pandas dataframe to tensorflow input

Question

i want to use a pandas dataset as an input to a neural net.

my neural net model is:

def build_model():
    model = Sequential()
    model.add(Dense(128, activation = "relu"))
    model.add(Dropout(0.2))
    model.add(Dense(64, activation = "relu"))
    model.add(Dropout(0.1))
    model.add(Dense(32, activation = "softmax"))

    model.compile(
        optimizer='adam',
        loss=['binary_crossentropy'],
        metrics=['accuracy']
    )
    return model

tensorboard = TensorBoard(log_dir=f"logs/{time.time()}", histogram_freq=1)

model = build_model()

history = model.fit(
    x_train,
    y_train,
    epochs=5,
    batch_size=32,
    validation_data=(
        x_val,
        y_val
    ),
    callbacks=[
        tensorboard
    ]
)

and i pass my dataframe as input as such:

y_val, x_val, y_train, x_train = test_data.drop(['gender', 
       'comorbidities_count', 'comorbidities_significant_count',
       'medication_count'],axis=1),test_data.drop(['fried'],axis=1),training_data.drop([ 'gender', 'comorbidities_count', 'comorbidities_significant_count',
       'medication_count'],axis=1),training_data.drop(['fried'],axis=1)

but i get this error:

ValueError: Please provide as model inputs either a single array or a list of arrays.

Does anyone know hot to turn this dataframe into an array so i can feed it? Or is there some other issue i am not in knowledge of?

SdahlSean · Accepted Answer · 2019-12-28 15:46:31Z

1

Use

y_val, x_val, y_train, x_train = test_data.drop(['gender', 
       'comorbidities_count', 'comorbidities_significant_count',
       'medication_count'],axis=1).to_numpy().astype(np.float32) ,test_data.drop(['fried'],axis=1).to_numpy().astype(np.float32) ,training_data.drop([ 'gender', 'comorbidities_count', 'comorbidities_significant_count',
       'medication_count'],axis=1).to_numpy().astype(np.float32) ,training_data.drop(['fried'],axis=1).to_numpy().astype(np.float32)

The .to_numpy() function of a pd dataframe turns it into a numpy array.

edited Dec 28, 2019 at 15:46

answered Dec 28, 2019 at 15:36

SdahlSean

5833 silver badges14 bronze badges

Sign up to request clarification or add additional context in comments.

13 Comments

Tzikos Over a year ago

now i get this: ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type int).

SdahlSean Over a year ago

add .astype(np.float32) after every array. this will convert the arrays to float arrays

Tzikos Over a year ago

sorry but now i get: NotFoundError: Failed to create a directory: logs/1577540868.3478014\train; No such file or directory [Op:CreateSummaryFileWriter]

SdahlSean Over a year ago

this is caused by the tensorboard = TensorBoard(log_dir=f"logs/{time.time()}", histogram_freq=1) line and not related to this issue

SdahlSean Over a year ago

try to use log_dir="logs/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S") as your log dir. For that you have to import datetime.

|

Collectives™ on Stack Overflow

pandas dataframe to tensorflow input

1 Answer 1

13 Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

13 Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related