从nc文件中提取风速数据并且进行时间序列分析

                                   本文目的

• 介绍了如何从nc文件中，提取风速数据；
• 介绍如何将风速数据转换成时间序列；
• 简单的时间序列的趋势拆解（首发）。
  0 h2 q& c& e; @3 z  A' q# {
  1 @4 b+ T3 D( h

代码链接

代码我已经放在Github上面了，免费分享使用，https://github.com/yuanzhoulvpi2 ... ree/main/python_GIS。

9 `$ l: B8 I5 W6 u$ Z

过程介绍

' v6 L5 c! }* }( v0 \, n, r, p& @

1. 导入包

2 H/ u$ {& v) X, d0 a+ ?

[Python] 纯文本查看 复制代码

# 基础的数据处理工具
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt # 可视化
import datetime # 处理python时间函数
import netCDF4 as nc  # 处理nc数据
from netCDF4 import num2date  # 处理nc数据
import geopandas as gpd  # 处理网格数据，shp之类的
import rasterio  # 处理tiff文件
from shapely.geometry import Point  # gis的一些逻辑判断
from cartopy import crs as ccrs  # 设置投影坐标系等
from tqdm import tqdm  # 打印进度条
from joblib import Parallel, delayed  # 并行
import platform  # 检测系统

tqdm.pandas()

# matplotlib 显示中文的问题
if platform.system() == 'Darwin':
    plt.rcParams["font.family"] = 'Arial Unicode MS'
elif platform.system() == 'Windows':
    plt.rcParams["font.family"] = 'SimHei'
else:
    pass

& U/ L1 F* ^; G7 x0 r
2.导入数据 处理数据
' |( w. ]+ l8 v0 m0 O
4 L$ {0 @$ s2 }/ H, {, p. L) a0 [
4 H  d" H# {2 u" b

[Python] 纯文本查看 复制代码

# 导入数据
nc_data = nc.Dataset("./数据集/GIS实践3/2016_2020.nc")

# 处理数据
raw_latitude = np.array(nc_data.variables['latitude'])
raw_longitude = np.array(nc_data.variables['longitude'])
raw_time = np.array(nc_data.variables['time'])
raw_u10 = np.array(nc_data.variables['u10'])
raw_v10 = np.array(nc_data.variables['v10'])
# 提取缺失值，并且将缺失值替换
missing_u10_value = nc_data.variables['u10'].missing_value
missing_v10_value = nc_data.variables['v10'].missing_value
raw_v10[raw_v10 == missing_v10_value] = np.nan
raw_u10[raw_u10 == missing_u10_value] = np.nan


# 处理时间
def cftime2datetime(cftime, units, format='%Y-%m-%d %H:%M:%S'):
    """
    将nc文件里面的时间格式 从cftime 转换到 datetime格式
    :param cftime:
    :param units:
    :param format:
    :return:
    """
    return datetime.datetime.strptime(num2date(times=cftime, units=units).strftime(format), format)

clean_time_data = pd.Series([cftime2datetime(i, units=str(nc_data.variables['time'].units)) for i in tqdm(raw_time)])
clean_time_data[:4]

5 z" `- c' L" s' d, t/ V: t3. 计算风速数据
$ v* ?* x7 ?  _

8 T+ v; S. @+ }$ @1 Q

[Python] 纯文本查看 复制代码

windspeed_mean = pd.Series([np.sqrt(raw_v10[i,:, :] ** 2 + raw_u10[i, :, :]**2).mean() for i in tqdm(range(clean_time_data.shape[0]))])

time_windspeed = pd.DataFrame({'time':clean_time_data,'mean_ws':windspeed_mean})
time_windspeed

4. 年度数据可视化

- o1 {  j$ q& @6 z% u9 u
7 o8 J% Y4 [, g6 {% z- [

[Python] 纯文本查看 复制代码

year_data = time_windspeed.groupby(time_windspeed.time.dt.year).agg(
    mean_ws = ('mean_ws', 'mean')
).reset_index()

# year_data

with plt.style.context('fivethirtyeight') as style:

    fig, ax = plt.subplots(figsize=(10,3), dpi=300)
    ax.plot(year_data['time'], year_data['mean_ws'], '-o',linewidth=3, ms=6)
    ax.set_xticks(year_data['time'])
    #
    #
    for i in range(year_data.shape[0]):
        ax.text(year_data.iloc[/size][/font][i][font=新宋体][size=3]['time']+0.1, year_data.iloc[/size][/font][i][font=新宋体][size=3]['mean_ws'], str(np.around(year_data.iloc[/size][/font][i][font=新宋体][size=3]['mean_ws'], 2)),
                bbox=dict(boxstyle='round', facecolor='white', alpha=0.5))
    #
    for i in ['top', 'right']:
        ax.spines[/size][/font][i][font=新宋体][size=3].set_visible(False)

    ax.set_title("各年平均风速")
    ax.set_ylabel("$Wind Speed / m.s^{-1}$")

