Python BankNote 예제들

예제 #1

파일: app.py 프로젝트: yogeshsangtani/Ship-Classification

def predict_banknote(data: BankNote):
    data = data.dict()
    variance = data['variance']
    skewness = data['skewness']
    curtosis = data['curtosis']
    entropy = data['entropy']
    prediction = classifier.predict([[variance, skewness, curtosis, entropy]])
    if (prediction[0] > 0.5):
        prediction = "Fake note"
    else:
        prediction = "Its a Bank note"
    return {'prediction': prediction}

예제 #2

파일: app.py 프로젝트: rahulbordoloi/FastAPI

async def predict(data: BankNote):
    data = data.dict()
    variance = data['variance']
    skewness = data['skewness']
    curtosis = data['curtosis']
    entropy = data['entropy']
    predictedValue = model.predict_proba(
        [[variance, skewness, curtosis, entropy]])[:, 1][0]
    if predictedValue < 0.5:
        prediction = "Fake Note"
    else:
        prediction = "Authentic Bank Note"
    return {'prediction': prediction}

예제 #3

파일: banknote_authetication_prediction_model_FastAPI.py 프로젝트: amritendugithub/BankNote-Prediction-FastAPI

def predict_banknote(data:BankNote):
    data = data.dict()
    print(data)
    variance = data['variance']
    skewness = data['skewness']
    curtosis = data['curtosis']
    entropy = data['entropy']
    print(classifier.predict([[variance,skewness,curtosis,entropy]]))
    prediction = classifier.predict([[variance,skewness,curtosis,entropy]])
    if(prediction[0]>0.5):
        prediction = 'Fake Note'
    else:
        prediction = 'Genuine Bank Note'
    return {'prediction':prediction}

예제 #4

파일: main.py 프로젝트: pkiran76/Bank_Notes_Auth

def pred_bank(
    data: BankNote
):  #capture the i/p features needed from the class object and assign to an object data
    data = data.dict()
    print(data)
    variance = data["variance"]
    print(variance)
    skewness = data["skewness"]
    curtosis = data['curtosis']
    entropy = data["entropy"]
    print(classifier.predict([[variance, skewness, curtosis, entropy]]))
    prediction = classifier.predict([[variance, skewness, curtosis, entropy]])
    if prediction[0] > 0.5:
        prediction = "Fake_Note"
    else:
        prediction = "Genuine Note"
    return {"prediction": prediction}