[DL] Att01

Author

김보람

Published

November 13, 2023

해당 강의노트는 전북대학교 김광수교수님 2023-2 고급딥러닝 자료임

## https://www.tensorflow.org/tutorials/keras/regression?hl=ko ##

import pathlib
import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns
import numpy as np
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers

print(tf.__version__)
2.14.0
dataset_path = keras.utils.get_file("auto-mpg.data", "http://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data")
dataset_path
'/root/.keras/datasets/auto-mpg.data'
column_names = ['MPG','Cylinders','Displacement','Horsepower','Weight',
                'Acceleration', 'Model Year', 'Origin']
raw_dataset = pd.read_csv(dataset_path, names=column_names,
                      na_values = "?", comment='\t',
                      sep=" ", skipinitialspace=True)

dataset = raw_dataset.copy()
dataset.tail()
MPG Cylinders Displacement Horsepower Weight Acceleration Model Year Origin
393 27.0 4 140.0 86.0 2790.0 15.6 82 1
394 44.0 4 97.0 52.0 2130.0 24.6 82 2
395 32.0 4 135.0 84.0 2295.0 11.6 82 1
396 28.0 4 120.0 79.0 2625.0 18.6 82 1
397 31.0 4 119.0 82.0 2720.0 19.4 82 1 
dataset = dataset.dropna()
origin = dataset.pop('Origin')
#dataset['USA'] = (origin == 1)*1.0
dataset['Europe'] = (origin == 2)*1.0
dataset['Japan'] = (origin == 3)*1.0
dataset.tail()
SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  dataset['USA'] = (origin == 1)*1.0
<ipython-input-5-f05403a9f198>:4: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  dataset['Europe'] = (origin == 2)*1.0
<ipython-input-5-f05403a9f198>:5: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  dataset['Japan'] = (origin == 3)*1.0
MPG Cylinders Displacement Horsepower Weight Acceleration Model Year USA Europe Japan
393 27.0 4 140.0 86.0 2790.0 15.6 82 1.0 0.0 0.0
394 44.0 4 97.0 52.0 2130.0 24.6 82 0.0 1.0 0.0
395 32.0 4 135.0 84.0 2295.0 11.6 82 1.0 0.0 0.0
396 28.0 4 120.0 79.0 2625.0 18.6 82 1.0 0.0 0.0
397 31.0 4 119.0 82.0 2720.0 19.4 82 1.0 0.0 0.0 
train_dataset = dataset.sample(frac=0.8,random_state=0)
test_dataset = dataset.drop(train_dataset.index)
train_stats = train_dataset.describe()
train_stats.pop("MPG")
train_stats = train_stats.transpose()
train_stats
train_labels = train_dataset.pop('MPG')
test_labels = test_dataset.pop('MPG')
def norm(x):
  return (x - train_stats['mean']) / train_stats['std']
normed_train_data = norm(train_dataset)
normed_test_data = norm(test_dataset)
def build_model():
  model = keras.Sequential([

    layers.Dense(64, activation='relu', input_shape=[len(train_dataset.keys())]),
    layers.Dense(64, activation='relu'),  # 'linear' instead of 'relu'
    #layers.Dense(64, activation='relu'),
    #layers.Dense(64, activation='relu'),
    layers.Dense(1) ])

  optimizer = tf.keras.optimizers.RMSprop(0.001)
  model.compile(loss='mse',
                optimizer=optimizer,
                metrics=['mae', 'mse'])
  return model
model = build_model()
model.summary()

class PrintDot(keras.callbacks.Callback):
  def on_epoch_end(self, epoch, logs):
    if epoch % 100 == 0: print('')
    print('.', end='')

EPOCHS = 500
history = model.fit(
  normed_train_data, train_labels,
  epochs=EPOCHS, validation_split = 0.2, verbose=0,
  callbacks=[PrintDot()])
Model: "sequential_15"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 dense_53 (Dense)            (None, 64)                640       
                                                                 
 dense_54 (Dense)            (None, 64)                4160      
                                                                 
 dense_55 (Dense)            (None, 64)                4160      
                                                                 
 dense_56 (Dense)            (None, 64)                4160      
                                                                 
 dense_57 (Dense)            (None, 1)                 65        
                                                                 
=================================================================
Total params: 13185 (51.50 KB)
Trainable params: 13185 (51.50 KB)
Non-trainable params: 0 (0.00 Byte)
_________________________________________________________________

....................................................................................................
....................................................................................................
....................................................................................................
....................................................................................................
....................................................................................................
def plot_history(history):
  hist = pd.DataFrame(history.history)
  hist['epoch'] = history.epoch

  plt.figure(figsize=(8,12))

  plt.subplot(2,1,1)
  plt.xlabel('Epoch')
  plt.ylabel('Mean Abs Error [MPG]')
  plt.plot(hist['epoch'], hist['mae'],
           label='Train Error')
  plt.plot(hist['epoch'], hist['val_mae'],
           label = 'Val Error')
  plt.ylim([0,5])
  plt.legend()

  plt.subplot(2,1,2)
  plt.xlabel('Epoch')
  plt.ylabel('Mean Square Error [$MPG^2$]')
  plt.plot(hist['epoch'], hist['mse'],
           label='Train Error')
  plt.plot(hist['epoch'], hist['val_mse'],
           label = 'Val Error')
  plt.ylim([0,20])
  plt.legend()
  plt.show()

plot_history(history)

test_predictions = model.predict(normed_test_data).flatten()
yy = np.array(test_predictions)
xx = np.array(normed_test_data["Weight"])
print('MSE', np.mean(yy-test_labels)**2)

idx = np.array(np.argsort(xx), dtype='int')
print(idx)
xx = xx[idx]
yy = yy[idx]
3/3 [==============================] - 0s 4ms/step
MSE 3.2270409256119708
[ 9 65 44 56 38 24 76 57 74 66 43 45 40 37 67 60 10 52 41 21 13 30 68  3
 50 75 34 61 11 64 73 25 27 49 72 77  4 62 23 63 59 22 33 31 18 47 36  8
 51 46 48 32 29 69 58 70 28 39 71 16 26  0 55 53 15 54 42 12 14  6 35 20
 17  5 19  1  2  7]
plt.scatter(xx,yy)
plt.show()