- P  i! v# i' v+ u; o' }
+ r0 f! v0 J( g) V# L0 x
( r9 `) f1 q5 K; y+ r! E5. 月维度数据可视化

[Python] 纯文本查看 复制代码

month_data = time_windspeed.groupby(time_windspeed.time.dt.month).agg(
    mean_ws = ('mean_ws', 'mean')
).reset_index()


with plt.style.context('fivethirtyeight') as style:

    fig, ax = plt.subplots(figsize=(10,3), dpi=300)
    ax.plot(month_data['time'], month_data['mean_ws'], '-o',linewidth=3, ms=6)
    ax.set_xticks(month_data['time'])
    _ = ax.set_xticklabels(labels=[f'{i}月' for i in month_data['time']])


    for i in range(month_data.shape[0]):
        ax.text(month_data.iloc[/size][/font][i][font=新宋体][size=3]['time'], month_data.iloc[/size][/font][i][font=新宋体][size=3]['mean_ws']+0.05, str(np.around(month_data.iloc[/size][/font][i][font=新宋体][size=3]['mean_ws'], 2)),
                bbox=dict(boxstyle='round', facecolor='white', alpha=0.5))

    for i in ['top', 'right']:
        ax.spines[/size][/font][i][font=新宋体][size=3].set_visible(False)

    ax.set_title("各月平均风速")
    ax.set_ylabel("$Wind Speed / m.s^{-1}$")
    fig.savefig("month_plot.png")

- y5 M" o5 L1 l) ^

6.天维度数据可视化

• 计算天数据
  
  

[Python] 纯文本查看 复制代码

day_data = time_windspeed.groupby(time_windspeed.time.apply(lambda x: x.strftime('%Y-%m-%d'))).agg(
    mean_ws = ('mean_ws', 'mean')
).reset_index()

day_data['time'] = pd.to_datetime(day_data['time'])

day_data = day_data.set_index('time')
day_data.head()

• 可视化
  
  + D" w( [8 e% q/ F* Z

[Python] 纯文本查看 复制代码

# day_data.dtypes
fig, ax = plt.subplots(figsize=(20,4), dpi=300)
ax.plot(day_data.index, day_data['mean_ws'], '-o')
# ax.xaxis.set_ticks_position('none')
# ax.tick_params(axis="x", labelbottom=False)
ax.set_title("每天平均风速")
ax.set_ylabel("$Wind Speed / m.s^{-1}$")
ax.set_xlabel("date")
fig.savefig('day_plot.png')

* d" b. f9 r& J* v3 y1 T

1.天维度数据做趋势拆解

: v& I) B5 o+ |# _, v3 p* P

[Python] 纯文本查看 复制代码

# 导入包
from statsmodels.tsa.seasonal import seasonal_decompose
from dateutil.parser import parse
# 乘法模型
result_mul = seasonal_decompose(day_data['mean_ws'], model="multilicative", extrapolate_trend='freq')
result_add = seasonal_decompose(day_data['mean_ws'], model="additive", extrapolate_trend='freq')
font = {'family': 'serif',
        'color': 'darkred',
        'weight': 'normal',
        'size': 16,
        }
# 画图

with plt.style.context('classic'):
    fig, ax = plt.subplots(ncols=2, nrows=4, figsize=(22, 15), sharex=True, dpi=300)


    def plot_decompose(result, ax, index, title, fontdict=font):
        ax[0, index].set_title(title, fontdict=fontdict)
        result.observed.plot(ax=ax[0, index])
        ax[0, index].set_ylabel("Observed")

        result.trend.plot(ax=ax[1, index])
        ax[1, index].set_ylabel("Trend")

        result.seasonal.plot(ax=ax[2, index])
        ax[2, index].set_ylabel("Seasonal")

        result.resid.plot(ax=ax[3, index])
        ax[3, index].set_ylabel("Resid")


    plot_decompose(result=result_add, ax=ax, index=0, title="Additive Decompose", fontdict=font)
    plot_decompose(result=result_mul, ax=ax, index=1, title="Multiplicative Decompose", fontdict=font)
    fig.savefig('decompose.png')

2 X9 m8 O7 Y1 }

               
. K# g( w0 d6 k, Z

( E0 h( ~0 e- e1 j- }8 ^! n

9 C( C* K0 N! l2 D  S1 p3 T' _
" c2 B- w+ L# }7 j  A1 m  F# d