I am trying to implement the following example code, but the lesson I am referencing isn't quite clear. I know I am loading in data as a CSV file, but I am not sure if the dataframe.label was supposed to return the row labels or column labels. Additionally, I cannot figure out how to replace it with working code. I have tried using iloc, .columns, .to_numpy(), .as_matrix() all to no avail, and part of my struggle is determining what exactly .label did at one point (or was supposed to do). Here is the lesson I am referencing: https://www.kaggle.com/dansbecker/deep-learning-from-scratch and here is the code: def data_prep(raw): out_y = keras.utils.to_categorical(raw.label, num_classes) num_images = raw.shape[0] x_as_array = raw.values[:,1:] x_shaped_array = x_as_array.reshape(num_images, img_rows, img_cols, 1) out_x = x_shaped_array / 255 return out_x, out_y train_file = "../input/digit-recognizer/train.csv" raw_data = pd.read_csv(train_file) x, y = data_prep(raw_data) The original error I got was: AttributeError: 'DataFrame' object has no attribute 'label' Can anyone shed some light into this? Continue reading...
