update,

.gitattributes

@@ -0,0 +1,31 @@
+*.mp4 filter=lfs diff=lfs merge=lfs
+*.zip filter=lfs diff=lfs merge=lfs
+*.7z filter=lfs diff=lfs merge=lfs
+*.tar.gz filter=lfs diff=lfs merge=lfs
+*.jpg filter=lfs diff=lfs merge=lfs
+*.png filter=lfs diff=lfs merge=lfs
+*.avif filter=lfs diff=lfs merge=lfs
+*.webm filter=lfs diff=lfs merge=lfs
+*.mkv filter=lfs diff=lfs merge=lfs
+
+# Documents
+*.doc	diff=astextplain
+*.DOC	diff=astextplain
+*.docx	diff=astextplain
+*.DOCX	diff=astextplain
+*.dot	diff=astextplain
+*.DOT	diff=astextplain
+*.pdf	diff=astextplain
+*.PDF	diff=astextplain
+*.rtf	diff=astextplain
+*.RTF	diff=astextplain
+
+*.gif filter=lfs diff=lfs merge=lfs
+*.GIF filter=lfs diff=lfs merge=lfs
+*.bmp filter=lfs diff=lfs merge=lfs
+*.BMP filter=lfs diff=lfs merge=lfs
+*.tiff filter=lfs diff=lfs merge=lfs
+*.TIFF filter=lfs diff=lfs merge=lfs
+*.wav filter=lfs diff=lfs merge=lfs
+*.WAV filter=lfs diff=lfs merge=lfs
+*.log filter=lfs diff=lfs merge=lfs

.gitignore

@@ -0,0 +1 @@
+**/~*.*

gitUpdate.sh

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+
+set -ex
+
+git add .
+git commit -m'update,'
+
+git push

meta.md

@@ -0,0 +1,5 @@
+---
+tags: MSc, Alan Ho
+---
+
+https://filetransfer.io/data-package/qrjzX2rx#link

quotation2/notes.md

@@ -0,0 +1,32 @@
+V:
+2bcd 我自己本身做咗，但係覺得唔係好啱
+3A就唔識做
+最後第四題都唔太識🙂‍↔️
+
+L:
+Q1: 你想我做左佢算定係要講埋你知點做?
+你可以做咗先，然之後我自己理解吓
+
+Q2: 幾時要?
+我下個禮拜四(21/Nov) 2100交
+
+咦，咁 2b,c,d 我洗唔洗做?
+點為之 3A?
+第4題我做?
+
+
+Sorry 應該係Q3 part 2: who are the top4 coaches leading the most
+number of Athletes ?
+Q4 就你做
+Q2 bcd就睇價錢再決定🙏🏻🙏🏻
+
+
+Q2 HKD350
+
+Q3 2 HKD 200
+1. Read the 4 csvs to be your pandas data frame into your kernel.
+2. In athletes.csv and coaches.xlsx, who are the top 4 coaches leading the most
+number of Athletes ?
+
+
+Q4 HKD 300

task1/archive/helloworld.json

@@ -0,0 +1,10 @@
+[
+  {
+    "id": "1",
+    "name": "helloworld"
+  },
+  {
+    "id": "2",
+    "name": "hellohell"
+  }
+]

task1/archive/notes.md

@@ -0,0 +1 @@
+https://colab.research.google.com/drive/1mdhOdWbnqwfk5RalwNqEj6IBnV7_LUia#scrollTo=cSea-HnRSxKV

