本项目是利用五年左右的世界地震数据，通过python的pandas库、matplotlib库、basemap库等进行数据可视化，绘制出地震散点图。主要代码如下所示
|
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
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
|
from __future__ import division
import pandas as pd
from pandas import series,dataframe
import numpy as np
from matplotlib.patches import polygon
chi_provinces = ['北京','天津','上海','重庆',
'河北','山西','辽宁','吉林',
'黑龙江','江苏','浙江','安徽',
'福建','江西','山东','河南',
'湖北','湖南','广东','海南',
'四川','贵州','云南','陕西',
'甘肃','青海','*','内蒙古',
'广西','*','宁夏','*',
'香港','澳门'] #list of chinese provinces
def is_in_china(str):
if str[:2] in chi_provinces:
return true
else:
return false
def convert_data_2014(x):
try:
return float(x.strip())
except valueerror:
return x
except attributeerror:
return x
def format_lat_lon(x):
try:
return x/100
except(typeerror):
return np.nan
df = pd.read_excel(r'c:/users/ggws/desktop/shuju/201601-12.xls')
df = df.append(pd.read_excel(r'c:/users/ggws/desktop/shuju/201201-12.xls'),ignore_index = true)
df = df.append(pd.read_excel(r'c:/users/ggws/desktop/shuju/shuju.xls'),ignore_index = true)
df = df.append(pd.read_excel(r'c:/users/ggws/desktop/shuju/201501-12.xls'),ignore_index = true)
df_2014 = pd.read_excel(r'c:/users/ggws/desktop/shuju/201401-12.xls') #have to introduce statics of 2014 independently because the format and the type of data of specific column in this data set are different from others
df['longitude'] = df['longitude'].apply(convert_data_2014)
df['latitude'] = df['latitude'].apply(convert_data_2014)
df_2014['longitude'] = df_2014['longitude'].apply(convert_data_2014)
df_2014['latitude'] = df_2014['latitude'].apply(convert_data_2014)
df = df.append(df_2014,ignore_index = true)
df = df[['latitude','longitude','magnitude','referenced place','time']] #only save four columns as valuable statics
df[['longitude','latitude']] = df[['longitude','latitude']].applymap(format_lat_lon) #use function "applymap" to convert the format of the longitude and latitude statics
df = df.dropna(axis=0,how='any') #drop all rows that have any nan values
format_magnitude = lambda x: float(str(x).strip('ml'))
df['magnitude'] = df['magnitude'].apply(format_magnitude)
#df = df[df['referenced place'].apply(is_in_china)]
lon_mean = (df['longitude'].groupby(df['referenced place'])).mean()
lat_mean = (df['latitude'].groupby(df['referenced place'])).mean()
group_counts = (df['magnitude'].groupby(df['referenced place'])).count()
after_agg_data = pd.concat([lon_mean,lat_mean,group_counts], axis = 1 )
after_agg_data.rename(columns = {'magnitude':'counts'} , inplace = true)
#aggregate after grouping the data
after_sorted_data = after_agg_data.sort_values(by = 'counts',ascending = false)
new_index = np.arange(len(after_sorted_data.index))
after_sorted_data.index = new_index
paint_data = after_sorted_data[after_sorted_data['counts']>=after_sorted_data['counts'][80]]
import matplotlib.pyplot as plt
from mpl_toolkits.basemap import basemap
plt.figure(figsize=(16,8))
m = basemap()
m.readshapefile(r'c:/users/ggws/desktop/jb/gadm36_chn_1', 'states', drawbounds=true)
ax = plt.gca()
'''
for nshape,seg in enumerate (m.states):
poly = polygon(seg,facecolor = 'r')
ax.add_patch(poly)
'''
m.drawcoastlines(linewidth=0.5)
m.drawcountries(linewidth=0.5)
m.shadedrelief()
for indexs in df.index:
lon2,lat2 = df.loc[indexs].values[1],df.loc[indexs].values[0]
x,y = m(lon2,lat2)
m.plot(x,y,'ro',markersize = 0.5) #获取经度值
'''
for indexs in after_sorted_data.index[:80]:
lon,lat = after_sorted_data.loc[indexs].values[0],after_sorted_data.loc[indexs].values[1]
x,y = m(lon,lat)
m.plot(x,y,'wo',markersize = 10*(after_sorted_data.loc[indexs].values[2]/after_sorted_data.loc[0].values[2]))
'''
plt.title("worldwide earthquake")
plt.show()
#indexs-len(df.index)+80
|
效果如下
以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持服务器之家。
原文链接：https://blog.csdn.net/qq_36228216/article/details/86680246