数据分析常用图表的绘制

import matplotlib.pyplot as plt
import numpy as np

1、Subplots

plt.figure()
# 表示1行2列，现在在第一个子图上进行操作
plt.subplot(1, 2, 1)
linear_data = np.arange(1, 9)
plt.plot(linear_data, '-o')
exponential_data = linear_data ** 2
plt.subplot(1, 2, 2)
plt.plot(exponential_data, '-x')
plt.subplot(1, 2, 1)
plt.plot(exponential_data, '-x')
# 保证子图中坐标范围一致
plt.figure()
ax1 = plt.subplot(1, 2, 1)
plt.plot(linear_data, '-o')
ax2 = plt.subplot(1, 2, 2, sharey=ax1)
plt.plot(exponential_data, '-x')
fig, ((ax1, ax2, ax3), (ax4, ax5, ax6)) = plt.subplots(2, 3,                                                    sharex=True, sharey=True)
ax5.plot(exponential_data, '-')

2、直方图

fig, ((ax1, ax2), (ax3, ax4)) = plt.subplots(2, 2, sharex=True)
axs = [ax1, ax2, ax3, ax4]

for n in range(len(axs)):
    sample_size = 10 ** (n + 1)
    sample = np.random.normal(loc=0., scale=1., size=sample_size)
    # 默认bin的个数为10
    axs[n].hist(sample)
    axs[n].set_title('n={}'.format(sample_size))
fig, ((ax1, ax2), (ax3, ax4)) = plt.subplots(2, 2, sharex=True)
axs = [ax1, ax2, ax3, ax4]

for n in range(len(axs)):
    sample_size = 10 ** (n + 1)
    sample = np.random.normal(loc=0., scale=1., size=sample_size)
    # bin设为100
    axs[n].hist(sample, bins=100)
    axs[n].set_title('n={}'.format(sample_size))

# 使用gridspec和直方图绘制一个复杂分析图
import matplotlib.gridspec as gridspec

x = np.random.random(size=10000)
y = np.random.normal(loc=0., scale=1., size=10000)

plt.figure()
gspec = gridspec.GridSpec(3, 3)

top_hist = plt.subplot(gspec[0, 1:])
side_hist = plt.subplot(gspec[1:, 0])
lower_right = plt.subplot(gspec[1:, 1:])

lower_right.scatter(x, y)
top_hist.hist(x, bins=100, normed=True)
side_hist.hist(y, bins=100, orientation='horizontal', normed=True)
side_hist.invert_xaxis()

3、盒形图

import pandas as pd
# 正态分布采样
normal_sample = np.random.normal(loc=0., scale=1., size=10000)
# 随机数采样
random_sample = np.random.random(size=10000)
# gamma分布采样
gamma_sample = np.random.gamma(2, size=10000)

df = pd.DataFrame({'normal': normal_sample,
                  'random': random_sample,
                  'gamma': gamma_sample})
plt.figure()
plt.boxplot(df['normal'], whis='range')
plt.figure()
plt.boxplot([df['normal'], df['random'], df['gamma']], whis='range')
plt.figure()
plt.boxplot([df['normal'], df['random'], df['gamma']])
plt.show()

4、热图

plt.figure()
y = np.random.normal(loc=0., scale=1., size=10000)
x = np.random.random(size=10000)
plt.hist2d(x, y, bins=25)

plt.figure()
y = np.random.normal(loc=0., scale=1., size=10000)
x = np.random.random(size=10000)
plt.hist2d(x, y, bins=100)
plt.colorbar()
plt.show()