edit code

.ipynb_checkpoints/Untitled-checkpoint.ipynb

@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

.ipynb_checkpoints/utils-checkpoint.py

@@ -24,17 +24,17 @@ def get_single_prediction(text):
     # manipulate data into a format that we pass to our model
     text = text.lower().strip() #lower case
 
-    # Vectorise text and store in new dataframe. Sentence vector = average of word vectors
-    text_vectors = tfidf.transform(list(text))
-    print('check1')
+    # Vectorise text
+    text_vectors = tfidf.transform([text])
+
     # Make topic predictions
-    results = svc.predict_proba(text_vectors).squeeze().round(2)
-    print('check2')
+    results = svc.predict_proba(text_vectors.reshape()).squeeze().round(2)
+
     pred_prob = pd.DataFrame({'topic': labels, 'probability': results}).sort_values('probability', ascending=True)
-    print('check3')
+
     # Make sentiment predictions
-    text_vectors_sentiment = tfidf_sentiment.transform(list(text))
-    print('check4')
+    text_vectors_sentiment = tfidf_sentiment.transform([text])
+ 
     results_sentiment = svc_sentiment.predict_proba(text_vectors).squeeze().round(2)
     pred_prob_sentiment = pd.DataFrame({'sentiment': ['Negative', 'Positive'], 'probability': results_sentiment}).sort_values('probability', ascending=True)
     

