《利用Python进行数据分析》读书笔记-8-第八章-绘图和可视化

字数统计: 1.9k字   |   阅读时长≈ 10分

matplotlib API入门

Figure 和 Subplot

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
import matplotlib.pyplot as plt

## Figure 和 Subplot
# matplotlib的图像都位于Figure对象中，构建新对象
fig = plt.figure()
# 不能通过Figure绘图，必须用add_subplot创建一个或多个subplot才行
ax1 = fig.add_subplot(2,2,1)
ax2 = fig.add_subplot(2,2,2)
ax3 = fig.add_subplot(2,2,3)
plt.show()
# 这三个是表示图像是2*2的，当前占编号1，2，3位

plt.plot([1.5,3.5,-2,1.6])

from numpy.random import randn
plt.plot(randn(50).cumsum(), 'k--')
plt.show()
# "k--"线型选项，黑色虚线图

# 随机柱状图，20柱，每柱间隔0.3
_ = ax1.hist(randn(100), bins=20, color='k', alpha=0.3)
# 随机散点图，30个点
ax2.scatter(np.arange(30), np.arange(30) + 3 * randn(30))
# plt.show()

颜色、标记和线型

1
2
3
4
plt.plot(randn(30).cumsum(), 'ko--')
# 等价于以下明确形式：R
# plot(randn(30).cumsum(), color='k', linestyle='dashed', marker='0')
plt.show()

图8-6带有标记的线型图

刻度、标签和图例

xlim xticks xticklabels
范围 刻度位置 刻度标签

标题、轴标签、刻度以及刻度标签

1
2
3
4
5
fig = plt.figure(); ax = fig.add_subplot(1,1,1)
ax.plot(randn(1000).cumsum())
ax.set_title('My first matplotlib plot')
ax.set_xlabel('Stages')
plt.show()

图8-8 用于演示xticks的简单线形图

添加图例

1
2
3
4
5
6
7
# 方式一：传入参数label
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') # 添加图例
plt.show()

图8-8 用于演示xticks的简单线形图

图注解以及在Subplot上绘图

1
2
3
4
5
6
7
8
9
10
11
fig = plt.figure()
ax = fig.add_subplot(1,1,1)
# 创建块对象
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(shp) 添加到subplot中
ax.add_patch(rect)
ax.add_patch(circ)
ax.add_patch(pgon)
plt.show()

图8-12 由三个块图形组成的图

将图标保存到文件

1
2
3
4
5
6
7
8
9
10
plt.savefig('figpath.svg')
plt.savefig('figpath.pdf')
# # dpi-分辨率，bbox_inches-剪除图标周围空白部分
plt.savefig('figpath.png', dpi=400, bbox_inches= 'tight')
# 以上都是存到磁盘，也可以存入文件型对象
from io import StringIO
buffer = StringIO()
plt.savefig(buffer)
plot_data = buffer.getvalue()
# 对在Web上提供生成的图片很实用

matplotlib配置

1
2
3
4
5
6
7
# 如设置图像大小
plt.rc('figure', figsize=10*10)
# 关键字参数，写成字典
font_options = {'family': 'monospace',
                'weight': 'bold',
                'size': 'small'}
plt.rc('font', **font_options)

pandas中的绘图函数

线形图

简单Series图表

1
2
3
4
5
from pandas import Series
from pandas import DataFrame
s = Series(np.random.randn(10).cumsum(), index=np.arange(0,100,10))
s.plot()
plt.show()

图8-13 简单Series图表

简单的DataFrame图表

1
2
3
df = DataFrame(np.random.randn(10,4).cumsum(0), columns=['A','B','C','D'],index=np.arange(0,100,10))
df.plot()
plt.show()

图8-14 简单的DataFrame图表

柱状图

1
2
3
4
5
6
# kind="bar"(垂直柱状图)，kind="barh"(水平柱状图)
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)
plt.show()

图8-15 水平和垂直柱状图

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
df = DataFrame(np.random.rand(6,4), index=['one', 'two', 'three', 'four', 'five', 'six'],
               columns=pd.Index(['A','B','C','D'],name='Genus'))

# print df
# Genus         A         B         C         D
# one    0.465771  0.579470  0.053485  0.863450
# two    0.550022  0.855826  0.967881  0.792683
# three  0.666868  0.536417  0.245592  0.839482
# four   0.439348  0.676450  0.637932  0.106940
# five   0.606376  0.609878  0.498459  0.010276
# six    0.923550  0.243204  0.422216  0.979446

df.plot(kind='bar')
plt.savefig('图8-16 DataFrame柱状图')
# plt.show()
# 设置stacked=True生成DataFrame的堆积柱状图，每行都堆积在一起
df.plot(kind='barh', stacked=True, alpha=0.5)
plt.savefig('图8-17 DataFrame堆积柱状图')
# plt.show()
1
2
3
4
5
6
7
8
9
10
11
12
tips = pd.read_csv('../pydata-book-master/ch08/tips.csv')
party_counts = pd.crosstab(tips.day, tips.size)
# print party_counts
# col_0  1708
# day
# Fri      19
# Sat      87
# Sun      76
# Thur     62

