머신러닝스터디/2016/2016 09 03 - Revision history

Maintenance script: Repair batch-0005 pages from live compare

2026-03-27T00:44:58Z

Repair batch-0005 pages from live compare

← Older revision		Revision as of 00:44, 27 March 2026
Line 19:		Line 19:
	test = pd.read_csv("../input/test.csv")		test = pd.read_csv("../input/test.csv")

	y_train = train['label'].as_matrix()		y_train = train['label'].as_matrix()
	X_train = train.drop('label', axis=1).as_matrix()		X_train = train.drop('label', axis=1).as_matrix()

Line 37:		Line 37:
	model.add(keras.layers.Dense(10, activation='softmax'))		model.add(keras.layers.Dense(10, activation='softmax'))

	model.compile(loss='categorical_crossentropy', optimizer='adagrad', metrics=['accuracy'])		model.compile(loss='categorical_crossentropy', optimizer='adagrad', metrics=['accuracy'])
	model.fit(X_train, to_categorical(y_train, 10), nb_epoch=5, batch_size=600)		model.fit(X_train, to_categorical(y_train, 10), nb_epoch=5, batch_size=600)

Line 44:		Line 44:
	print(score)		print(score)

	print(model.predict(X_test))[0]		print(model.predict(X_test))[0]
	print(y_test[0])		print(y_test[0])
	== 다음 시간에는 ==		== 다음 시간에는 ==
	* 다음 시간에도 kaggle digits 계속...		* 다음 시간에도 kaggle digits 계속...

14.32.111.138 at 03:31, 13 September 2016

2016-09-13T03:31:56Z

← Older revision		Revision as of 03:31, 13 September 2016
Line 47:		Line 47:
	print(y_test[0])		print(y_test[0])
	== 다음 시간에는 ==		== 다음 시간에는 ==
			* 다음 시간에도 kaggle digits 계속...

14.32.111.138 at 03:30, 13 September 2016

2016-09-13T03:30:56Z

← Older revision		Revision as of 03:30, 13 September 2016
Line 10:		Line 10:
	* 0번째 컬럼을 분리하였으나 학습정확도가 10%대		* 0번째 컬럼을 분리하였으나 학습정확도가 10%대
	** 학습이 전혀 되지 않은 것..(0~9중에 찍었을 때 1/10 확률로 정답)		** 학습이 전혀 되지 않은 것..(0~9중에 찍었을 때 1/10 확률로 정답)
			=== 코드 ===
	import pandas as pd		import pandas as pd
	import keras		import keras
Line 15:		Line 16:
	from keras.utils.np_utils import to_categorical		from keras.utils.np_utils import to_categorical

	train = pd.read_csv("./input/train.csv")		train = pd.read_csv("../input/train.csv")
	test = pd.read_csv("./input/test.csv")		test = pd.read_csv("../input/test.csv")

	y_train = train['label'].as_matrix()		y_train = train['label'].as_matrix()

imported>rabierre: {CREATE}

2016-09-06T17:36:09Z

{CREATE}

New page

[[머신러닝스터디/2016]]
[[머신러닝스터디/2016/목차]]
== 내용 ==
* Project
** [https://www.kaggle.com/c/digit-recognizer kaggle digit recignizer]
** train 데이터의 0번째 컬럼이 y값(785열)이고 test는 y값이 주어지지 않음(784 열)
** 데이터 전처리 필요
** pandas 라이브러리에 익숙하지 않아 각자 input data 핸들링 하는 방법에 대해 알아봄

* 0번째 컬럼을 분리하였으나 학습정확도가 10%대
** 학습이 전혀 되지 않은 것..(0~9중에 찍었을 때 1/10 확률로 정답)
import pandas as pd
import keras
from sklearn.cross_validation import train_test_split
from keras.utils.np_utils import to_categorical

train = pd.read_csv("./input/train.csv")
test = pd.read_csv("./input/test.csv")

y_train = train['label'].as_matrix()
X_train = train.drop('label', axis=1).as_matrix()

X_train, X_test, y_train, y_test = train_test_split(X_train, y_train, test_size=0.30)

model = keras.models.Sequential()

model.add(keras.layers.Dense(64, input_dim=28*28, activation='relu'))
model.add(keras.layers.Dropout(0.5))

model.add(keras.layers.Dense(32, activation='relu'))
model.add(keras.layers.Dropout(0.5))

model.add(keras.layers.Dense(16, activation='relu'))
model.add(keras.layers.Dropout(0.5))

model.add(keras.layers.Dense(10, activation='softmax'))

model.compile(loss='categorical_crossentropy', optimizer='adagrad', metrics=['accuracy'])
model.fit(X_train, to_categorical(y_train, 10), nb_epoch=5, batch_size=600)

score = model.evaluate(X_test, to_categorical(y_test, 10), batch_size=700)

print(score)

print(model.predict(X_test))[0]
print(y_test[0])
== 다음 시간에는 ==