Pandas and basic plotting

In [177]:

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import random as rnd
%matplotlib inline

In [4]:

np.arange(0,10, 2)

Out[4]:

array([0, 2, 4, 6, 8])

In [5]:

np.linspace(10,23,6)

Out[5]:

array([ 10. ,  12.6,  15.2,  17.8,  20.4,  23. ])

In [23]:

rnd.seed(121)
rnd.random()

Out[23]:

0.08730148686581662

In [51]:

l1 = [1,2,3,4]
a = np.array(l1)
a = a.reshape(2,2)
print(a)
print(a[:,0])

[[1 2]
 [3 4]]
[1 3]

In [54]:

a.dtype

Out[54]:

dtype('int32')

In [64]:

np.transpose(np.ones(3).reshape(1,3)).dtype

Out[64]:

dtype('float64')

In [66]:

np.random.randn(2)

Out[66]:

array([-0.16930965,  1.30136014])

In [67]:

np.random.uniform(0,1,5)

Out[67]:

array([ 0.78556333,  0.11732278,  0.35629669,  0.27716212,  0.20262334])

In [72]:

plt.plot(np.random.uniform(0,1,5))

Out[72]:

[<matplotlib.lines.Line2D at 0x26aabf22278>]

In [85]:

countries = ['aus', 'Ind', 'pak', 'SL', 'Eng']
happiness_Index = ['8','4','4','6','8.5']

df = pd.DataFrame(happiness_Index, index = countries, columns = ['happiness_Index'])
df
df1 = pd.DataFrame(np.random.randn(5,5), index = "0,1,2,3,4".split(","), columns="a b c d e".split(" "))
df1

Out[85]:

	a	b	c	d	e
0	0.650215	-0.810062	0.632912	-0.343608	1.385923
1	0.080158	1.485864	0.788142	-0.066174	-0.922874
2	-0.574159	-0.861349	-0.972300	-2.240135	0.591917
3	0.408051	1.422824	-1.108161	0.056692	1.261179
4	-0.634453	-0.140949	0.212248	0.351281	-0.538127

In [96]:

df1.loc[['0']]

Out[96]:

	a	b	c	d	e
0	0.650215	-0.810062	0.632912	-0.343608	1.385923

In [99]:

df1.loc[['1','2'],['b','c']]

Out[99]:

	b	c
1	1.485864	0.788142
2	-0.861349	-0.972300

In [108]:

df1.loc[:,['b','c']]

Out[108]:

	b	c
0	-0.810062	0.632912
1	1.485864	0.788142
2	-0.861349	-0.972300
3	1.422824	-1.108161
4	-0.140949	0.212248

In [109]:

df1 > 0

Out[109]:

	a	b	c	d	e
0	True	False	True	False	True
1	True	True	True	False	False
2	False	False	False	False	True
3	True	True	False	True	True
4	False	False	True	True	False

In [111]:

df1[df1 > 0][['a','e']]

Out[111]:

	a	e
0	0.650215	1.385923
1	0.080158	NaN
2	NaN	0.591917
3	0.408051	1.261179
4	NaN	NaN

In [112]:

df1['d'] > 0

Out[112]:

0    False
1    False
2    False
3     True
4     True
Name: d, dtype: bool

In [114]:

df1[df1['d'] > 0]

Out[114]:

	a	b	c	d	e
3	0.408051	1.422824	-1.108161	0.056692	1.261179
4	-0.634453	-0.140949	0.212248	0.351281	-0.538127

In [136]:

newind = 'a0 a1 a2 a3 a4'.split()

In [137]:

df1['new_index'] = newind

In [138]:

df1

Out[138]:

	a	b	c	d	e	new_index
0	0.650215	-0.810062	0.632912	-0.343608	1.385923	a0
1	0.080158	1.485864	0.788142	-0.066174	-0.922874	a1
2	-0.574159	-0.861349	-0.972300	-2.240135	0.591917	a2
3	0.408051	1.422824	-1.108161	0.056692	1.261179	a3
4	-0.634453	-0.140949	0.212248	0.351281	-0.538127	a4

In [139]:

df1.reset_index()

Out[139]:

	index	a	b	c	d	e	new_index
0	0	0.650215	-0.810062	0.632912	-0.343608	1.385923	a0
1	1	0.080158	1.485864	0.788142	-0.066174	-0.922874	a1
2	2	-0.574159	-0.861349	-0.972300	-2.240135	0.591917	a2
3	3	0.408051	1.422824	-1.108161	0.056692	1.261179	a3
4	4	-0.634453	-0.140949	0.212248	0.351281	-0.538127	a4

In [141]:

df1.set_index('new_index')