Untitled.ipynb

@@ -0,0 +1,126 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "8e91c310-bc69-4a28-9197-e180aaaa491f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "utils imported!\n"
+     ]
+    }
+   ],
+   "source": [
+    "import re\n",
+    "import pickle\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "\n",
+    "\n",
+    "tfidf = pickle.load(open('models/tfidf.sav', 'rb'))\n",
+    "svc_sentiment = pickle.load(open('models/sentiment_model.sav', 'rb'))\n",
+    "tfidf_sentiment = pickle.load(open('models/tfidf_sentiment.sav', 'rb'))\n",
+    "svc = pickle.load(open('models/svc_model.sav', 'rb'))\n",
+    "\n",
+    "labels = [\n",
+    "       'Product quality', 'Knowledge',\n",
+    "       'Appointment', 'Service etiquette', 'Waiting time',\n",
+    "       'Repair speed', 'Repair cost', 'Repair quality', 'Warranty',\n",
+    "       'Product replacement', 'Loan sets']\n",
+    "\n",
+    "sample_file = pd.read_csv('sample.csv').to_csv(index=False).encode('utf-8')\n",
+    "\n",
+    "print('utils imported!')\n",
+    "\n",
+    "def get_single_prediction(text):\n",
+    "    \n",
+    "    # manipulate data into a format that we pass to our model\n",
+    "    text = text.lower().strip() #lower case\n",
+    "\n",
+    "    # Vectorise text and store in new dataframe. Sentence vector = average of word vectors\n",
+    "    text_vectors = tfidf.transform(list(text))\n",
+    "    print(text_vectors.shape)\n",
+    "    # Make topic predictions\n",
+    "    results = svc.predict_proba(text_vectors).squeeze().round(2)\n",
+    "    print(results.shape)\n",
+    "\n",
+    "    pred_prob = pd.DataFrame({'topic': labels, 'probability': results}).sort_values('probability', ascending=True)\n",
+    "\n",
+    "    # Make sentiment predictions\n",
+    "    text_vectors_sentiment = tfidf_sentiment.transform(list(text))\n",
+    "\n",
+    "    results_sentiment = svc_sentiment.predict_proba(text_vectors).squeeze().round(2)\n",
+    "    pred_prob_sentiment = pd.DataFrame({'sentiment': ['Negative', 'Positive'], 'probability': results_sentiment}).sort_values('probability', ascending=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "b940cb16-c287-4fef-accc-fa54f20c3864",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(5, 500)\n",
+      "(5, 11)\n"
+     ]
+    },
+    {
+     "ename": "ValueError",
+     "evalue": "Data must be 1-dimensional",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
+      "\u001b[1;32m<ipython-input-11-5105897e9757>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mget_single_prediction\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'hello'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
+      "\u001b[1;32m<ipython-input-10-f4ad9599dac2>\u001b[0m in \u001b[0;36mget_single_prediction\u001b[1;34m(text)\u001b[0m\n\u001b[0;32m     32\u001b[0m     \u001b[0mprint\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mresults\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     33\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 34\u001b[1;33m     \u001b[0mpred_prob\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mDataFrame\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m{\u001b[0m\u001b[1;34m'topic'\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mlabels\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'probability'\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mresults\u001b[0m\u001b[1;33m}\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msort_values\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'probability'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mascending\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mTrue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     35\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     36\u001b[0m     \u001b[1;31m# Make sentiment predictions\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mC:\\HA\\Python\\Anaconda\\lib\\site-packages\\pandas\\core\\frame.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, data, index, columns, dtype, copy)\u001b[0m\n\u001b[0;32m    527\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    528\u001b[0m         \u001b[1;32melif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdict\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 529\u001b[1;33m             \u001b[0mmgr\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0minit_dict\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcolumns\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mdtype\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    530\u001b[0m         \u001b[1;32melif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mma\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mMaskedArray\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    531\u001b[0m             \u001b[1;32mimport\u001b[0m \u001b[0mnumpy\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mma\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmrecords\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mmrecords\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mC:\\HA\\Python\\Anaconda\\lib\\site-packages\\pandas\\core\\internals\\construction.py\u001b[0m in \u001b[0;36minit_dict\u001b[1;34m(data, index, columns, dtype)\u001b[0m\n\u001b[0;32m    285\u001b[0m             \u001b[0marr\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mis_datetime64tz_dtype\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0marr\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32melse\u001b[0m \u001b[0marr\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcopy\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0marr\u001b[0m \u001b[1;32min\u001b[0m \u001b[0marrays\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    286\u001b[0m         ]\n\u001b[1;32m--> 287\u001b[1;33m     \u001b[1;32mreturn\u001b[0m \u001b[0marrays_to_mgr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0marrays\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdata_names\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcolumns\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mdtype\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    288\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    289\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mC:\\HA\\Python\\Anaconda\\lib\\site-packages\\pandas\\core\\internals\\construction.py\u001b[0m in \u001b[0;36marrays_to_mgr\u001b[1;34m(arrays, arr_names, index, columns, dtype, verify_integrity)\u001b[0m\n\u001b[0;32m     83\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     84\u001b[0m         \u001b[1;31m# don't force copy because getting jammed in an ndarray anyway\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 85\u001b[1;33m         \u001b[0marrays\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_homogenize\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0marrays\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     86\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     87\u001b[0m         \u001b[0mcolumns\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mensure_index\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mC:\\HA\\Python\\Anaconda\\lib\\site-packages\\pandas\\core\\internals\\construction.py\u001b[0m in \u001b[0;36m_homogenize\u001b[1;34m(data, index, dtype)\u001b[0m\n\u001b[0;32m    353\u001b[0m                     \u001b[0mval\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdict\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mval\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    354\u001b[0m                 \u001b[0mval\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlib\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfast_multiget\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mval\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0moindex\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_values\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdefault\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mnan\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 355\u001b[1;33m             val = sanitize_array(\n\u001b[0m\u001b[0;32m    356\u001b[0m                 \u001b[0mval\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mindex\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mdtype\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcopy\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mraise_cast_failure\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    357\u001b[0m             )\n",
+      "\u001b[1;32mC:\\HA\\Python\\Anaconda\\lib\\site-packages\\pandas\\core\\construction.py\u001b[0m in \u001b[0;36msanitize_array\u001b[1;34m(data, index, dtype, copy, raise_cast_failure)\u001b[0m\n\u001b[0;32m    527\u001b[0m     \u001b[1;32melif\u001b[0m \u001b[0msubarr\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mndim\u001b[0m \u001b[1;33m>\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    528\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mndarray\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 529\u001b[1;33m             \u001b[1;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"Data must be 1-dimensional\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    530\u001b[0m         \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    531\u001b[0m             \u001b[0msubarr\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcom\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0masarray_tuplesafe\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mdtype\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;31mValueError\u001b[0m: Data must be 1-dimensional"
+     ]
+    }
+   ],
+   "source": [
+    "get_single_prediction('hello')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1f68efcf-479d-41de-be1e-e94d00b58fab",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

utils.py

@@ -24,17 +24,17 @@ def get_single_prediction(text):
     # manipulate data into a format that we pass to our model
     text = text.lower().strip() #lower case
 
-    # Vectorise text and store in new dataframe. Sentence vector = average of word vectors
-    text_vectors = tfidf.transform(list(text))
-    print('check1')
+    # Vectorise text
+    text_vectors = tfidf.transform([text])
+
     # Make topic predictions
-    results = svc.predict_proba(text_vectors).squeeze().round(2)
-    print('check2')
+    results = svc.predict_proba(text_vectors.reshape()).squeeze().round(2)
+
     pred_prob = pd.DataFrame({'topic': labels, 'probability': results}).sort_values('probability', ascending=True)
-    print('check3')
+
     # Make sentiment predictions
-    text_vectors_sentiment = tfidf_sentiment.transform(list(text))
-    print('check4')
+    text_vectors_sentiment = tfidf_sentiment.transform([text])
+ 
     results_sentiment = svc_sentiment.predict_proba(text_vectors).squeeze().round(2)
     pred_prob_sentiment = pd.DataFrame({'sentiment': ['Negative', 'Positive'], 'probability': results_sentiment}).sort_values('probability', ascending=True)