• 新興科技：大數據與人工智慧

擷取2020年校園空品資料

• 講義

• 目前Google Colab程式已安裝 pandas, matplotlib, numpy, seaborn, statsmodels, warnings 等套件，然而，我們還需另外自行安裝兩個未預先安裝好的套件：kats 和 calplot，安裝方式如下：

  !pip install --upgrade pip
  
  # Kats
  !pip install kats ax-platform statsmodels
  
  # calplot
  !pip install calplot
  
  !pip install pmdarima

   

  待安裝完畢後，使用下列的指令來行匯入相關的套件，以完成本單元的準備工作：

  import warnings
  import calplot
  import pandas as pd
  import numpy as np
  import matplotlib as mpl
  import matplotlib.pyplot as plt
  import statsmodels.api as sm
  import os, zipfile
  import pmdarima as pm
  
  from datetime import datetime, timedelta
  from dateutil import parser as datetime_parser
  from statsmodels.tsa.stattools import adfuller, kpss
  from statsmodels.tsa.seasonal import seasonal_decompose
  from kats.detectors.outlier import OutlierDetector
  from kats.detectors.cusum_detection import CUSUMDetector
  from kats.consts import TimeSeriesData, TimeSeriesIterator
  from IPython.core.pylabtools import figsize

  把2020年的歷史數據擷取下來，解壓縮後，只取用某一台機器所發出的資料，然後針對這台機器的資料進行數據分析。

  !mkdir Air CSV_Air
  
  !wget -O Air/2020.zip "https://history.colife.org.tw/?r=/download&path=L%2Bepuuawo%2BWTgeizqi%2FkuK3noJTpmaJf5qCh5ZyS56m65ZOB5b6u5Z6L5oSf5ris5ZmoLzIwMjAuemlw"
  
  #開始進行解壓縮
  folder = 'Air'
  extension_zip = '.zip'
  extension_csv = '.csv'
  
  for subfolder in os.listdir(folder):
      path = f'{folder}/{subfolder}'
      if os.path.isdir(path):
          for item in os.listdir(path):
              if item.endswith(extension_zip):
                  file_name = f'{path}/{item}'
                  zip_ref = zipfile.ZipFile(file_name)
                  zip_ref.extractall(path)
                  zip_ref.close()
  
          for item in os.listdir(path):
            path2 = f'{path}/{item}'
            if os.path.isdir(path2):
              for it in os.listdir(path2):
                if it.endswith(extension_zip):
                  file_name = f'{path2}/{it}'
                  zip_ref = zipfile.ZipFile(file_name)
                  zip_ref.extractall('CSV_Air') # decide path
                  zip_ref.close()
            elif item.endswith(extension_csv):
              os.rename(path2, f'CSV_Air/{item}')

   

  folder = 'CSV_Air'
  extension_csv = '.csv'
  id = '74DA38F208E2'
  
  air = pd.DataFrame()
  for item in os.listdir(folder):
    file_name = f'{folder}/{item}'
    df = pd.read_csv(file_name)
    if 'pm25' in list(df.columns):
      df.rename({'pm25':'PM25'}, axis=1, inplace=True)
    filtered = df.query(f'device_id==@id')
    air = pd.concat([air, filtered], ignore_index=True)
  air.dropna(subset=['timestamp'], inplace=True)
  
  for i, row in air.iterrows():
    aware = datetime_parser.parse(str(row['timestamp']))
    naive = aware.replace(tzinfo=None)
    air.at[i, 'timestamp'] = naive
  air.set_index('timestamp', inplace=True)
  
  !rm -rf Air CSV_Air

   

  air.drop(columns=['device_id', 'SiteName'], inplace=True)
  air.sort_values(by='timestamp', inplace=True)
  air.info()
  print(air.head())

   

  plt.figure(figsize=(15, 10), dpi=60)
  plt.plot(air[:]["PM25"])
  
  plt.xlabel("Date")
  plt.ylabel("PM2.5")
  plt.title("PM2.5 Time Series Plot")
  
  plt.tight_layout()
  
  plt.show()

  

  air_hour = air.resample('H').mean() #每小時的平均
  air_day = air.resample('D').mean()  #每日的平均
  air_month = air.resample('M').mean()  #每月的平均
  
  print(air_hour.head())
  print(air_day.head())
  print(air_month.head())

  # cmap: 設定呈現的顏色色盤 (https://matplotlib.org/stable/gallery/color/colormap_reference.html)
  # textformat: 設定圖中數字呈現的樣式
  pl1 = calplot.calplot(data = air_day['PM25'], cmap = 'GnBu', textformat = '{:.0f}', 
  											figsize = (24, 12), suptitle = "PM25 by Month and Year")