javiferfer

def read_idx(filename):
    with gzip.open(filename, 'rb') as f:
        zero, data_type, dims = struct.unpack('>HBB', f.read(4))
        shape = tuple(struct.unpack('>I', f.read(4))[0] for d in range(dims))
        return np.fromstring(f.read(), dtype=np.uint8).reshape(shape)
        
train_x = read_idx('./fashion-mnist/data/fashion/train-images-idx3-ubyte.gz')
train_y = read_idx('./fashion-mnist/data/fashion/train-labels-idx1-ubyte.gz')
test_x = read_idx('./fashion-mnist/data/fashion/t10k-images-idx3-ubyte.gz')
test_y = read_idx('./fashion-mnist/data/fashion/t10k-labels-idx1-ubyte.gz')

javiferfer

pd = pd.DataFrame(fetch_california_housing.data, columns=fetch_california_housing.feature_names)
pd['AveHouseVal'] = (fetch_california_housing.target)*100000

javiferfer

(mu, sigma) = norm.fit(residuals)
print( '\n mu = {:.2f} and sigma = {:.2f}\n'.format(mu, sigma))

_, p_value = stats.shapiro(residuals)
print('Shapiro-Wilk test p-value: ' + str(p_value))

# Get the fitted parameters used by the function
sns.distplot(residuals , fit=norm)
plt.legend(['Normal dist. ($\mu=$ {:.2f} and $\sigma=$ {:.2f} )'.format(mu, sigma)], loc='best')
plt.ylabel('Frequency')

javiferfer

X = pd[['MedInc', 'Latitude', 'AveRooms']]
Y = pd['AveHouseVal']

X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.2, random_state=5)
lin_model = LinearRegression()
lin_model.fit(X_train, Y_train)

# model evaluation for training set
y_train_predict = lin_model.predict(X_train)
rmse = (np.sqrt(mean_squared_error(Y_train, y_train_predict)))

javiferfer

corrmat = pd.corr()
plt.subplots(figsize=(12,9))
mask = np.zeros_like(corrmat, dtype=np.bool)
mask[np.triu_indices_from(mask)] = True
sns.heatmap(corrmat, vmax=0.9, square=True, annot=True, mask=mask, cbar_kws={"shrink": .5})

javiferfer

plt.figure(figsize=(10,8))
plt.scatter(pd['Latitude'], pd['Longitude'], c=pd['AveHouseVal'], s=pd['Population']/100)
plt.colorbar()

javiferfer

pd.isnull().sum()

javiferfer

pd = pd.DataFrame(fetch_california_housing.data, columns=fetch_california_housing.feature_names)
pd.head()

javiferfer

print(fetch_california_housing.DESCR)

javiferfer

fetch_california_housing = fetch_california_housing()
print(fetch_california_housing.keys())