pandas_ex.py

# Shuffle dataframe

cities.reindex(np.random.permutation(cities.index))

# Read data from Google Cloud Storage

california_housing_dataframe = pd.read_csv("https://storage.googleapis.com/mledu-datasets/california_housing_train.csv", sep=",")

# Convert pandas data into a dict of np arrays
# where `key` is column name.
# example:
# {'households': array([ 472.,  463.,  117., ...,  356.,  359., 1453.]), 'median_income': array([1.4936, 1.82  , 1.6509, ..., 2.8462, 8.4016, 4.3644]), 'total_rooms': array([5612., 7650.,  720., ..., 2019., 2648., 8507.]), 'housing_median_age': array([15., 19., 17., ..., 36., 33., 19.]), 'longitude': array([-114.31, -114.47, -114.56, ..., -121.39, -121.39, -121.39]), 'total_bedrooms': array([1283., 1901.,  174., ...,  369.,  357., 1470.])}

features = {key:np.array(value) for key,value in dict(features).items()}