Upload app.py
Browse files
app.py
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from fastapi import FastAPI
|
| 2 |
+
from pydantic import BaseModel
|
| 3 |
+
import joblib
|
| 4 |
+
|
| 5 |
+
|
| 6 |
+
model = joblib.load("model.joblib")
|
| 7 |
+
tfidf_vectorizer = joblib.load("tfidf_vectorizer.joblib")
|
| 8 |
+
|
| 9 |
+
|
| 10 |
+
class TextInput(BaseModel):
|
| 11 |
+
text: str
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
app = FastAPI()
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
@app.post("/predict")
|
| 18 |
+
def predict(input: TextInput):
|
| 19 |
+
|
| 20 |
+
processed_text = preprocess_text(input.text)
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
text_tfidf = tfidf_vectorizer.transform([processed_text])
|
| 24 |
+
|
| 25 |
+
prediction = model.predict(text_tfidf)
|
| 26 |
+
|
| 27 |
+
return {"prediction": "Spam" if int(prediction[0]) == 0 else "Ham"}
|
| 28 |
+
|
| 29 |
+
def preprocess_text(text):
|
| 30 |
+
import re
|
| 31 |
+
from nltk.stem import WordNetLemmatizer
|
| 32 |
+
from nltk.corpus import stopwords
|
| 33 |
+
lemmatizer = WordNetLemmatizer()
|
| 34 |
+
stop_words = set(stopwords.words('english'))
|
| 35 |
+
|
| 36 |
+
text = re.sub('[^a-zA-Z]', ' ', text)
|
| 37 |
+
text = text.lower()
|
| 38 |
+
words = text.split()
|
| 39 |
+
words = [lemmatizer.lemmatize(word) for word in words if word not in stop_words]
|
| 40 |
+
return ' '.join(words)
|