TensorFlow 2.0 中的神经网络问题

Question

import tensorflow as tf
import pandas as pd
import numpy as np
import matplotlib as plt
from sklearn.model_selection import train_test_split
from tensorflow import keras
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from sklearn.preprocessing import StandardScaler
import functools

LABEL_COLUMN = 'Endstage'
LABELS = [1, 2, 3, 4]
x = pd.read_csv('HCVnew.csv', index_col=False)


def get_dataset(file_path, **kwargs):
  dataset = tf.data.experimental.make_csv_dataset(
      file_path,
      batch_size=35, # Artificially small to make examples easier to show.
      label_name=LABEL_COLUMN,
      na_value="?",
      num_epochs=1,
      ignore_errors=True,
      **kwargs)
  return dataset

SELECT_COLUMNS = ["Alter", "Gender", "BMI", "Fever", "Nausea", "Fatigue",
                  "WBC", "RBC", "HGB", "Plat", "AST1", "ALT1", "ALT4", "ALT12", "ALT24", "ALT36", "ALT48", "ALT24w",
                  "RNABase", "RNA4", "Baseline", "Endstage"]

DEFAULTS = [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0,
            0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0]
temp_dataset = get_dataset("HCVnew.csv",
                           select_columns=SELECT_COLUMNS,
                           column_defaults=DEFAULTS)
def pack(features, label):
  return tf.stack(list(features.values()), axis=-1), label

packed_dataset = temp_dataset.map(pack)

"""
for features, labels in packed_dataset.take(1):
  print(features.numpy())
  print()
  print(labels.numpy())
"""

NUMERIC_FEATURES = ["Alter", "Gender","BMI", "Fever", "Nausea", "Fatigue",
                  "WBC", "RBC", "HGB", "Plat", "AST1", "ALT1", "ALT4", "ALT12", "ALT24", "ALT36", "ALT48", "ALT24w",
                  "RNABase", "RNA4", "Baseline", "Endstage"]


desc = pd.read_csv("HCVnew.csv")[NUMERIC_FEATURES].describe()

MEAN = np.array(desc.T['mean'])
STD = np.array(desc.T['std'])

def normalize_numeric_data(data, mean, std):
  # Center the data
  return (data-mean)/std



# See what you just created.
raw_train_data = get_dataset("HCVnew.csv")
raw_test_data = get_dataset("HCVnew.csv")

class PackNumericFeatures(object):
  def __init__(self, names):
    self.names = names

  def __call__(self, features, labels):
    numeric_freatures = [features.pop(name) for name in self.names]
    numeric_features = [tf.cast(feat, tf.float32) for feat in numeric_freatures]
    numeric_features = tf.stack(numeric_features, axis=-1)
    features['numeric'] = numeric_features

    return features, labels

NUMERIC_FEATURES = ["Alter", "Gender","BMI", "Fever", "Nausea", "Fatigue",
                  "WBC", "RBC", "HGB", "Plat", "AST1", "ALT1", "ALT4", "ALT12", "ALT24", "ALT36", "ALT48", "ALT24w",
                  "RNABase", "RNA4", "Baseline", "Endstage"]

packed_train_data = raw_train_data.map(
    PackNumericFeatures(NUMERIC_FEATURES))

packed_test_data = raw_test_data.map(
    PackNumericFeatures(NUMERIC_FEATURES))




normalizer = functools.partial(normalize_numeric_data, mean=MEAN, std=STD)

numeric_column = tf.feature_column.numeric_column('numeric', normalizer_fn=normalizer, shape=[len(NUMERIC_FEATURES)])
numeric_columns = [numeric_column]

numeric_layer = tf.keras.layers.DenseFeatures(numeric_columns)
preprocessing_layer = tf.keras.layers.DenseFeatures(numeric_columns)



#———————————————————————MODEL———————————————————————————————————————————————————————————————————————————————————————————

model = tf.keras.Sequential([
  preprocessing_layer,
  tf.keras.layers.Dense(128, activation='relu'),
  tf.keras.layers.Dense(128, activation='relu'),
  tf.keras.layers.Dense(1, activation='sigmoid'),
])

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

data_x = get_dataset("HCVnew.csv")

train_data = data_x.shuffle(500)

model.fit(train_data, epochs=20)

Hello, I'm trying to build a neural network that can predict Hepatitis C based on a csv file containing patient information and I can't fix the error... I'm getting the error: KeyError 'Endstage', whereas Endstage is the csv column that contains the corresponding values (between 1 and 4) and serves as the label column. If someone has an idea that could fix my problem then please tell me. Thanks a lot for your help!

Answer 1

That's because Endstage is your label column and the framework does a favour to you by removing (popping) it out of your dataset. Otherwise your training data set would have also the target class, rendering it useless.

Remove it from NUMERIC_FEATURES and any other place that makes it into your training set features.

[EDIT]

The OP asked in the follow-up question (in the comments) why, after fixing the initial problem, he's getting an error:

ValueError: Feature numeric is not in features dictionary

By the looks of it, feature called numeric is produced via call to PackNumericFeatures . The latter is used to create packed_train_data and packed_test_data , but these are never used. Yet this line:

numeric_column = tf.feature_column.numeric_column('numeric', normalizer_fn=normalizer, shape=[len(NUMERIC_FEATURES)])

assumes the data is there - hence the error.