Numpy (35)

How to drop rows that contain a missing value from a numpy array?

# Input
url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data'
iris_2d = np.genfromtxt(url, delimiter=',', dtype='float', usecols=[0,1,2,3])
iris_2d[np.random.randint(150, size=20), np.random.randint(4, size=20)] = np.nan

# Solution
# No direct numpy function for this.
# 1:
any_nan_in_row = np.array([~np.any(np.isnan(row)) for row in iris_2d])
iris_2d[any_nan_in_row][:5]

# 2: (By Rong)
iris_2d[np.sum(np.isnan(iris_2d), axis = 1) == 0][:5]

# output
 array([[ 4.9,  3. ,  1.4,  0.2],
        [ 4.7,  3.2,  1.3,  0.2],
        [ 4.6,  3.1,  1.5,  0.2],
        [ 5. ,  3.6,  1.4,  0.2],
        [ 5.4,  3.9,  1.7,  0.4]])