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-141-4b031fb7ee18> in <module>()
----> 1 df1.set_index('new_index')

TypeError: 'list' object is not callable

In [144]:

from collections import defaultdict

In [146]:

d = defaultdict(list)
d['a'].append(100)
d['a'].append(101)
d['a'].append(102)
d['b'].append(200)
d['b'].append(201)

In [151]:

d['b'].append(np.nan)
d

Out[151]:

defaultdict(list, {'a': [100, 101, 102], 'b': [200, 201, nan]})

In [154]:

df2 = pd.DataFrame(d)
df2

Out[154]:

	a	b
0	100	200.0
1	101	201.0
2	102	NaN

In [155]:

df2['Countries'] = 'aus ind eng'.split()
df2

Out[155]:

	a	b	Countries
0	100	200.0	aus
1	101	201.0	ind
2	102	NaN	eng

In [156]:

byCountry = df2.groupby('Countries')

In [162]:

df3 = pd.DataFrame(np.random.randn(3,3), index = 'a b c'.split(), columns = 'x y z'.split())
df3

Out[162]:

	x	y	z
a	-0.505596	1.574099	-0.822803
b	2.362696	0.507077	0.555769
c	-0.394249	0.331578	-0.048262

In [171]:

x = np.linspace(0,10,5)
y2 = y**2
y3 = x**3
print(y2)
print(y3)

[  0.00000000e+00   2.44140625e+02   1.56250000e+04   1.77978516e+05
   1.00000000e+06]
[    0.       15.625   125.      421.875  1000.   ]

In [167]:

plt.plot(x,y3)

Out[167]:

[<matplotlib.lines.Line2D at 0x26aac1f9710>]

In [168]:

plt.subplot(1,2,1)
plt.plot(x,y2,'r--')
plt.subplot(1,2,2)
plt.plot(x,y3,'g--')

Out[168]:

[<matplotlib.lines.Line2D at 0x26aac2586d8>]

In [190]:

fig = plt.figure(figsize=(2,1), dpi=50)
axes = fig.add_axes([0,0,2,2])
axes.plot(x, y2, 'b')

Out[190]:

[<matplotlib.lines.Line2D at 0x26aaca5c9b0>]

In [197]:

fig, axes = plt.subplots(nrows=1, ncols=2)

In [204]:

for ax in axes:
    ax.plot(x, y, 'b')
    ax.set_xlabel('x')
    ax.set_ylabel('y')
    ax.set_title('title')
fig
plt.tight_layout()

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-204-f836af9c8ade> in <module>()
      5     ax.set_title('title')
      6 fig
----> 7 plt.tight_layout()

C:\Users\hp\AppData\Local\Continuum\Anaconda3\lib\site-packages\matplotlib\pyplot.py in tight_layout(pad, h_pad, w_pad, rect)
   1385 
   1386     fig = gcf()
-> 1387     fig.tight_layout(pad=pad, h_pad=h_pad, w_pad=w_pad, rect=rect)
   1388 
   1389 

C:\Users\hp\AppData\Local\Continuum\Anaconda3\lib\site-packages\matplotlib\figure.py in tight_layout(self, renderer, pad, h_pad, w_pad, rect)
   1750                                          renderer,
   1751                                          pad=pad, h_pad=h_pad, w_pad=w_pad,
-> 1752                                          rect=rect)
   1753 
   1754         self.subplots_adjust(**kwargs)

C:\Users\hp\AppData\Local\Continuum\Anaconda3\lib\site-packages\matplotlib\tight_layout.py in get_tight_layout_figure(fig, axes_list, subplotspec_list, renderer, pad, h_pad, w_pad, rect)
    320         subplots.append(ax)
    321 
--> 322     max_nrows = max(nrows_list)
    323     max_ncols = max(ncols_list)
    324 

ValueError: max() arg is an empty sequence

<matplotlib.figure.Figure at 0x26aae7c79e8>

lets look at seaborn library

In [205]:

import seaborn as sns

In [206]:

tips = sns.load_dataset('tips')
tips.head()

Out[206]:

	total_bill	tip	sex	smoker	day	time	size
0	16.99	1.01	Female	No	Sun	Dinner	2
1	10.34	1.66	Male	No	Sun	Dinner	3
2	21.01	3.50	Male	No	Sun	Dinner	3
3	23.68	3.31	Male	No	Sun	Dinner	2
4	24.59	3.61	Female	No	Sun	Dinner	4

In [207]:

sns.violinplot(x="day", y="total_bill", data=tips,hue='sex',palette='rainbow')

Out[207]:

<matplotlib.axes._subplots.AxesSubplot at 0x26aaf26b710>