tynbl.github.io
Pandas及Seaborn绘图
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%matplotlib notebook
1. Pandas绘图
# 可用的绘图样式
plt.style.available
['seaborn-dark-palette',
'seaborn-muted',
'seaborn-whitegrid',
'seaborn-colorblind',
'seaborn',
'seaborn-pastel',
'seaborn-darkgrid',
'seaborn-bright',
'seaborn-paper',
'ggplot',
'dark_background',
'seaborn-talk',
'fivethirtyeight',
'_classic_test',
'bmh',
'seaborn-notebook',
'seaborn-poster',
'seaborn-deep',
'seaborn-ticks',
'seaborn-white',
'seaborn-dark',
'grayscale',
'classic']
# 设置绘图样式
plt.style.use('seaborn-colorblind')
DataFrame绘图
np.random.seed(100)
df = pd.DataFrame({'A': np.random.randn(365).cumsum(0),
'B': np.random.randn(365).cumsum(0) + 20,
'C': np.random.randn(365).cumsum(0) - 20},
index=pd.date_range('2017/1/1', periods=365))
df.head()
| A | B | C | |
|---|---|---|---|
| 2017-01-01 | -1.749765 | 21.091816 | -19.638975 |
| 2017-01-02 | -1.407085 | 20.686733 | -17.061997 |
| 2017-01-03 | -0.254049 | 21.223177 | -15.474676 |
| 2017-01-04 | -0.506485 | 19.091862 | -14.786998 |
| 2017-01-05 | 0.474835 | 19.354939 | -14.805210 |
df.plot()
<IPython.core.display.Javascript object>
<matplotlib.axes._subplots.AxesSubplot at 0x9d6b518>
df.plot('A', 'B', kind='scatter')
<IPython.core.display.Javascript object>
<matplotlib.axes._subplots.AxesSubplot at 0x63e0550>
# 颜色(c)和大小(s)有'B'列的数据决定
ax = df.plot('A', 'C', kind='scatter',
c='B', s=df['B'], colormap='viridis')
<IPython.core.display.Javascript object>
C:\Anaconda2\envs\py35\lib\site-packages\matplotlib\collections.py:877: RuntimeWarning: invalid value encountered in sqrt
scale = np.sqrt(self._sizes) * dpi / 72.0 * self._factor
# 设置坐标为相同比例
ax.set_aspect('equal')
df.plot(kind='box')
<IPython.core.display.Javascript object>
<matplotlib.axes._subplots.AxesSubplot at 0xb7fb208>
df.plot(kind='hist', alpha=0.7)
<IPython.core.display.Javascript object>
<matplotlib.axes._subplots.AxesSubplot at 0xceca438>
df.plot(kind='kde')
<IPython.core.display.Javascript object>
<matplotlib.axes._subplots.AxesSubplot at 0xc5b9780>
pandas.tools.plotting
iris = pd.read_csv('iris.csv')
iris.head()
| SepalLength | SepalWidth | PetalLength | PetalWidth | Name | |
|---|---|---|---|---|---|
| 0 | 5.1 | 3.5 | 1.4 | 0.2 | Iris-setosa |
| 1 | 4.9 | 3.0 | 1.4 | 0.2 | Iris-setosa |
| 2 | 4.7 | 3.2 | 1.3 | 0.2 | Iris-setosa |
| 3 | 4.6 | 3.1 | 1.5 | 0.2 | Iris-setosa |
| 4 | 5.0 | 3.6 | 1.4 | 0.2 | Iris-setosa |
# 用于查看变量间的关系
pd.plotting.scatter_matrix(iris)
<IPython.core.display.Javascript object>
array([[<matplotlib.axes._subplots.AxesSubplot object at 0x000000000F79EBA8>,
<matplotlib.axes._subplots.AxesSubplot object at 0x000000001038CA90>,
<matplotlib.axes._subplots.AxesSubplot object at 0x00000000103DABE0>,
<matplotlib.axes._subplots.AxesSubplot object at 0x000000001041C860>],
[<matplotlib.axes._subplots.AxesSubplot object at 0x0000000010469D68>,
<matplotlib.axes._subplots.AxesSubplot object at 0x00000000104AB5C0>,
<matplotlib.axes._subplots.AxesSubplot object at 0x00000000104F9710>,
<matplotlib.axes._subplots.AxesSubplot object at 0x000000001053CF60>],
[<matplotlib.axes._subplots.AxesSubplot object at 0x000000001058F3C8>,
<matplotlib.axes._subplots.AxesSubplot object at 0x00000000105D2668>,
