commit

gov.py

@@ -21,7 +21,7 @@ translator = Translator()
 def datemodifier(date_string):
     """Date Modifier Function"""
     try:
-        to_date = time.strptime(date_string,"%Y-%m-%d %H:%M:%S")
+        to_date = time.strptime(date_string,"%Y-%m-%d-%H:%M:%S")
         return time.strftime("%Y-%m-%d",to_date)
     except:
         return False

ner.ipynb

@@ -1,85 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from flair.nn import Classifier\n",
-    "from flair.data import Sentence\n",
-    "\n",
-    "linker = Classifier.load('linker')\n",
-    "ner = Classifier.load('flair/ner-english-ontonotes-fast')\n",
-    "\n",
-    "def linker_model(input_text, tagger):\n",
-    "    \"\"\"Linker model predict tags for sentences\"\"\"\n",
-    "    sentence = Sentence(input_text)\n",
-    "    tagger.predict(sentence)\n",
-    "\n",
-    "    # iterate through sentences and print predicted labels\n",
-    "    label_dict = {}\n",
-    "    for label in sentence.get_labels():\n",
-    "        if label.data_point.text.endswith(\"F.C.\"):\n",
-    "            continue\n",
-    "        if (label.score>0.5) & (label.value != \"<unk>\"):\n",
-    "            if label.value in label_dict:\n",
-    "                label_dict[label.value].append(label.data_point.text)\n",
-    "            else:\n",
-    "                label_dict[label.value] = [label.data_point.text]\n",
-    "    return label_dict\n",
-    "\n",
-    "def find_keys_by_value(dictionary, value):\n",
-    "    \"\"\"Find key by value\"\"\"\n",
-    "    keys = []\n",
-    "    for key, values in dictionary.items():\n",
-    "        if value in values:\n",
-    "            keys.append(key)\n",
-    "    return keys\n",
-    "\n",
-    "def recognition_model(input_text, label_dict, tagger):\n",
-    "    \"\"\"recognition model\"\"\"\n",
-    "    ner_dict = {}\n",
-    "    score_dict = {}\n",
-    "    sentence = Sentence(input_text)\n",
-    "    tagger.predict(sentence)\n",
-    "    # for sentence in sentences:\n",
-    "    for label in sentence.get_labels():\n",
-    "        if label.score>0.5:\n",
-    "            data_point = label.data_point.text\n",
-    "            label_value = label.value\n",
-    "            # label_value PER\n",
-    "            keys = find_keys_by_value(label_dict, data_point)\n",
-    "            if len(keys)>0:\n",
-    "                if label_value in ner_dict:\n",
-    "                    if keys[0] not in ner_dict[label_value]:\n",
-    "                        ner_dict[label.value].append(keys[0])\n",
-    "                        score_dict[keys[0]] = label.score\n",
-    "                else:\n",
-    "                    ner_dict[label.value] = [keys[0]]\n",
-    "                    score_dict[keys[0]] = label.score\n",
-    "    return ner_dict, score_dict"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "for _, item in df.iterrows():\n",
-    "    label_dict = linker_model(item['content'],linker)\n",
-    "    ner_dict, score_dict = recognition_model(item['content'], label_dict, ner)\n",
-    "    # result = result_dictionary_constructor(ner_dict, label_dict)\n",
-    "    print(ner_dict, score_dict)"
-   ]
-  }
- ],
- "metadata": {
-  "language_info": {
-   "name": "python"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}