Fabian Schreiber fabsta

minst

from keras.datasets import mnist
(X_train, y_train), (X_test, y_test) = mnist.load_data()
(X_train.shape, y_train.shape, X_test.shape, y_test.shape)
>> ((60000, 28, 28), (60000,), (10000, 28, 28), (10000,))

X_test = np.expand_dims(X_test,1)
X_train = np.expand_dims(X_train,1)

Pandas cheat sheet for data science

Pandas cheat sheet for data science
Statistics
- Multi-variate analysis
- Feature understanding
Preliminaries
Import

	# list = [1, 3, 5, 7, 9]
	# Using for loop
	for i in list:
	print(i)
	# 1
	# 3

	# for index
	for i in range(length):
	print(list[i])

	# often works
	df = pd.read_csv('file.csv')
	df = pd.read_csv('file.csv', header=0, index_col=0, quotechar='"',sep=':', na_values = ['na', '-', '.', ''])
	# specifying "." and "NA" as missing values in the Last Name column and "." as missing values in Pre-Test Score column
	df = pd.read_csv('../data/example.csv', na_values={'Last Name': ['.', 'NA'], 'Pre-Test Score': ['.']})
	# skipping the top 3 rows
	df = pd.read_csv('../data/example.csv', na_values=sentinels, skiprows=3)
	# interpreting "," in strings around numbers as thousands separators
	df = pd.read_csv('../data/example.csv', thousands=',')