task1/archive/spices.json

@@ -0,0 +1,77 @@
+{
+  "HGV": { "space": 0, "spaceDIS": 0, "spaceEV": 0, "spaceUNL": 0 },
+  "LGV": { "space": 0, "spaceDIS": 0, "spaceEV": 0, "spaceUNL": 0 },
+  "address": {
+    "buildingName": "Kai Tak Cruise Terminal",
+    "buildingNo": "33",
+    "dcDistrict": "Kwun Tong District",
+    "floor": "1",
+    "region": "KLN",
+    "streetName": "Shing Fung Road",
+    "subDistrict": "Kowloon Bay"
+  },
+  "carpark_Type": "multi-storey",
+  "coach": { "space": 0, "spaceDIS": 0, "spaceEV": 0, "spaceUNL": 0 },
+  "contactNo": "+852 3465 6888, 09:30-18:00 Mon-Fri, except public holiday",
+  "creationDate": "2016-08-16 10:03:56",
+  "displayAddress": "1st floor, Kai Tak Cruise Terminal, 33 Shing Fung Road, Kowloon Bay, KLN",
+  "district": "Kwun Tong District",
+  "facilities": ["disabilities", "evCharger"],
+  "gracePeriods": [{ "minutes": 10 }],
+  "heightLimits": [{ "height": 2 }],
+  "lang": "en_US",
+  "latitude": 22.3062049,
+  "longitude": 114.21309471,
+  "modifiedDate": "2024-01-03 13:28:25",
+  "motorCycle": { "space": 0, "spaceDIS": 0, "spaceEV": 0, "spaceUNL": 0 },
+  "name": "Kai Tak Cruise Terminal Car Park 1",
+  "nature": "commercial",
+  "openingHours": [
+    {
+      "excludePublicHoliday": "False",
+      "periodEnd": "23:00",
+      "periodStart": "07:00",
+      "weekdays": ["MON", "TUE", "WED", "THU", "FRI", "SAT", "SUN", "PH"]
+    }
+  ],
+  "opening_status": "OPEN",
+  "park_Id": "10",
+  "paymentMethods": ["octopus", "visa"],
+  "privateCar": {
+    "hourlyCharges": [
+      {
+        "covered": "covered",
+        "excludePublicHoliday": "True",
+        "periodEnd": "23:00",
+        "periodStart": "07:00",
+        "price": 15,
+        "remark": "",
+        "type": "hourly",
+        "usageMinimum": 1,
+        "weekdays": ["MON", "TUE", "WED", "THU", "FRI"]
+      },
+      {
+        "covered": "covered",
+        "excludePublicHoliday": "False",
+        "periodEnd": "23:00",
+        "periodStart": "07:00",
+        "price": 20,
+        "remark": "",
+        "type": "hourly",
+        "usageMinimum": 1,
+        "weekdays": ["SAT", "SUN", "PH"]
+      }
+    ],
+    "space": 112,
+    "spaceDIS": 0,
+    "spaceEV": 0,
+    "spaceUNL": 0
+  },
+  "publishedDate": "2018-12-12 12:22:47",
+  "renditionUrls": {
+    "banner": "https://sps-opendata.pilotsmartke.gov.hk/rest/getRendition/fs-1%3A693265207413252869411532657339312395903827562313.JPG/banner.png",
+    "square": "https://sps-opendata.pilotsmartke.gov.hk/rest/getRendition/fs-1%3A693265207413252869411532657339312395903827562313.JPG/square.png",
+    "thumbnail": "https://sps-opendata.pilotsmartke.gov.hk/rest/getRendition/fs-1%3A693265207413252869411532657339312395903827562313.JPG/thumbnail.png"
+  },
+  "website": "http://www.kaitakcruiseterminal.com.hk/"
+}

task1/archive/task1.py

@@ -0,0 +1,36 @@
+# https://api.data.gov.hk/v1/carpark-info-vacancy?data=vacancy&vehicleTypes=privateCar
+import requests
+from pprint import pprint
+import json
+
+url = "https://api.data.gov.hk/v1/carpark-info-vacancy"
+params = {
+    "data": "vacancy",
+    "vehicleTypes": "privateCar"
+}
+
+response = requests.get(url, params=params)
+js_result_vacancy = response.json()['results']
+
+url = "https://api.data.gov.hk/v1/carpark-info-vacancy"
+
+response = requests.get(url)
+js_result_all = response.json()['results']
+
+output = []
+for jrv in js_result_vacancy:
+  for jra in js_result_all:
+    if jrv['park_Id'] == jra['park_Id']:
+      output.append(jra)
+      break
+
+js_row = output[0]
+
+pprint(js_row)
+pprint("length of json: "+str(len(output)))
+
+# Store js_result into js_result.json
+with open('js_result_o.json', 'w') as outfile:
+    json.dump(output, outfile, indent=2)
+
+task1_json = output

task1/archive/task1_fufill_answer.py

@@ -0,0 +1,20 @@
+# https://api.data.gov.hk/v1/carpark-info-vacancy?data=vacancy&vehicleTypes=privateCar
+import requests
+from pprint import pprint
+
+url = "https://api.data.gov.hk/v1/carpark-info-vacancy"
+
+response = requests.get(url)
+js_result = response.json()['results']
+
+js_row = js_result[0]
+
+pprint(js_row)
+pprint("length of json: "+str(len(js_result)))
+
+
+import json
+
+# Store js_result into js_result.json
+with open('js_result.json', 'w') as outfile:
+    json.dump(js_result, outfile, indent=2)

