单列数据的频率分布直方图

from matplotlib import pyplot as plt

# 计算组数
d = 800 # 组距
num_bins = int((max(a) - min(a)) // d)
print(max(a), min(a), max(a) - min(a))
print(num_bins)
# 设置图形大小
plt.figure(figsize=(20, 13), dpi=80)
# 绘制直方图
plt.hist(a, num_bins)
# 设置x轴的刻度
plt.xticks(range(int(min(a)), int(max(a)) + d, d))
plt.grid()
plt.show()

 np.histogram()分箱的使用

from matplotlib import pyplot as plt
import pandas as pd
import numpy as np
rawdata = pd.read_csv('./data/svr_result.csv')
rawdata=rawdata["test"]
print(rawdata.head())
# 计算组数
d = 0.5 # 组距
num_bins = np.histogram(rawdata)[1].size
print(num_bins)
# 设置图形大小
plt.figure(figsize=(20, 13), dpi=180)
# 绘制直方图
plt.hist(rawdata, num_bins)
# 设置x轴的刻度
plt.xticks(np.histogram(rawdata)[1])
plt.grid()
plt.show()

 自动化使用plt绘图

from matplotlib import pyplot as plt
import pandas as pd
import numpy as np
plt.rcParams['font.sans-serif']=['SimHei']
rawdata = pd.read_csv('./data/svr_result.csv')
rawdata=rawdata["test"]
print(rawdata.head())
n, bins, patches = plt.hist(x=rawdata, bins='auto', color='#0504aa',
    alpha=0.7, rwidth=0.85)
plt.grid(axis='y', alpha=0.75)
plt.xlabel('Value')
plt.ylabel('Frequency')
plt.title('测试集分布直方图')
# plt.text(23, 45, r'$\mu=15, b=3$')for a,b in zip(x,y):
#     plt.text(a, b+0.05, '%.0f' % b, ha='center', va= 'bottom',fontsize=7)#设置标签
maxfreq = n.max()
# 设置y轴的上限
plt.ylim(ymax=np.ceil(maxfreq / 10) * 10 if maxfreq % 10 else maxfreq + 10)
plt.show()

 seaborn方式(强推荐)

import matplotlib.pyplot as plt
import matplotlib as mpl
import pandas as pd
import numpy as np
import seaborn as sns
# 制作频数分布表

# 分割区间
data_split = pd.cut(rawdata, [0, 2, 4, 6, 8, 10], labels=[u"(0,2]", u"(2,4]", u"(4,6]", u"(6,8]", u"(8,10]"])
#计算每个区间的频数并按上面的labels调整顺序
freq_chart = data_split.value_counts()
freq_chart = freq_chart.sort_index()
#保存为一个频率分布字典
freq_dict= {'section': freq_chart.index, 'frequency': freq_chart.values}
#将对应的频率分布字典转化为pd文件
freq_data = pd.DataFrame(freq_dict)

ax = plt.figure(figsize=(10, 5)).add_subplot(111)
sns.barplot(x="section", y="frequency", data=freq_data, palette="Set3")  # palette设置颜色
#设置y轴高度 y轴高度最好为最大都轴超20%
ax.set_ylim([0, 20000])
ax.set_title('频数分布图', size=40)
#设置字体大小
plt.xticks(fontsize=30)
plt.yticks(fontsize=30)
#设置数据标签
for x, y in zip(range(5), freq_data.frequency):
    ax.text(x, y, '%d' % y, ha='center', va='bottom', fontsize=30, color='grey')
plt.show()

import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns
#只用调整bin_list分布方式即可自绘图

# 制作频数分布表
bin_list = [0.0,0.05,0.10,0.15,0.20]
plt.rcParams["font.sans-serif"] = ["SimHei"]
rawdata = pd.read_excel("./data/train_result.xlsx")
print(rawdata.describe())
rawdata = rawdata['result']
# 分割区间
split_str = []
for i in range(len(bin_list)):
    if (i < len(bin_list) - 1):
        split_str.append(str(bin_list[i]) + '~' + str(bin_list[i + 1]))
    else:
        break
data_split = pd.cut(rawdata, bin_list,
                    labels=split_str)

# 计算每个区间的频数并按上面的labels调整顺序
freq_chart = data_split.value_counts()
freq_chart = freq_chart.sort_index()
# 保存为一个频率分布字典
freq_dict = {'section': freq_chart.index, 'frequency': freq_chart.values}
# 将对应的频率分布字典转化为pd文件
freq_data = pd.DataFrame(freq_dict)

ax = plt.figure(figsize=(100, 35)).add_subplot(111)
sns.barplot(x="section", y="frequency", data=freq_data, palette="Set3")  # palette设置颜色
# 设置y轴高度 y轴高度最好为最大都轴超20%
ax.set_ylim([0, max(int(freq_data["frequency"]+0.2*freq_data["frequency"]))])
ax.set_title('总体训练集预测频数0-0.2分布', size=100)
# 设置字体大小
plt.axhline(y=2000, ls=":", c="red", lw=4, label='2000分界线')  # 添加水平直线 lw粗细
plt.legend()
plt.xticks(fontsize=50)
plt.yticks(fontsize=50)
# 设置数据标签
for x, y in zip(range(len(bin_list)), freq_data.frequency):
    ax.text(x, y, '%d' % y, ha='center', va='bottom', fontsize=50, color='black')
plt.show()