party_counts = party_counts.ix[:, 2:5]
print party_counts

实战：绘制地图-图形化显示海地地震危机数据

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
data = pd.read_csv('../pydata-book-master/ch08/Haiti.csv')
# print data
# 拿出时间戳和位置信息
# print data[['INCIDENT DATE', 'LATITUDE', 'LONGITUDE']][:10]
#       INCIDENT DATE   LATITUDE   LONGITUDE
# 0  05/07/2010 17:26  18.233333  -72.533333
# 1  28/06/2010 23:06  50.226029    5.729886
# 2  24/06/2010 16:21  22.278381  114.174287
# 3  20/06/2010 21:59  44.407062    8.933989
# 4  18/05/2010 16:26  18.571084  -72.334671
# 5  26/04/2010 13:14  18.593707  -72.310079
# 6  26/04/2010 14:19  18.482800  -73.638800
# 7  26/04/2010 14:27  18.415000  -73.195000
# 8  15/03/2010 10:58  18.517443  -72.236841
# 9  15/03/2010 11:00  18.547790  -72.410010

# 消息类型
# print data['CATEGORY'][:6]
# 0          1. Urgences | Emergency, 3. Public Health,
# 1    1. Urgences | Emergency, 2. Urgences logistiqu...
# 2    2. Urgences logistiques | Vital Lines, 8. Autr...
# 3                            1. Urgences | Emergency,
# 4                            1. Urgences | Emergency,
# 5                       5e. Communication lines down,
# Name: CATEGORY, dtype: object

# 异常的地理位置
# print data.describe()
#             Serial     LATITUDE    LONGITUDE
# count  3593.000000  3593.000000  3593.000000
# mean   2080.277484    18.611495   -72.322680
# std    1171.100360     0.738572     3.650776
# min       4.000000    18.041313   -74.452757
# 25%    1074.000000    18.524070   -72.417500
# 50%    2163.000000    18.539269   -72.335000
# 75%    3088.000000    18.561820   -72.293570
# max    4052.000000    50.226029   114.174287

# 清除错误位置信息并移除缺失分类信息：
data = data[(data.LATITUDE > 18) & (data.LATITUDE < 20) &
            (data.LONGITUDE > -75) & (data.LONGITUDE < -70)
            & data.CATEGORY.notnull()]

# 编写函数获取所有分类的列表，将各个分类信息拆分为编码和英语名称
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()

# 测试get_english是否正常
# print get_english('2. Urgences logistiques | Vital Lines')
# ('2', 'Vital Lines')

all_cats = get_all_categories(data.CATEGORY)
# 生成器表达式
english_mapping = dict(get_english(x) for x in all_cats)

# print english_mapping['2a']
# Food Shortage

# print english_mapping['6c']
# Earthquake and aftershocks
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
# 抽取分类编码，构造全0DataFrame
def get_code(seq):
    return [x.split('.')[0] for x in seq if x]

all_codes = get_code(all_cats)
code_index = pd.Index(pd.unique(all_codes))
dummy_frame = DataFrame(np.zeros((len(data), len(code_index))), index=data.index, columns=code_index)
# print dummy_frame.ix[:, :6]
#         1   1a   1b   1c   1d    2
# 0     0.0  0.0  0.0  0.0  0.0  0.0
# 4     0.0  0.0  0.0  0.0  0.0  0.0
# 5     0.0  0.0  0.0  0.0  0.0  0.0
# 6     0.0  0.0  0.0  0.0  0.0  0.0
# 7     0.0  0.0  0.0  0.0  0.0  0.0
# 8     0.0  0.0  0.0  0.0  0.0  0.0
# 9     0.0  0.0  0.0  0.0  0.0  0.0
# 10    0.0  0.0  0.0  0.0  0.0  0.0

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_'))
# print data.ix[:,10:15]
#       category_1  category_1a  category_1b  category_1c  category_1d
# 0            1.0          0.0          0.0          0.0          0.0
# 4            1.0          0.0          0.0          0.0          0.0
# 5            0.0          0.0          0.0          0.0          0.0
# 6            0.0          0.0          0.0          0.0          0.0
# 7            0.0          0.0          0.0          0.0          0.0
# 8            0.0          0.0          0.0          0.0          0.0
# 9            0.0          0.0          0.0          0.0          0.0
# 10           0.0          1.0          0.0          0.0          0.0

# Python绘制地图依赖于basemap工具集(http://matplotlib.github.com/basemap）插件
# 绘制黑白海地地图
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):
    # 创建极球面投影的Basemap实例
    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')

    # 绘制海岸线、州届、国界以及地图边界
    m.drawcoastlines()
    m.drawstates()
    m.drawcountries()
    return m

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]
    # 计算地图的投影坐标
    x, y = m(cat_data.LONGITUDE, cat_data.LATITUDE)

    m.plot(x, y, 'k.', alpha=0.5)
    ax.set_title('%s: %s' % (code, english_mapping[code]))

扫一扫，分享到微信

tag:

    缺失模块。
    1、请确保node版本大于6.2
    2、在博客根目录（注意不是yilia-plus根目录）执行以下命令：
    npm i hexo-generator-json-content --save

    3、在根目录_config.yml里添加配置： 

      jsonContent:
    meta: false
    pages: false
    posts:
      title: true
      date: true
      path: true
      text: false
      raw: false
      content: false
      slug: false
      updated: false
      comments: false
      link: false
      permalink: false
      excerpt: false
      categories: false
      tags: true