task1/archive/task1_fufill_question.py

@@ -0,0 +1,18 @@
+# https://api.data.gov.hk/v1/carpark-info-vacancy?data=vacancy&vehicleTypes=privateCar
+import requests
+from pprint import pprint
+
+url = "https://api.data.gov.hk/v1/carpark-info-vacancy"
+params = {
+    "data": "vacancy",
+    "vehicleTypes": "privateCar"
+}
+
+response = requests.get(url, params=params)
+js_result = response.json()['results']
+
+
+js_row = js_result[0]
+
+pprint(js_row)
+pprint("length of json: "+str(len(js_result)))

task1/archive/task2A.py

@@ -0,0 +1,17 @@
+import requests
+from pprint import pprint
+
+url = "https://api.data.gov.hk/v1/carpark-info-vacancy"
+
+response = requests.get(url)
+js_result = response.json()['results']
+
+js_row = js_result[0]
+pprint(js_row)
+pprint("length of json: "+str(len(js_result)))
+
+def get_url_image(js_row):
+  return None if js_row.get('renditionUrls', {}).get("square") == None else js_row['renditionUrls']['square']
+
+
+pprint(get_url_image(js_row))

task1/archive/task2B copy.py

@@ -0,0 +1,17 @@
+# %pip install beautifulsoup4
+
+from pprint import pprint
+
+import requests
+from bs4 import BeautifulSoup
+
+def scrape_h1():
+    url = 'http://example.com'
+    res = requests.get(url)
+    soup = BeautifulSoup(res.text, 'html.parser')
+    h1 = soup.find('h1').text
+    return h1
+
+ph_dates = scrape_h1()
+
+pprint(ph_dates)

task1/archive/task2B.py

@@ -0,0 +1,31 @@
+# %pip install beautifulsoup4
+
+from pprint import pprint
+import re
+import requests
+from bs4 import BeautifulSoup
+
+txt_month =["January", "February", "March", "April", "May", "June", "July", "August", "September", "October", "November", "December"]
+
+def formatNumber(number):
+   return number.zfill(2)
+
+def txtMonthToIntMonth(txtMonth):
+  return formatNumber(str((txt_month.index(txtMonth)+1)))
+
+def scrape_holiday():
+    output = []
+    url = 'https://www.gov.hk/en/about/abouthk/holiday/2024.htm'
+    res = requests.get(url)
+    soup = BeautifulSoup(res.text, 'html.parser')
+    h1s = soup.select('tr>td.date')
+    for h1 in h1s[1:]:
+        temp = re.split(r'\s', h1.text)
+        temp1 = '2024-'+txtMonthToIntMonth(temp[1])+ '-'+ formatNumber(temp[0])
+        output.append(temp1)
+    pprint(output)
+    return output
+
+ph_dates = scrape_holiday()
+
+pprint(ph_dates)

task1/archive/task2c.py

@@ -0,0 +1,52 @@
+# get_todayinfo(js_row, ph_dates)
+# get_todayinfo(js_row, ph_dates, '2024-12-25')
+
+import datetime
+import json
+from pprint import pprint
+
+js_row = {}
+with open('spices.json') as f:
+    js_row = json.load(f)
+
+ph_dates = [
+  '2024-10-18',
+]
+
+def get_todayinfo(js_row, ph_dates, today_date_str = datetime.datetime.today().strftime('%Y-%m-%d')):
+  given_date = datetime.datetime.strptime(today_date_str, '%Y-%m-%d')
+  weekdays = ['MON', 'TUE', 'WED', 'THU', 'FRI', 'SAT', 'SUN']
+  txt_weekday =  "PH" if today_date_str in  ph_dates else weekdays[given_date.weekday()]
+  pprint((today_date_str,ph_dates,txt_weekday))
+
+  output = {
+    'periodStart': '',
+    'periodEnd': '',
+    'price': 0,
+    'space': 0,
+    'today': today_date_str,
+    'today_weekday': txt_weekday
+    }
+  
+  if (js_row.get('privateCar') != None):
+      jp = js_row['privateCar']
+      if (jp.get('space') != None):
+        output['space'] = js_row['privateCar']['space']
+      if (jp.get('hourlyCharges') != None):
+        for i in js_row['privateCar']['hourlyCharges']:
+          if txt_weekday in i['weekdays']:
+              output['periodStart'] = i['periodStart']
+              output['periodEnd'] = i['periodEnd']
+              output['price'] = i['price']
+              break
+
+
+  output['today'] = today_date_str
+  output['today_weekday'] = txt_weekday
+
+  
+  return output
+
+pprint(get_todayinfo(js_row, ph_dates))
+pprint(get_todayinfo(js_row, ph_dates,'2024-01-01'))
+pprint(get_todayinfo(js_row, ph_dates,'2024-10-18'))

