Duplicate from OrganizedProgrammers/SEPredictor

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+ebd4appdom.xlsx filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: SEPredictor
+emoji: ⚡
+colorFrom: green
+colorTo: yellow
+sdk: gradio
+sdk_version: 3.29.0
+app_file: app.py
+pinned: false
+duplicated_from: OrganizedProgrammers/SEPredictor
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,65 @@
+from flask import Flask, jsonify, request, render_template
+import pandas as pd
+import numpy as np
+from sentence_transformers import SentenceTransformer, util
+import torch
+import re
+
+app = Flask(__name__)
+
+
+
+def extract_embeddings(embeddings_str):
+    pattern = r'(-?\d+(?:\.\d+)?(?:[eE]-?\d+)?)'
+    matches = re.findall(pattern, embeddings_str)
+    return list(map(float, matches))
+
+df = pd.read_excel("ebd4appdom.xlsx")
+embedder = SentenceTransformer('all-MiniLM-L6-v2')
+df['Embeddings'] = df['Embeddings'].apply(extract_embeddings)
+descriptions_embeddings = list(df.Embeddings)
+patnums = list(df["Number"])
+standards = list(df["Standards"])
+urls = list(df["URL"])
+descriptions = list(df.Description)
+
+def split_string(s, max_len, overlap, min_words_count=0):
+    words = s.split()
+    substrings = []
+    start = 0
+    while start + max_len < len(words):
+        end = start + max_len
+        substring = " ".join(words[start:end])
+        substrings.append(substring)
+        start = end - overlap
+    substrings.append(" ".join(words[start:]))
+    long_substrings = []
+    for string in substrings:
+        if len(string.split()) > min_words_count:
+            long_substrings.append(string)
+    return long_substrings
+
+@app.route('/', methods=['GET', 'POST'])
+def index():
+    if request.method == 'POST':
+        query = request.form['query']
+        user_samples = split_string(query, 80, 3)
+        top_k = min(5, len(descriptions))
+        results = []
+        cpt=0
+        for user_sample in user_samples:
+            sp=[[user_sample, 'sample' + str(cpt)]]
+            sample_embedding = embedder.encode(user_sample, convert_to_tensor=True)
+            cos_scores = util.cos_sim(sample_embedding, descriptions_embeddings)[0]
+            top_results = torch.topk(cos_scores, top_k)
+            for score, idx in zip(top_results[0], top_results[1]):
+                my_dict = dict(score= round(float(score.item()), 4), standards=standards[idx], desc=descriptions[idx], url=urls[idx])
+                sp.append(my_dict)
+            results.append(sp)
+            cpt += 1
+        return render_template('index.html', results=results)
+    else:
+        return render_template('index.html', results=None)
+
+if __name__ == '__main__':
+    app.run(host="0.0.0.0", port=7860)

ebd4appdom.xlsx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c00f2818e0c2e19382d6d180b020c4e8a03b681f5b7d8afb8cf39b620b5faea6
+size 332417405

requirements.txt

@@ -0,0 +1,7 @@
+gradio
+pandas
+numpy
+torch>=1.6
+flask
+sentence-transformers
+openpyxl

templates/index.html

@@ -0,0 +1,95 @@
+<!DOCTYPE html>
+<html>
+  <head>
+    <meta charset="utf-8">
+    <title>SEPredictor</title>
+    <link href="https://cdn.jsdelivr.net/npm/[email protected]/dist/css/bootstrap.min.css" rel="stylesheet" integrity="sha384-aFq/bzH65dt+w6FI2ooMVUpc+21e0SRygnTpmBvdBgSdnuTN7QbdgL+OapgHtvPp" crossorigin="anonymous">
+    <script src="https://cdn.jsdelivr.net/npm/[email protected]/dist/js/bootstrap.bundle.min.js" integrity="sha384-qKXV1j0HvMUeCBQ+QVp7JcfGl760yU08IQ+GpUo5hlbpg51QRiuqHAJz8+BrxE/N" crossorigin="anonymous"></script>
+    <style>
+      body {
+        background-color: #EEEEEE;
+      }
+      form {
+        padding: 5em 10em;
+      }
+      .btn-primary {
+        font-size: 1.2em;
+        padding: 0em 7em;
+        display: block;
+        margin: 0 auto;
+      }
+      .similarsamples{
+        padding: 2em 2em;
+      }
+      .navbar {
+        position: fixed;
+        top: 0;
+        width: 100%;
+        z-index: 1;
+      }
+    </style>
+  
+  </head>
+
+
+  <body>
+
+
+    <nav class="navbar bg-body-tertiary">
+      <div class="container-fluid">
+        <a class="navbar-brand" href="http://127.0.0.1:5000/">SEPredictor</a>
+      </div>
+    </nav>
+
+
+    <form method="POST" action="/">
+      <div class="mb-3">
+        <label for="query">Enter your patent description:</label>
+        <textarea type="text" id="query" name="query" class="form-control" rows="10"></textarea>
+      </div>
+      <input type="submit" value="Search similar patents" class="btn btn-primary mb-3">
+    </form>
+
+    
+    <div class="similarsamples">
+      {% if results %}
+      <h2>Description Samples:</h2>
+      {% for result in results %}
+      <div class="accordion accordion-flush" id="accordionFlushExample">
+        <div class="accordion-item">
+          <h2 class="accordion-header">
+            <button class="accordion-button collapsed" type="button" data-bs-toggle="collapse" data-bs-target= '#{{ result[0][1] }}' aria-expanded="false" aria-controls="flush-collapseOne">
+                <p>{{ result[0][0] }}</p>
+              </button>
+            </h2>
+            <div id="{{ result[0][1] }}" class="accordion-collapse collapse" data-bs-parent="#accordionFlushExample">
+              <div class="accordion-body">
+                <table class="table table-light table-striped">
+                  <thead>
+                    <tr>
+                      <th scope="col">Score</th>
+                      <th scope="col">Sample</th>
+                      <th scope="col">Standards</th>
+                      <th scope="col">Document</th>
+                    </tr>
+                  </thead>
+                  <tbody>
+                    {% for i in range(1,6) %}
+                    <tr>
+                      <th scope="row">{{ result[i]['score'] }}</th>
+                      <td>{{ result[i]['desc'] }}</td>
+                      <td>{{ result[i]['standards'] }}</td>
+                      <td><a href= {{ result[i]['url'] }}>Open</a></td>
+                    </tr>
+                    {% endfor %}
+                  </tbody>
+                </table>
+              </div>
+            </div>
+        </div>
+      </div>
+      {% endfor %}
+      {% endif %}
+    </div>
+  </body>
+</html>