Skip to content
TheChatArchiveThe Chat Archive
gpt-4-0125-preview· OpenAIAi2 WildChat-4.8M (AI2)

code: %% from sklearn.preprocessing import StandardScaler import pandas as pd import…

  1. User

    code:

    %%

    from sklearn.preprocessing import StandardScaler import pandas as pd import numpy as np from tensorflow import keras import joblib from tensorflow.keras.models import Sequential from tensorflow.keras.layers import LSTM,Dense,Dropout import os

    %%

    csv_directory = r"C:\Users\arisa\Desktop\day_spot_summary" csv_files = [file for file in os.listdir(csv_directory) if file.endswith('.csv')]

    %%

    from tensorflow.keras.layers import BatchNormalization def build_lstm_model(input_shape): model = Sequential([ LSTM(2716, activation='tanh', input_shape=input_shape, return_sequences=True), # Adjusted for LSTM Dropout(0.20), BatchNormalization(), # LSTM(2716, activation='tanh', return_sequences=False), # Additional LSTM layer # Dropout(0.10), Dense(2716, activation='relu'), Dropout(0.15), Dense(256, activation='relu'), Dropout(0.10), Dense(128, activation='relu'), Dense(64, activation='relu'), Dense(32, activation='relu'), Dense(12), ])

    model.compile(optimizer='adam',
                  loss='mse',  # Use Mean Squared Error for regression
                  metrics=['mae'])  # Mean Absolute Error as an additional metric
    return model
    

    %%

    x_scaler_loaded = joblib.load('nn_x_minmaxscaler.sav') y_scaler_loaded = joblib.load('nn_y_minmaxscaler.sav')

    %%

    def data_generator_lstm( n_steps,x_scaler,y_scaler):

    while True:
        for csv_file in csv_files:
            # Read the CSV file
            file_path = os.path.join(csv_directory, csv_file)
            chunk = pd.read_csv(file_path)
        
    
            feature_data = chunk.drop([
                'y_High_1d', 'y_Low_1d', 'y_Priority_1d',
                 'y_High_2d', 'y_Low_2d', 'y_Priority_2d',
                  'y_High_3d', 'y_Low_3d', 'y_Priority_3d',
                   'y_High_5d', 'y_Low_5d', 'y_Priority_5d'], axis=1)
            target_data = chunk[[
                'y_High_1d','y_Low_1d', 'y_Priority_1d',
                 'y_High_2d', 'y_Low_2d', 'y_Priority_2d',
                  'y_High_3d', 'y_Low_3d', 'y_Priority_3d',
                   'y_High_5d', 'y_Low_5d', 'y_Priority_5d'
                   ]]
            
            feature_data_scaled = pd.DataFrame(x_scaler.transform(feature_data), columns=feature_data.columns)
            # Assuming target_data also needs to be scaled, apply scaler separately
            target_data_scaled = pd.DataFrame(y_scaler.transform(target_data), columns=target_data.columns)
    
            # ensuring end_ix does not go out of feature_data_scaled’s bounds
            num_samples = (len(feature_data_scaled) - n_steps) // 32
            for i in range(num_samples):
                start_ix = i * 32
                end_ix = start_ix + n_steps
    
                X = feature_data_scaled[start_ix:end_ix]
                # using .iloc to avoid KeyError, and selecting the corresponding outputs
                y = target_data_scaled.iloc[start_ix:end_ix].iloc[-1]
    
                yield X.reshape((1, n_steps, -1)), y.reshape((1, -1))
            
           
    

    model = build_lstm_model((30, 2716))

    model.summary()

    %%

    import warnings warnings.filterwarnings(action='ignore', message='X has feature names, but MinMaxScaler was fitted without feature names') train_generator = data_generator_lstm(30,x_scaler_loaded,y_scaler_loaded)

    Update total_samples, train_samples, and val_samples according to your dataset after transformations

    model.fit( train_generator, steps_per_epoch=50, epochs=75, # Add validation_data if you have a validation generator )

    error: { "name": "AttributeError", "message": "'DataFrame' object has no attribute 'reshape'", "stack": "--------------------------------------------------------------------------- AttributeError Traceback (most recent call last) ~\AppData\Local\Temp\ipykernel_17980\261283929.py in ?() ----> 7 import warnings 8 warnings.filterwarnings(action='ignore', message='X has feature names, but MinMaxScaler was fitted without feature names') 9 train_generator = data_generator_lstm(30,x_scaler_loaded,y_scaler_loaded) 10

    c:\Users\arisa\.conda\envs\tf\lib\site-packages\keras\utils\traceback_utils.py in ?(*args, **kwargs) 68 # To get the full stack trace, call: 69 # tf.debugging.disable_traceback_filtering() 70 raise e.with_traceback(filtered_tb) from None 71 finally: ---> 72 del filtered_tb

    ~\AppData\Local\Temp\ipykernel_17980\994707971.py in ?(n_steps, x_scaler, y_scaler) 32 X = feature_data_scaled[start_ix:end_ix] 33 # using .iloc to avoid KeyError, and selecting the corresponding outputs 34 y = target_data_scaled.iloc[start_ix:end_ix].iloc[-1] 35 ---> 36 yield X.reshape((1, n_steps, -1)), y.reshape((1, -1)) 37 38 # Prepare sequences for features and targets 39 # X, y = [], []

    c:\Users\arisa\.conda\envs\tf\lib\site-packages\pandas\core\generic.py in ?(self, name) 6295 and name not in self._accessors 6296 and self._info_axis._can_hold_identifiers_and_holds_name(name) 6297 ): 6298 return self[name] -> 6299 return object.getattribute(self, name)

    AttributeError: 'DataFrame' object has no attribute 'reshape'" }

  2. Assistant

    The error 'DataFrame' object has no attribute 'reshape' indicates that you are trying to use the reshape method on a Pandas DataFrame, which is not supported. The reshape method is a NumPy array operation, and while Pandas is built on top of NumPy, DataFrame objects do not directly expose this method. To fix this error, you will need to convert the DataFrame objects X and y to NumPy arrays before calling reshape.

    Here is how you can modify the lines causing the error:

    yield X.reshape((1, n_steps, -1)), y.reshape((1, -1))
    

    You should convert X and y to NumPy arrays using .values (or .to_numpy() which is more explicit and recommended) before reshaping:

    yield X.values.reshape((1, n_steps, -1)), y.values.reshape((1, -1))
    

    Or using .to_numpy():

    yield X.to_numpy().reshape((1, n_steps, -1)), y.to_numpy().reshape((1, -1))
    

    So, your modified generator function part would look something like this:

    for i in range(num_samples):
        start_ix = i * 32
        end_ix = start_ix + n_steps
    
        X = feature_data_scaled[start_ix:end_ix]
        y = target_data_scaled.iloc[start_ix:end_ix].iloc[-1]
    
        # Convert to NumPy and then reshape
        yield X.to_numpy().reshape((1, n_steps, -1)), y.to_numpy().reshape((1, -1))
    

    With this change, your code should work, because you're now supplying numpy.ndarray objects to the reshape function, which supports this operation.

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.