Language Portuguese

app/language_detection.ipynb

@@ -302,16 +302,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 53,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "'English'"
+       "'Inglês'"
       ]
      },
-     "execution_count": 33,
+     "execution_count": 53,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -321,6 +321,9 @@
     "       'Greek', 'Hindi', 'Italian', 'Kannada', 'Malayalam', 'Portugeese',\n",
     "       'Russian', 'Spanish', 'Sweedish', 'Tamil', 'Turkish']\n",
     "\n",
+    "dict_por = {'Arabic': 'Árabe', 'Danish': 'Dinamarquês', 'Dutch': 'Holandês', 'English': 'Inglês', 'French': 'Francês', 'German': 'Alemão',\n",
+    "         'Greek': 'Grego', 'Hindi': 'Hindi', 'Italian': 'Italiano', 'Kannada': 'Kannada', 'Malayalam': 'Malaiala', 'Portugeese': 'Português',\n",
+    "            'Russian': 'Russo', 'Spanish': 'Espanhol', 'Sweedish': 'Sueco', 'Tamil': 'Tâmil', 'Turkish': 'Turco'}\n",
     "\n",
     "\n",
     "def predict_language(text):\n",
@@ -329,7 +332,7 @@
     "    text = text.lower()\n",
     "    text = cv.transform([text]).toarray()\n",
     "    pred = model.predict(text)\n",
-    "    return classes[pred[0]]\n",
+    "    return dict_por[classes[pred[0]]]\n",
     "\n",
     "\n",
     "predict_language('How are?')"
@@ -337,22 +340,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
+   "execution_count": 52,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'language': 'Portugeese'}\n"
+      "{'language': 'English'}\n"
      ]
     }
    ],
    "source": [
     "import requests\n",
     "\n",
-    "url = 'http://localhost:7860/predict'\n",
-    "text1 = 'Oi tudo bem, como voce vai?'\n",
+    "url = 'https://hudsonma-simpleapplicationdocker.hf.space/predict'\n",
+    "text1 = ' How are u bro?'\n",
     "\n",
     "response = requests.post(url, json={'text': text1})\n",
     "\n",
@@ -364,23 +367,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "<Response [500]>"
-      ]
-     },
-     "execution_count": 30,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "response"
-   ]
+   "outputs": [],
+   "source": []
   },
   {
    "cell_type": "code",
@@ -391,26 +381,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<style>#sk-container-id-2 {color: black;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MultinomialNB()</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MultinomialNB</label><div class=\"sk-toggleable__content\"><pre>MultinomialNB()</pre></div></div></div></div></div>"
-      ],
-      "text/plain": [
-       "MultinomialNB()"
-      ]
-     },
-     "execution_count": 39,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "model"
-   ]
+   "outputs": [],
+   "source": []
   },
   {
    "cell_type": "code",

app/model/model.py

@@ -5,7 +5,6 @@ from pathlib import Path
 from sklearn.feature_extraction.text import CountVectorizer
 
 cv = CountVectorizer(max_features=1500)
-__version__ = '01'
 
 BASE_DIR = Path(__file__).resolve(strict=True).parent
 
@@ -18,10 +17,14 @@ classes = ['Arabic', 'Danish', 'Dutch', 'English', 'French', 'German',
            'Greek', 'Hindi', 'Italian', 'Kannada', 'Malayalam', 'Portugeese',
            'Russian', 'Spanish', 'Sweedish', 'Tamil', 'Turkish']
 
+dict_por = {'Arabic': 'Árabe', 'Danish': 'Dinamarquês', 'Dutch': 'Holandês', 'English': 'Inglês', 'French': 'Francês', 'German': 'Alemão',
+         'Greek': 'Grego', 'Hindi': 'Hindi', 'Italian': 'Italiano', 'Kannada': 'Kannada', 'Malayalam': 'Malaiala', 'Portugeese': 'Português',
+            'Russian': 'Russo', 'Spanish': 'Espanhol', 'Sweedish': 'Sueco', 'Tamil': 'Tâmil', 'Turkish': 'Turco'}
+
 def predict_language(text):
     text = re.sub(r'[!@#$(),\n"%^*?\:;~`0-9]', ' ', text)
     text = re.sub(r'[\[\]]', ' ', text)
     text = text.lower()
     text = vocab.transform([text]).toarray() 
     pred = model.predict(text)
-    return classes[pred[0]]
+    return dict_por[classes[pred[0]]]