#!/usr/bin/env python
# coding: utf-8

# ## PyData.Tokyo Meetup #4 - Performance Tips

# In[1]:


get_ipython().run_line_magic('load_ext', 'watermark')
get_ipython().run_line_magic('watermark', "-a 'Hideki Tanaka (@atelierhide)' -v -p numpy,numba,cython -d")


# ---
# ### Multiprocessing

# In[2]:


from multiprocessing import Pool
import math

pool = Pool(processes=4)
get_ipython().run_line_magic('timeit', 'pool.map(math.sqrt, xrange(10000))')

pool.close()
pool.join()


# ---
# ### Numpy, Numba, Cython

# In[3]:


import numpy as np
X = np.random.random((1000, 3))


# In[4]:


def pairwise_python(X):
    M = X.shape[0]
    N = X.shape[1]
    D = np.empty((M, M), dtype=np.float)
    for i in range(M):
        for j in range(M):
            d = 0.0
            for k in range(N):
                tmp = X[i, k] - X[j, k]
                d += tmp * tmp
            D[i, j] = np.sqrt(d)
    return D


# In[5]:


# Numpy
def pairwise_numpy(X):
    return np.sqrt(((X[:, None, :] - X) ** 2).sum(-1))


# In[6]:


# Numba
from numba.decorators import autojit
pairwise_numba = autojit(pairwise_python)


# In[7]:


# Cython
get_ipython().run_line_magic('load_ext', 'Cython')


# In[8]:


get_ipython().run_cell_magic('cython', '', '\nimport numpy as np\ncimport cython\nfrom libc.math cimport sqrt\n\n@cython.boundscheck(False)\n@cython.wraparound(False)\ndef pairwise_cython(double[:, ::1] X):\n    cdef int M = X.shape[0]\n    cdef int N = X.shape[1]\n    cdef double tmp, d\n    cdef double[:, ::1] D = np.empty((M, M), dtype=np.float64)\n    for i in range(M):\n        for j in range(M):\n            d = 0.0\n            for k in range(N):\n                tmp = X[i, k] - X[j, k]\n                d += tmp * tmp\n            D[i, j] = sqrt(d)\n    return np.asarray(D)\n')


# In[10]:


get_ipython().run_line_magic('timeit', 'pairwise_python(X)')
get_ipython().run_line_magic('timeit', 'pairwise_numpy(X)')
get_ipython().run_line_magic('timeit', 'pairwise_numba(X)')
get_ipython().run_line_magic('timeit', 'pairwise_cython(X)')


# ---
# ### List Comprehension, Map, Numpy

# In[11]:


import math
import numpy as np


# In[12]:


def list_append(x):
    results = []
    for i in xrange(x):
        results.append(math.sqrt(i))
    return results

def list_append2(x):
    results = []
    for i in xrange(x):
        results.append(math.sqrt(i))
    return results

def list_comp(x):
    results = [math.sqrt(i) for i in xrange(x)]
    return results

def list_map(x):
    results = map(math.sqrt, xrange(x))
    return results

def list_numpy(x):
    results = list(np.sqrt(np.arange(x)))
    return results


# In[13]:


x = 10000
get_ipython().run_line_magic('timeit', 'list_append(x)')
get_ipython().run_line_magic('timeit', 'list_append2(x)')
get_ipython().run_line_magic('timeit', 'list_comp(x)')
get_ipython().run_line_magic('timeit', 'list_map(x)')
get_ipython().run_line_magic('timeit', 'list_numpy(x)')


# ### References
# 
# - [High Performance Python Computing for Data Science](http://www.slideshare.net/tkm2261/high-performance-python-computing-for-data-science)
# - [Numba vs. Cython](https://jakevdp.github.io/blog/2013/06/15/numba-vs-cython-take-2/)