipeline': load("pipelines/pipeline_ex3_s2.joblib")
},
{
'id': 7,
'name': 'Embedded using GloVe',
'pipeline': load("pipelines/pipeline_ex3_s3.joblib")
},
{
'id': 8,
'name': 'Embedded using Bio2Vec',
'pipeline': load("pipelines/pipeline_ex3_s4.joblib")
},
]
pipeline_metadata = [{'id': p['id'], 'name': p['name']} for p in PIPELINES]
def get_pipeline_by_id(pipelines, pipeline_id):
return next((p['pipeline'] for p in pipelines if p['id'] == pipeline_id), None)
def get_name_by_id(pipelines, pipeline_id):
return next((p['name'] for p in pipelines if p['id'] == pipeline_id), None)
def requestResults(text, pipeline):
labels = pipeline.predict(text)
if isinstance(labels, np.ndarray):
labels = labels.tolist()
return labels[0]
import os
LOG_FILE = "/tmp/usage_log.jsonl" # Use temporary file path for Hugging Face Spaces
def log_interaction(user_input, model_name, predictions):
log_entry = {
"timestamp": datetime.datetime.utcnow().isoformat(),
"model": model_name,
"user_input": user_input,
"predictions": predictions
}
try:
os.makedirs(os.path.dirname(LOG_FILE), exist_ok=True) # Ensure the directory exists
with open(LOG_FILE, "a") as log_file:
log_file.write(json.dumps(log_entry) + "\n")
except Exception as e:
print(f"Error writing to log: {e}")
# You could also return a response with the error, or raise an error to stop the process
app = Flask(__name__)
@app.route('/')
def index():
return render_template('index.html', pipelines= pipeline_metadata)
@app.route('/', methods=['POST'])
def get_data():
if request.method == 'POST':
text = request.form['search']
tokens = re.findall(r"\w+|[^\w\s]", text)
tokens_fomatted = pd.Series([pd.Series(tokens)])
pipeline_id = int(request.form['pipeline_select'])
pipeline = get_pipeline_by_id(PIPELINES, pipeline_id)
name = get_name_by_id(PIPELINES, pipeline_id)
labels = requestResults(tokens_fomatted, pipeline)
results = dict(zip(tokens, labels))
log_interaction(text, name, results)
return render_template('index.html', results=results, name=name, pipelines= pipeline_metadata)
if __name__ == '__main__':
app.run(host="0.0.0.0", port=7860)
|