task1/archive/task2d copy.py

@@ -0,0 +1,90 @@
+import pandas as pd
+import json
+import datetime
+from pprint import pprint
+
+test_json = []
+# Load and parse the JSON file
+with open('js_result.json', 'r') as file:
+    test_json = json.load(file)
+
+ph_dates = [
+  '2024-10-18',
+]
+
+
+task1_json = []
+# Load and parse the JSON file
+with open('task1.json', 'r') as file:
+    task1_json = json.load(file)
+
+
+def get_url_image(js_row):
+  url_image = ''
+
+  return None if js_row.get('renditionUrls', {}).get("square") == None else js_row['renditionUrls']['square']
+
+
+def get_todayinfo(js_row, ph_dates, today_date_str = datetime.datetime.today().strftime('%Y-%m-%d')):
+  given_date = datetime.datetime.strptime(today_date_str, '%Y-%m-%d')
+  weekdays = ['MON', 'TUE', 'WED', 'THU', 'FRI', 'SAT', 'SUN']
+  txt_weekday =  "PH" if today_date_str in  ph_dates else weekdays[given_date.weekday()]
+
+  output = {
+    'periodStart': '',
+    'periodEnd': '',
+    'price': 0,
+    'space': 0,
+    'today': today_date_str,
+    'today_weekday': txt_weekday
+    }
+  
+  if (js_row.get('privateCar') != None):
+      jp = js_row['privateCar']
+      if (jp.get('space') != None):
+        output['space'] = js_row['privateCar']['space']
+      if (jp.get('hourlyCharges') != None):
+        for i in js_row['privateCar']['hourlyCharges']:
+          if txt_weekday in i['weekdays']:
+              output['periodStart'] = i['periodStart']
+              output['periodEnd'] = i['periodEnd']
+              output['price'] = i['price']
+              break
+
+  output['today'] = today_date_str
+  output['today_weekday'] = txt_weekday
+
+  return output
+
+hodgepodge = []
+for jr in test_json:
+   hodgepodge.append({**jr, **get_todayinfo(jr, ph_dates), "url_image": get_url_image(jr)})
+
+output = []
+for hp in hodgepodge:
+   output.append({
+      "park_Id": hp.get('park_Id',""),
+      "name": hp.get('name',""),
+      "displayAddress": hp.get('displayAddress',""),
+      "district": hp.get('district',""),
+      "latitude": hp.get('latitude',""),
+      "longitude": hp.get('longitude',""),
+      "opening_status": hp.get('opening_status',""),
+      "facilities": hp.get('facilities',"") ,
+      "paymentMethods": hp.get('paymentMethods',"") ,
+      "modifiedDate": hp.get('modifiedDate',""),
+      'periodStart': hp.get('periodStart',""),
+      "url_image": hp.get('url_image',""),
+      'periodEnd': hp.get('periodEnd',""),
+      'price': hp.get('price',""),
+      'space': hp.get('space',""),
+      'today': hp.get('today',""),
+      'today_weekday': hp.get('today_weekday',""),
+   })
+
+pprint(output[0])
+
+# Translate the JSON data to a pandas DataFrame
+test_df = pd.DataFrame(test_json)
+
+print("done")

