In [2]:
import numpy as np
from matplotlib import pyplot as plt
In [3]:
%matplotlib inline
In [4]:
fig = plt.figure()
In [5]:
ax1 = fig.add_subplot(2, 2, 1)
In [6]:
ax2 = fig.add_subplot(2, 2, 2)
ax3 = fig.add_subplot(2, 2, 3)
In [10]:
%matplotlib notebook
fig.show()
In [11]:
from numpy.random import randn
plt.plot(randn(50).cumsum(), 'k--')
Out[11]:
In [12]:
_ = ax1.hist(randn(100), bins=20, color='k', alpha=0.3)
ax2.scatter(np.arange(30), np.arange(30) + 3 * randn(30))
Out[12]:
In [13]:
plt.close('all')
In [15]:
%matplotlib inline
fig, axes = plt.subplots(2, 3)
axes
Out[15]:
In [16]:
plt.subplots_adjust(left=None, bottom=None, right=None, top=None,
wspace=None, hspace=None)
In [17]:
fig, axes = plt.subplots(2, 2, sharex=True, sharey=True)
for i in range(2):
for j in range(2):
axes[i, j].hist(randn(500), bins=50, color='k', alpha=0.5)
plt.subplots_adjust(wspace=0, hspace=0)
In [18]:
fig, axes = plt.subplots(2, 2, sharex=True, sharey=True)
for i in range(2):
for j in range(2):
axes[i, j].hist(randn(500), bins=50, color='k', alpha=0.5)
plt.subplots_adjust(wspace=0, hspace=0)
In [ ]:
plt.figure()
plt.plot(randn(30).cumsum(), 'ko--')
In [20]:
plt.close('all')
data = randn(30).cumsum()
plt.plot(data, 'k--', label='Default')
plt.plot(data, 'k-', drawstyle='steps-post', label='steps-post')
plt.legend(loc='best')
Out[20]:
In [21]:
fig = plt.figure(); ax = fig.add_subplot(1, 1, 1)
ax.plot(randn(1000).cumsum())
Out[21]:
In [25]:
fig = plt.figure(); ax = fig.add_subplot(1, 1, 1)
ticks = ax.set_xticks([0, 250, 500, 750, 1000])
labels = ax.set_xticklabels(['one', 'two', 'three', 'four', 'five'],
rotation=30, fontsize='small')
ax.set_title('My first matplotlib plot')
ax.set_xlabel('Stages')
ax.plot(randn(1000).cumsum())
Out[25]:
In [26]:
fig = plt.figure(); ax = fig.add_subplot(1, 1, 1)
ax.plot(randn(1000).cumsum(), 'k', label='one')
ax.plot(randn(1000).cumsum(), 'k--', label='two')
ax.plot(randn(1000).cumsum(), 'k.', label='three')
ax.legend(loc='best')
Out[26]:
In [29]:
from datetime import datetime
import pandas as pd
data = pd.read_csv('spx.csv', index_col=0, parse_dates=True)
data
Out[29]:
In [30]:
fig = plt.figure()
ax = fig.add_subplot(1, 1, 1)
spx = data['PX']
spx.plot(ax=ax, style='k-')
crisis_data = [
(datetime(2007, 10, 11), 'Peak of bull market'),
(datetime(2008, 3, 12), 'Bear Stearns Fails'),
(datetime(2008, 9, 15), 'Lehman Bankruptcy')
]
for date, label in crisis_data:
ax.annotate(label, xy=(date, spx.asof(date) + 50),
xytext=(date, spx.asof(date) + 200),
arrowprops=dict(facecolor='black'),
horizontalalignment='left', verticalalignment='top')
# Zoom in on 2007-2010
ax.set_xlim(['1/1/2007', '1/1/2011'])
ax.set_ylim([600, 1800])
ax.set_title('Important dates in 2008-2009 financial crisis')
Out[30]:
In [31]:
fig = plt.figure()
ax = fig.add_subplot(1, 1, 1)
rect = plt.Rectangle((0.2, 0.75), 0.4, 0.15, color='k', alpha=0.3)
circ = plt.Circle((0.7, 0.2), 0.15, color='b', alpha=0.3)
pgon = plt.Polygon([[0.15, 0.15], [0.35, 0.4], [0.2, 0.6]],
color='g', alpha=0.5)
ax.add_patch(rect)
ax.add_patch(circ)
ax.add_patch(pgon)
Out[31]:
In [32]:
fig
fig.savefig('figpath.svg')
fig.savefig('figpath.png', dpi=400, bbox_inches='tight')
In [33]:
from io import BytesIO
buffer = BytesIO()
plt.savefig(buffer)
plot_data = buffer.getvalue()
In [35]:
from pandas import Series, DataFrame
s = Series(np.random.randn(10).cumsum(), index=np.arange(0, 100, 10))
s.plot()
Out[35]:
In [36]:
df = DataFrame(np.random.randn(10, 4).cumsum(0),
columns=['A', 'B', 'C', 'D'],
index=np.arange(0, 100, 10))
df.plot()
Out[36]:
In [37]:
fig, axes = plt.subplots(2, 1)
data = Series(np.random.rand(16), index=list('abcdefghijklmnop'))
data.plot(kind='bar', ax=axes[0], color='k', alpha=0.7)
data.plot(kind='barh', ax=axes[1], color='k', alpha=0.7)
Out[37]:
In [38]:
df = DataFrame(np.random.rand(6, 4),
index=['one', 'two', 'three', 'four', 'five', 'six'],
columns=pd.Index(['A', 'B', 'C', 'D'], name='Genus'))
df
df.plot(kind='bar')
Out[38]:
In [39]:
df.plot(kind='barh', stacked=True, alpha=0.5)
Out[39]:
In [45]:
tips = pd.read_csv('tips.csv')
tips
Out[45]:
