Python model.predict方法代码示例

# 需要导入模块: import model [as 别名]
# 或者: from model import predict [as 别名]
def invocations():
    """
    A flask handler for predictions

    Returns:
        A flask response with either a prediction or an error
    """

    # pre-process request
    data = flask.request.get_data()  # read data

    # make predictions
    try:
        out = predict(data, ctx)  # extract prediction
        logging.info("Predicted digit: {}".format(out))
        return flask.jsonify(result=out)

    except Exception as ex:
        logging.error(ex)
        return flask.Response(response='Error while processing the request',
                              status=500,
                              mimetype='text/plain') 

# 需要导入模块: import model [as 别名]
# 或者: from model import predict [as 别名]
def invocations():
    """
    A flask handler for predictions

    Returns:
        A flask response with either a prediction or an error
    """

    # pre-process request
    data = flask.request.get_json()  # read data

    # make predictions
    try:
        out = predict(data, ctx)  # extract prediction
        logging.info("Predict: {}".format(out))
        return flask.jsonify(result=out)

    except Exception as ex:
        logging.error(ex)
        return flask.Response(response='Error while processing the request',
                              status=500,
                              mimetype='text/plain') 

# 需要导入模块: import model [as 别名]
# 或者: from model import predict [as 别名]
def predict(data: ModelData) -> str:
    """
    Pass the request data as ModelData object,
    as this can be customised in the model.py file to adapt based
    on deployed model to make predictions

    Parameters:
      data: Parse the request body data based on your model schema and
        pass this to predict method to make prediction
    """
    return model.predict(data) 

# 需要导入模块: import model [as 别名]
# 或者: from model import predict [as 别名]
def feedback(data: FeedbackData) -> str:
    """
    Pass the request data as FeedbackData object,
    as this can be customised in the model.py file to adapt based
    on deployed model to make predictions

    Parameters:
      data: Parse the request body data based on your model schema and
        pass this to predict method to make prediction
    """
    return model.feedback(data)

# Load our pre trained model 

# 需要导入模块: import model [as 别名]
# 或者: from model import predict [as 别名]
def RF(X, y, X_ind, y_ind, is_reg=False):
    """Cross Validation and independent set test for Random Forest model

    Arguments:
        X (ndarray): Feature data of training and validation set for cross-validation.
                     m X n matrix, m is the No. of samples, n is the No. of fetures
        y (ndarray): Label data of training and validation set for cross-validation.
                     m-D vector, and m is the No. of samples.
        X_ind (ndarray): Feature data of independent test set for independent test.
                         It has the similar data structure as X.
        y_ind (ndarray): Feature data of independent set for for independent test.
                         It has the similar data structure as y
        out (str): The file path for saving the result data.
        is_reg (bool, optional): define the model for regression (True) or classification (False) (Default: False)

    Returns:
         cvs (ndarray): cross-validation results. The shape is (m, ), m is the No. of samples.
         inds (ndarray): independent test results. It has similar data structure as cvs.
        """
    if is_reg:
        folds = KFold(5).split(X)
        alg = RandomForestRegressor
    else:
        folds = StratifiedKFold(5).split(X, y)
        alg = RandomForestClassifier
    cvs = np.zeros(y.shape)
    inds = np.zeros(y_ind.shape)
    for i, (trained, valided) in enumerate(folds):
        model = alg(n_estimators=500, n_jobs=1)
        model.fit(X[trained], y[trained])
        if is_reg:
            cvs[valided] = model.predict(X[valided])
            inds += model.predict(X_ind)
        else:
            cvs[valided] = model.predict_proba(X[valided])[:, 1]
            inds += model.predict_proba(X_ind)[:, 1]
    return cvs, inds / 5 

# 需要导入模块: import model [as 别名]
# 或者: from model import predict [as 别名]
def SVM(X, y, X_ind, y_ind, is_reg=False):
    """Cross Validation and independent set test for Support Vector Machine (SVM)

    Arguments:
        X (ndarray): Feature data of training and validation set for cross-validation.
                     m X n matrix, m is the No. of samples, n is the No. of fetures
        y (ndarray): Label data of training and validation set for cross-validation.
                     m-D vector, and m is the No. of samples.
        X_ind (ndarray): Feature data of independent test set for independent test.
                         It has the similar data structure as X.
        y_ind (ndarray): Feature data of independent set for for independent test.
                         It has the similar data structure as y
        out (str): The file path for saving the result data.
        is_reg (bool, optional): define the model for regression (True) or classification (False) (Default: False)

    Returns:
         cvs (ndarray): cross-validation results. The shape is (m, ), m is the No. of samples.
         inds (ndarray): independent test results. It has similar data structure as cvs.
    """
    if is_reg:
        folds = KFold(5).split(X)
        model = SVR()
    else:
        folds = StratifiedKFold(5).split(X, y)
        model = SVC(probability=True)
    cvs = np.zeros(y.shape)
    inds = np.zeros(y_ind.shape)
    gs = GridSearchCV(model, {'C': 2.0 ** np.array([-5, 15]), 'gamma': 2.0 ** np.array([-15, 5])}, n_jobs=5)
    gs.fit(X, y)
    params = gs.best_params_
    print(params)
    for i, (trained, valided) in enumerate(folds):
        model = SVC(probability=True, C=params['C'], gamma=params['gamma'])
        model.fit(X[trained], y[trained])
        if is_reg:
            cvs[valided] = model.predict(X[valided])
            inds += model.predict(X_ind)
        else:
            cvs[valided] = model.predict_proba(X[valided])[:, 1]
            inds += model.predict_proba(X_ind)[:, 1]
    return cvs, inds / 5 

# 需要导入模块: import model [as 别名]
# 或者: from model import predict [as 别名]
def KNN(X, y, X_ind, y_ind, is_reg=False):
    """Cross Validation and independent set test for KNN.

    Arguments:
        X (ndarray): Feature data of training and validation set for cross-validation.
                     m X n matrix, m is the No. of samples, n is the No. of fetures
        y (ndarray): Label data of training and validation set for cross-validation.
                     m-D vector, and m is the No. of samples.
        X_ind (ndarray): Feature data of independent test set for independent test.
                         It has the similar data structure as X.
        y_ind (ndarray): Feature data of independent set for for independent test.
                         It has the similar data structure as y
        out (str): The file path for saving the result data.
        is_reg (bool, optional): define the model for regression (True) or classification (False) (Default: False)

    Returns:
         cvs (ndarray): cross-validation results. The shape is (m, ), m is the No. of samples.
         inds (ndarray): independent test results. It has similar data structure as cvs.
    """
    if is_reg:
        folds = KFold(5).split(X)
        alg = KNeighborsRegressor
    else:
        folds = StratifiedKFold(5).split(X, y)
        alg = KNeighborsClassifier
    cvs = np.zeros(y.shape)
    inds = np.zeros(y_ind.shape)
    for i, (trained, valided) in enumerate(folds):
        model = alg(n_jobs=1)
        model.fit(X[trained], y[trained])
        if is_reg:
            cvs[valided] = model.predict(X[valided])
            inds += model.predict(X_ind)
        else:
            cvs[valided] = model.predict_proba(X[valided])[:, 1]
            inds += model.predict_proba(X_ind)[:, 1]
    return cvs, inds / 5 

# 需要导入模块: import model [as 别名]
# 或者: from model import predict [as 别名]
def DNN(X, y, X_ind, y_ind, out, is_reg=False):
    """Cross Validation and independent set test for fully connected deep neural network

    Arguments:
        X (ndarray): Feature data of training and validation set for cross-validation.
                     m X n matrix, m is the No. of samples, n is the No. of fetures
        y (ndarray): Label data of training and validation set for cross-validation.
                     m X t matrix if it is for multi-task model,
                     m is the No. of samples, n is the No. of tasks or classes;
                     m-D vector if it is only for single task model, and m is the No. of samples.
        X_ind (ndarray): Feature data of independent test set for independent test.
                         It has the similar data structure as X.
        y_ind (ndarray): Feature data of independent set for for independent test.
                         It has the similar data structure as y
        out (str): The file path for saving the result data.
        is_reg (bool, optional): define the model for regression (True) or classification (False) (Default: False)

    Returns:
         cvs (ndarray): cross-validation results. If it is single task, the shape is (m, ),
                        m is the No. of samples, it contains real label and probability value;
                        if it is multi-task, the shape is m X n, n is the No. of tasks.
         inds (ndarray): independent test results. It has similar data structure as cvs.
    """
    if 'mtqsar' in out or is_reg:
        folds = KFold(5).split(X)
        NET = model.MTFullyConnected
    else:
        folds = StratifiedKFold(5).split(X, y[:, 0])
        NET = model.STFullyConnected
    indep_set = TensorDataset(T.Tensor(X_ind), T.Tensor(y_ind))
    indep_loader = DataLoader(indep_set, batch_size=BATCH_SIZE)
    cvs = np.zeros(y.shape)
    inds = np.zeros(y_ind.shape)
    for i, (trained, valided) in enumerate(folds):
        train_set = TensorDataset(T.Tensor(X[trained]), T.Tensor(y[trained]))
        train_loader = DataLoader(train_set, batch_size=BATCH_SIZE)
        valid_set = TensorDataset(T.Tensor(X[valided]), T.Tensor(y[valided]))
        valid_loader = DataLoader(valid_set, batch_size=BATCH_SIZE)
        net = NET(X.shape[1], y.shape[1], is_reg=is_reg)
        net.fit(train_loader, valid_loader, out='%s_%d' % (out, i), epochs=N_EPOCH, lr=LR)
        cvs[valided] = net.predict(valid_loader)
        inds += net.predict(indep_loader)
    cv, ind = y == y, y_ind == y_ind
    return cvs[cv], inds[ind] / 5