Resolve problems

app/language_detection.ipynb

@@ -14,7 +14,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -51,7 +51,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -60,7 +60,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -70,7 +70,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -103,7 +103,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -117,7 +117,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -128,7 +128,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -140,7 +140,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [
     {
@@ -152,7 +152,7 @@
        "MultinomialNB()"
       ]
      },
-     "execution_count": 43,
+     "execution_count": 18,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -166,7 +166,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -175,7 +175,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -192,12 +192,13 @@
     "ac = accuracy_score(y_test, y_predict)\n",
     "cm = confusion_matrix(y_test, y_predict)\n",
     "cr = classification_report(y_test, y_predict)\n",
+    "\n",
     "print('Accuracy is:', ac)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -237,7 +238,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -262,20 +263,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": 49,
    "metadata": {},
    "outputs": [],
    "source": [
-    "# # Save the model\n",
-    "# import pickle\n",
+    "# Salvar o modelo e o vocabulário\n",
+    "import pickle\n",
     "\n",
-    "# with open('trained-01.pkl', 'wb') as file:\n",
-    "#     pickle.dump(model, file)\n"
+    "with open('filename.pkl', 'wb') as f:\n",
+    "    pickle.dump({'model': model, 'vocab': cv}, f)\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 48,
    "metadata": {},
    "outputs": [
     {
@@ -284,7 +285,7 @@
        "array(['Portugeese', 'English'], dtype=object)"
       ]
      },
-     "execution_count": 46,
+     "execution_count": 48,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -301,16 +302,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
+   "execution_count": 33,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "'Portugeese'"
+       "'English'"
       ]
      },
-     "execution_count": 50,
+     "execution_count": 33,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -331,28 +332,39 @@
     "    return classes[pred[0]]\n",
     "\n",
     "\n",
-    "predict_language('Oi tudo bem?')"
+    "predict_language('How are?')"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 50,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'language': 'Portugeese'}\n"
+     ]
+    }
+   ],
    "source": [
     "import requests\n",
-    "#  teste api local \n",
-    "url = 'http://localhost:8080/predict'\n",
     "\n",
+    "url = 'http://localhost:7860/predict'\n",
     "text1 = 'Oi tudo bem, como voce vai?'\n",
     "\n",
     "response = requests.post(url, json={'text': text1})\n",
-    "\n"
+    "\n",
+    "if response.status_code == 200:\n",
+    "    print(response.json())\n",
+    "else:\n",
+    "    print(f\"Error: {response.status_code}, Detail: {response.text}\")\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 30,
    "metadata": {},
    "outputs": [
     {
@@ -361,7 +373,7 @@
        "<Response [500]>"
       ]
      },
-     "execution_count": 31,
+     "execution_count": 30,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -370,6 +382,36 @@
     "response"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "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"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,

app/main.py

@@ -1,22 +1,17 @@
-from fastapi import FastAPI,HTTPException
-from app.model.model import predict_language
-from app.model.model import __version__
+from fastapi import FastAPI, HTTPException
+from app.model.model import predict_language, __version__
 from app.schemas import Prediction, TextIn
 
-
 app = FastAPI()
 
-
 @app.get("/")
 def home():
     return {"message": "Ok", "model_version": __version__}
 
-
 @app.post("/predict", response_model=Prediction)
 def predict(payload: TextIn):
     try:
         language = predict_language(payload.text)
         return {"language": language}
     except Exception as e:
-        raise HTTPException(status_code=500, detail="Internal Server Error")
-    
+        raise HTTPException(status_code=400, detail=str(e))

app/model/{trained-01.pkl → filename.pkl}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c65a0d9fd8daa233db3aad9bcff1703ab1441e2bded657cc11b6cbea5daa3da
-size 9468690
+oid sha256:63f7dc5c0ca806fda6983b96a7721a8add27e09c140c41d1a339b3fb4d363fb2
+size 9993593

app/model/model.py

@@ -1,27 +1,27 @@
+# app/model/model.py
 import pickle
 import re
 from pathlib import Path
 from sklearn.feature_extraction.text import CountVectorizer
-cv = CountVectorizer(max_features = 1500)
-__version__ = '01'
 
+cv = CountVectorizer(max_features=1500)
+__version__ = '01'
 
 BASE_DIR = Path(__file__).resolve(strict=True).parent
 
+with open(f"{BASE_DIR}/filename.pkl", "rb") as f:
+    data = pickle.load(f)
+    model = data['model']
+    vocab = data['vocab']
 
-with open(f"{BASE_DIR}/trained-{__version__}.pkl", "rb") as f:
-    model = pickle.load(f)
-    
 classes = ['Arabic', 'Danish', 'Dutch', 'English', 'French', 'German',
-       'Greek', 'Hindi', 'Italian', 'Kannada', 'Malayalam', 'Portugeese',
-       'Russian', 'Spanish', 'Sweedish', 'Tamil', 'Turkish']
-
-
+           'Greek', 'Hindi', 'Italian', 'Kannada', 'Malayalam', 'Portugeese',
+           'Russian', 'Spanish', 'Sweedish', 'Tamil', 'Turkish']
 
 def predict_language(text):
     text = re.sub(r'[!@#$(),\n"%^*?\:;~`0-9]', ' ', text)
     text = re.sub(r'[\[\]]', ' ', text)
     text = text.lower()
-    text = cv.transform([text]).toarray()
-    pred = model.predict([text])
-    return classes[pred[0]]
+    text = vocab.transform([text]).toarray() 
+    pred = model.predict(text)
+    return classes[pred[0]]

app/schemas.py

@@ -1,9 +1,7 @@
 from pydantic import BaseModel
 
-
 class TextIn(BaseModel):
     text: str
-    
-    
+
 class Prediction(BaseModel):
     language: str