%load_ext watermark

%watermark -d -v -u -t -z -p numpy

import numpy as np

np.random.seed(123)

# A random 2D-array ranging from 0-100

X = np.random.rand(100,2)
X.dtype = np.float64
X *= 100 

def numpy_minmax(X):
    xmin =  X.min()
    return (X - xmin) / (X.max() - xmin)

from sklearn import preprocessing

def sci_minmax(X):
    minmax_scale = preprocessing.MinMaxScaler(feature_range=(0, 1), copy=True)
    return minmax_scale.fit_transform(X)

%matplotlib inline

from matplotlib import pyplot as plt

sci_mm = sci_minmax(X)
numpy_mm = numpy_minmax(X)

plt.scatter(numpy_mm[:,0], numpy_mm[:,1],
        color='g',
        label='NumPy bottom-up',
        alpha=0.5,
        marker='o'
        )

plt.scatter(sci_mm[:,0], sci_mm[:,1],
        color='b',
        label='scikit-learn',
        alpha=0.5,
        marker='x'
        )

plt.legend()
plt.grid()

plt.show()

import timeit
from numpy import append as np_append
from numpy import concatenate as np_concatenate
from numpy import hstack as np_hstack
from numpy import vstack as np_vstack

funcs = ('np_append', 'np_concatenate', 'np_hstack', 'np_linalg_norm')

t_append, t_hconc, t_vconc, t_hstack, t_vstack = [], [], [], [], []

orders_5 = [10**i for i in range(1, 5)]
for n in orders_5:
    
    nxn_dim = np.random.randn(n,n)

    t_vconc.append(min(timeit.Timer('np_concatenate((nxn_dim, nxn_dim))', 
            'from __main__ import nxn_dim, np_concatenate').repeat(repeat=5, number=1)))
    t_vstack.append(min(timeit.Timer('np_vstack((nxn_dim, nxn_dim))', 
            'from __main__ import nxn_dim, np_vstack').repeat(repeat=5, number=1)))    
    
orders_6 = [10**i for i in range(1, 6)]
for n in orders_6:
    
    nx1_dim = np.random.randn(n,1)
    
    t_append.append(min(timeit.Timer('np_append(nx1_dim, nx1_dim)', 
            'from __main__ import nx1_dim, np_append').repeat(repeat=5, number=1)))
    t_hconc.append(min(timeit.Timer('np_concatenate((nx1_dim, nx1_dim), axis=1)', 
            'from __main__ import nx1_dim, np_concatenate').repeat(repeat=5, number=1)))
    t_hstack.append(min(timeit.Timer('np_hstack((nx1_dim, nx1_dim))', 
            'from __main__ import nx1_dim, np_hstack').repeat(repeat=5, number=1)))

%matplotlib inline

from matplotlib import pyplot as plt

def plot():
    
    def settings():
        plt.xlim([min(orders_6) / 10, max(orders_6)* 10])
        plt.legend(loc=2, fontsize=14)
        plt.grid()
        plt.xticks(fontsize=16)
        plt.yticks(fontsize=16)
        plt.xscale('log')
        plt.yscale('log')
        plt.legend(loc=2, fontsize=14)

    fig = plt.figure(figsize=(15,8))

    plt.subplot(1,2,1)
    plt.plot(orders_5, t_vconc, alpha=0.7, label='np.concatenate((a,b))')
    plt.plot(orders_5, t_vstack, alpha=0.7, label='np.vstack((a,b))')    
    plt.xlabel(r'sample size $n$ ($n\times \, n$ NumPy array)', fontsize=14)
    plt.ylabel('time per computation in seconds', fontsize=14)
    plt.title('Vertical stacking of NumPy arrays (row wise)', fontsize=14)
    settings()
    
    
    plt.subplot(1,2,2)
    plt.plot(orders_6, t_hconc, alpha=0.7, label='np.concatenate((a,b), axis=1)')
    plt.plot(orders_6, t_hstack, alpha=0.7, label='np.hstack((a,b))') 
    plt.plot(orders_6, t_append, alpha=0.7, label='np.append(a,b)')  
    plt.xlabel(r'sample size $n$ ($n\times \, 1$ NumPy array)', fontsize=14)
    plt.ylabel('time per computation in seconds', fontsize=14)
    plt.title('Horizontal stacking of NumPy arrays (column wise)', fontsize=14)
    settings()

    plt.tight_layout()
    plt.show()

plot()

%watermark