In [46]:
party_counts = pd.crosstab(tips.day, tips.size)
party_counts
Out[46]:
In [47]:
party_counts = party_counts.ix[:, 2:5]
In [48]:
party_pcts = party_counts.div(party_counts.sum(1).astype(float), axis=0)
party_pcts
Out[48]:
In [49]:
party_pcts.plot(kind='bar', stacked=True)
In [50]:
tips['tip_pct'] = tips['tip'] / tips['total_bill']
tips['tip_pct'].hist(bins=50)
Out[50]:
In [51]:
tips['tip_pct'].plot(kind='kde')
Out[51]:
In [52]:
comp1 = np.random.normal(0, 1, size=200) # N(0, 1)
comp2 = np.random.normal(10, 2, size=200) # N(10, 4)
values = Series(np.concatenate([comp1, comp2]))
values.hist(bins=100, alpha=0.3, color='k', normed=True)
values.plot(kind='kde', style='k--')
Out[52]:
In [53]:
macro = pd.read_csv('macrodata.csv')
data = macro[['cpi', 'm1', 'tbilrate', 'unemp']]
trans_data = np.log(data).diff().dropna()
trans_data[-5:]
Out[53]:
In [54]:
plt.scatter(trans_data['m1'], trans_data['unemp'])
plt.title('Changes in log %s vs. log %s' % ('m1', 'unemp'))
Out[54]:
In [56]:
pd.scatter_matrix(trans_data, diagonal='kde', alpha=0.3)
Out[56]:
In [58]:
data = pd.read_csv('Haiti.csv')
data.info()
In [59]:
data[['INCIDENT DATE', 'LATITUDE', 'LONGITUDE']][:10]
Out[59]:
In [60]:
data['CATEGORY'][:6]
Out[60]:
In [61]:
data.describe()
Out[61]:
In [62]:
data = data[(data.LATITUDE > 18) & (data.LATITUDE < 20) &
(data.LONGITUDE > -75) & (data.LONGITUDE < -70)
& data.CATEGORY.notnull()]
In [63]:
def to_cat_list(catstr):
stripped = (x.strip() for x in catstr.split(','))
return [x for x in stripped if x]
def get_all_categories(cat_series):
cat_sets = (set(to_cat_list(x)) for x in cat_series)
return sorted(set.union(*cat_sets))
def get_english(cat):
code, names = cat.split('.')
if '|' in names:
names = names.split(' | ')[1]
return code, names.strip()
In [64]:
all_cats = get_all_categories(data.CATEGORY)
english_mapping = dict(get_english(x) for x in all_cats)
english_mapping['2a']
english_mapping['6c']
Out[64]:
In [65]:
def get_code(seq):
return [x.split('.')[0] for x in seq if x]
all_codes = get_code(all_cats)
code_index = pd.Index(np.unique(all_codes))
dummy_frame = DataFrame(np.zeros((len(data), len(code_index))),
index=data.index, columns=code_index)
In [66]:
dummy_frame.ix[:, :6].info()
In [67]:
for row, cat in zip(data.index, data.CATEGORY):
codes = get_code(to_cat_list(cat))
dummy_frame.ix[row, codes] = 1
data = data.join(dummy_frame.add_prefix('category_'))
In [68]:
data.ix[:, 10:15].info()
In [69]:
from mpl_toolkits.basemap import Basemap
import matplotlib.pyplot as plt
def basic_haiti_map(ax=None, lllat=17.25, urlat=20.25,
lllon=-75, urlon=-71):
# create polar stereographic Basemap instance.
m = Basemap(ax=ax, projection='stere',
lon_0=(urlon + lllon) / 2,
lat_0=(urlat + lllat) / 2,
llcrnrlat=lllat, urcrnrlat=urlat,
llcrnrlon=lllon, urcrnrlon=urlon,
resolution='f')
# draw coastlines, state and country boundaries, edge of map.
m.drawcoastlines()
m.drawstates()
m.drawcountries()
return m
In [70]:
fig, axes = plt.subplots(nrows=2, ncols=2, figsize=(12, 10))
fig.subplots_adjust(hspace=0.05, wspace=0.05)
to_plot = ['2a', '1', '3c', '7a']
lllat=17.25; urlat=20.25; lllon=-75; urlon=-71
for code, ax in zip(to_plot, axes.flat):
m = basic_haiti_map(ax, lllat=lllat, urlat=urlat,
lllon=lllon, urlon=urlon)
cat_data = data[data['category_%s' % code] == 1]
# compute map proj coordinates.
x, y = m(cat_data.LONGITUDE.values, cat_data.LATITUDE.values)
m.plot(x, y, 'k.', alpha=0.5)
ax.set_title('%s: %s' % (code, english_mapping[code]))
In [71]:
fig, axes = plt.subplots(nrows=2, ncols=2, figsize=(12, 10))
fig.subplots_adjust(hspace=0.05, wspace=0.05)
to_plot = ['2a', '1', '3c', '7a']
lllat=17.25; urlat=20.25; lllon=-75; urlon=-71
def make_plot():
for i, code in enumerate(to_plot):
cat_data = data[data['category_%s' % code] == 1]
lons, lats = cat_data.LONGITUDE, cat_data.LATITUDE
ax = axes.flat[i]
m = basic_haiti_map(ax, lllat=lllat, urlat=urlat,
lllon=lllon, urlon=urlon)
# compute map proj coordinates.
x, y = m(lons.values, lats.values)
m.plot(x, y, 'k.', alpha=0.5)
ax.set_title('%s: %s' % (code, english_mapping[code]))
In [ ]: