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）。
  
  

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 h. m' O9 S/ H  i

过程介绍

, B1 `7 W  z% Z* D( H8 B3 k; \2 H

1. 导入包

[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

. _8 e! Q0 _; C; C+ }

2.导入数据 处理数据
+ Y' e0 ]2 U4 R8 p
. d/ |% [* N' x' Z# H) v- w

[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]

) q, l2 q: k8 c' B6 i: D8 t
3. 计算风速数据
2 ~+ j% b0 w5 i
8 s' w# j  V- S! A. K7 Z
! I5 w3 v9 g- l. l

[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

& U% a3 B+ S9 t. y9 a# v1 a
1 x4 |" R4 J: X9 {  [5 l' _( T4. 年度数据可视化
1 J: z# i7 D+ |, s' u/ L
- N/ a$ g! ^# K0 S8 w+ C

[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("$Wind Speed / m.s^{-1}$")

# F6 N  L' w' D2 E7 @8 P- K; [
* p+ O5 a, h( F
% J2 a4 m1 h8 X5. 月维度数据可视化
9 b/ H+ i* ^; [' C: U( P2 a4 A

[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")

; _8 b# I5 n3 @8 y* y/ D! {

6.天维度数据可视化
4 V2 w3 P* V. z2 ~! V- I

• 计算天数据
  0 P* w" I. F' u' t. d/ Z
    O; c$ y, z. |# K1 }

[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
  
  8 \& }5 i# x7 C, y) J( u' ]4 j

[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')

4 g0 q0 j- b1 r  c  z. p  z/ l

- ~8 ~2 u# V5 n6 @2 Y1 I1.天维度数据做趋势拆解
+ T, X- _7 m5 i; B+ A" S

[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 C& [$ r6 q. }! Z. ], o" p

               
1 ]0 o5 O1 \! K/ q! n6 q& r1 O" i; W

: N% X; F2 r" C
4 L0 R% v( r9 W& K# `1 q6 l' D! o  e
8 g* S; ?$ `1 t: H* n; _