task1/archive/task2d.py

@@ -0,0 +1,94 @@
+import pandas as pd
+import json
+import datetime
+from pprint import pprint
+
+test_json = []
+# Load and parse the JSON file
+with open('js_result.json', 'r') as file:
+    test_json = json.load(file)
+
+ph_dates = [
+  '2024-10-18',
+]
+
+
+task1_json = []
+# Load and parse the JSON file
+with open('task1.json', 'r') as file:
+    task1_json = json.load(file)
+
+
+def get_url_image(js_row):
+  url_image = ''
+
+  return None if js_row.get('renditionUrls', {}).get("square") == None else js_row['renditionUrls']['square']
+
+task1_df = pd.DataFrame(task1_json)
+
+def get_todayinfo(js_row, ph_dates, today_date_str = datetime.datetime.today().strftime('%Y-%m-%d')):
+  given_date = datetime.datetime.strptime(today_date_str, '%Y-%m-%d')
+  weekdays = ['MON', 'TUE', 'WED', 'THU', 'FRI', 'SAT', 'SUN']
+  txt_weekday =  "PH" if today_date_str in  ph_dates else weekdays[given_date.weekday()]
+
+  output = {
+    'periodStart': '',
+    'periodEnd': '',
+    'price': 0,
+    'space': 0,
+    'today': today_date_str,
+    'today_weekday': txt_weekday
+    }
+  
+  if (js_row.get('privateCar') != None):
+      jp = js_row['privateCar']
+      if (jp.get('space') != None):
+        output['space'] = js_row['privateCar']['space']
+      if (jp.get('hourlyCharges') != None):
+        for i in js_row['privateCar']['hourlyCharges']:
+          if txt_weekday in i['weekdays']:
+              output['periodStart'] = i['periodStart']
+              output['periodEnd'] = i['periodEnd']
+              output['price'] = i['price']
+              break
+
+  output['today'] = today_date_str
+  output['today_weekday'] = txt_weekday
+
+  return output
+
+hodgepodge = []
+for jr in task1_json:
+   hodgepodge.append({**jr, **get_todayinfo(jr, ph_dates), "url_image": get_url_image(jr)})
+
+output = []
+for hp in hodgepodge:
+   output.append({
+      "park_Id": hp.get('park_Id',""),
+      "name": hp.get('name',""),
+      "displayAddress": hp.get('displayAddress',""),
+      "district": hp.get('district',""),
+      "latitude": hp.get('latitude',""),
+      "longitude": hp.get('longitude',""),
+      "opening_status": hp.get('opening_status',""),
+      "facilities": hp.get('facilities',"") ,
+      "paymentMethods": hp.get('paymentMethods',"") ,
+      "modifiedDate": hp.get('modifiedDate',""),
+      'periodStart': hp.get('periodStart',""),
+      "url_image": hp.get('url_image',""),
+      'periodEnd': hp.get('periodEnd',""),
+      'price': hp.get('price',""),
+      'space': hp.get('space',""),
+      'today': hp.get('today',""),
+      'today_weekday': hp.get('today_weekday',""),
+   })
+
+pprint(output[0])
+
+# Translate the JSON data to a pandas DataFrame
+test_df = pd.DataFrame(test_json)
+
+key_col = 'park_Id'
+new_df = test_df[[key_col, 'col2', 'col3']]
+
+print("done")

task1/archive/task3.py

@@ -0,0 +1,48 @@
+# https://api.data.gov.hk/v1/carpark-info-vacancy?data=vacancy&vehicleTypes=privateCar
+import requests
+from pprint import pprint
+
+url = "https://api.data.gov.hk/v1/carpark-info-vacancy"
+params = {
+    "data": "vacancy",
+    "vehicleTypes": "privateCar"
+}
+
+response = requests.get(url, params=params)
+js_result = response.json()['results']
+
+output = []
+for js_row in js_result:
+  if ((type(js_row.get('privateCar')) == type([]) ) and len(js_row.get('privateCar'))> 0):
+      if (js_row.get('privateCar')[0].get("vacancy_type",'-')== "A"):
+        output.append(js_row)
+
+test_json = [{
+    'park_Id': '10',
+    'privateCar': [{
+        'vacancy_type': 'A',
+        'vacancy': 29,
+        'lastupdate': '2024-10-18 16:04:59'
+    }]
+}]
+
+import pandas as pd
+
+# Create a DataFrame from the test_json
+df = pd.json_normalize(test_json, record_path=['privateCar'], meta='park_Id')
+
+
+# Extract the 'vacancy' column and flatten it
+vacancy_df = df[['park_Id', 'vacancy']]
+
+print(vacancy_df)
+
+
+pprint(output[0])
+pprint("length of json: "+str(len(output)))
+
+import json
+
+# Store output into task3_output.json
+with open('task3_output.json', 'w') as outfile:
+    json.dump(output, outfile, indent=2)

task1/archive/task4.py

@@ -0,0 +1,20 @@
+import json
+
+# Load js_result.json
+with open('js_result.json', 'r') as file:
+    js_result = json.load(file)
+
+# Load task3_output.json
+with open('task3_output.json', 'r') as file:
+    task3_output = json.load(file)
+
+
+output = []
+for js_row in js_result:
+  for t3 in task3_output:
+    if (js_row['park_Id'] == t3['park_Id']):
+      output.append({**js_row, 
+                     "t3_park_Id": t3['park_Id'],
+                     "t3_privateCar": t3['privateCar'],
+                     })
+      break

task1/notes.md

@@ -0,0 +1,5 @@
+quote HKD600
+
+HKD 200 received, Thanks.
+
+https://colab.research.google.com/drive/1gBOX9iMPVpqEGbkT3RSeH4jTQBzUykdF#scrollTo=LYIZvKU37xxR