<matplotlib.axes._subplots.AxesSubplot object at 0x000000001061FB70>,
<matplotlib.axes._subplots.AxesSubplot object at 0x00000000106654A8>],
[<matplotlib.axes._subplots.AxesSubplot object at 0x0000000011680898>,
<matplotlib.axes._subplots.AxesSubplot object at 0x000000000D31B550>,
<matplotlib.axes._subplots.AxesSubplot object at 0x00000000116E3AC8>,
<matplotlib.axes._subplots.AxesSubplot object at 0x0000000011731A20>]], dtype=object)
# 用于查看多遍量分布
plt.figure()
pd.plotting.parallel_coordinates(iris, 'Name')
<IPython.core.display.Javascript object>
<matplotlib.axes._subplots.AxesSubplot at 0x11718898>
2. Seaborn绘图
import seaborn as sns
np.random.seed(100)
v1 = pd.Series(np.random.normal(0, 10, 1000), name='v1')
v2 = pd.Series(2 * v1 + np.random.normal(60, 15, 1000), name='v2')
# 通过matplotlib绘图
plt.figure()
plt.hist(v1, alpha=0.7, bins=np.arange(-50, 150, 5), label='v1')
plt.hist(v2, alpha=0.7, bins=np.arange(-50, 150, 5), label='v2')
plt.legend()
<IPython.core.display.Javascript object>
<matplotlib.legend.Legend at 0x1270d5c0>
plt.figure()
plt.hist([v1, v2], histtype='barstacked', normed=True)
v3 = np.concatenate((v1, v2))
sns.kdeplot(v3)
<IPython.core.display.Javascript object>
<matplotlib.axes._subplots.AxesSubplot at 0x134566a0>
# 使用seaborn绘图
plt.figure()
sns.distplot(v3)
<IPython.core.display.Javascript object>
<matplotlib.axes._subplots.AxesSubplot at 0x13be8240>
# 使用seaborn绘图
plt.figure()
sns.jointplot(v1, v2, alpha=0.4)
<IPython.core.display.Javascript object>
<IPython.core.display.Javascript object>
<seaborn.axisgrid.JointGrid at 0x1437b8d0>
# 使用seaborn绘图
plt.figure()
grid = sns.jointplot(v1, v2, alpha=0.4)
grid.ax_joint.set_aspect('equal')
<IPython.core.display.Javascript object>
<IPython.core.display.Javascript object>
plt.figure()
sns.jointplot(v1, v2, kind='hex')
<IPython.core.display.Javascript object>
<IPython.core.display.Javascript object>
<seaborn.axisgrid.JointGrid at 0x166f1438>
plt.figure()
sns.jointplot(v1, v2, kind='kde')
<IPython.core.display.Javascript object>
<IPython.core.display.Javascript object>
<seaborn.axisgrid.JointGrid at 0x16efa6a0>
iris = pd.read_csv('iris.csv')
iris.head()
| SepalLength | SepalWidth | PetalLength | PetalWidth | Name | |
|---|---|---|---|---|---|
| 0 | 5.1 | 3.5 | 1.4 | 0.2 | Iris-setosa |
| 1 | 4.9 | 3.0 | 1.4 | 0.2 | Iris-setosa |
| 2 | 4.7 | 3.2 | 1.3 | 0.2 | Iris-setosa |
| 3 | 4.6 | 3.1 | 1.5 | 0.2 | Iris-setosa |
| 4 | 5.0 | 3.6 | 1.4 | 0.2 | Iris-setosa |
sns.pairplot(iris, hue='Name', diag_kind='kde')
<IPython.core.display.Javascript object>
<seaborn.axisgrid.PairGrid at 0x133a4ba8>
plt.figure()
plt.subplot(121)
sns.swarmplot('Name', 'PetalLength', data=iris)
plt.subplot(122)
sns.violinplot('Name', 'PetalLength', data=iris)
C:\Anaconda2\envs\py35\lib\site-packages\matplotlib\pyplot.py:524: RuntimeWarning: More than 20 figures have been opened. Figures created through the pyplot interface (`matplotlib.pyplot.figure`) are retained until explicitly closed and may consume too much memory. (To control this warning, see the rcParam `figure.max_open_warning`).
max_open_warning, RuntimeWarning)
<IPython.core.display.Javascript object>
<matplotlib.axes._subplots.AxesSubplot at 0x144e4400>