first commit

.gitignore.txt

@@ -0,0 +1,18 @@
+# Created by https://www.toptal.com/developers/gitignore/api/jupyternotebooks
+# Edit at https://www.toptal.com/developers/gitignore?templates=jupyternotebooks
+
+### JupyterNotebooks ###
+# gitignore template for Jupyter Notebooks
+# website: http://jupyter.org/
+
+.ipynb_checkpoints
+*/.ipynb_checkpoints/*
+
+# IPython
+profile_default/
+ipython_config.py
+
+# Remove previous ipynb_checkpoints
+#   git rm -r .ipynb_checkpoints/
+
+# End of https://www.toptal.com/developers/gitignore/api/jupyternotebooks

.ipynb_checkpoints/Province-checkpoint.ipynb

@@ -0,0 +1,188 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "c7d079e5",
+   "metadata": {},
+   "source": [
+    "# import pandas และอ่านข้อมูลไฟล์ทั้งหมดที่ต้องการ"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "566fde0d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "Subdistrict = pd.read_excel('ข้อมูลตำบลหรือแขวง.xls')\n",
+    "Province = pd.read_excel('ข้อมูลจังหวัด.xls')\n",
+    "District = pd.read_excel('ข้อมูลอำเภอหรือเขต.xls')\n",
+    "ThepExcel = pd.read_excel('ThepExcel-Thailand-Tambon.xlsx',sheet_name=1)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "be712d63",
+   "metadata": {},
+   "source": [
+    "# เลือก Column , เรียงลำดับค่าที่ต้องการจะใช้ และ DROP ตัวที่มีค่าซ้ำกันทิ้ง"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "2f14aa43",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "provinces_en = ThepExcel[['ProvinceThai','ProvinceEng']].sort_values(by=['ProvinceThai']).drop_duplicates(['ProvinceEng'],ignore_index=True)\n",
+    "ThepExcel2 = ThepExcel[['TambonID','TambonThaiShort','TambonEngShort']].sort_values(by=['TambonID']).drop_duplicates(['TambonID'],ignore_index=True)\n",
+    "Subdistrict = Subdistrict.sort_values(by=['PROVINCE_ID'])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ab44cac2",
+   "metadata": {},
+   "source": [
+    "#  เลือกเฉพาะ Column ที่ต้องการ และ จัดการเรื่องรหัสจังหวัด อำเภอและตำบลให้สามารถ Merge เข้ากันได้"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "ced4198b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "Province['PROVINCE_CODE_select'] = Province['PROVINCE_CODE'].apply(lambda x: str(x)[:2])\n",
+    "District['DISTRICT_CODE_select'] = District['DISTRICT_CODE'].apply(lambda x: str(x)[:2])\n",
+    "District['DISTRICT_CODE_select_Sub'] = District['DISTRICT_CODE'].apply(lambda x: str(x)[:4])\n",
+    "Subdistrict['SUBDISTRICT_CODE_select'] = Subdistrict['SUBDISTRICT_CODE'].apply(lambda x: str(x)[:4])\n",
+    "Subdistrict['SUBDISTRICT_CODE_select6'] = Subdistrict['SUBDISTRICT_CODE'].apply(lambda x: int (str(x)[:6]))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "53a49c89",
+   "metadata": {},
+   "source": [
+    "# Merge ข้อมูลแต่ละส่วนเข้าด้วยกัน โดยใช้ ชื่อและรหัสจังหวัด อำเภอและตำบล "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "20f217d2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "Province = Province.merge(provinces_en, left_on='PROVINCE_NAME',right_on='ProvinceThai')\n",
+    "df = Province.merge(District, left_on='PROVINCE_CODE_select',right_on='DISTRICT_CODE_select')\n",
+    "df1 = df.merge(Subdistrict, left_on='DISTRICT_CODE_select_Sub',right_on='SUBDISTRICT_CODE_select')\n",
+    "df2 = df1.merge(ThepExcel2, left_on='SUBDISTRICT_CODE_select6', right_on='TambonID' , how='left')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ffa24f59",
+   "metadata": {},
+   "source": [
+    "# เรียงลำดับ Column โดยเลือกเฉพาะ Column ที่ต้องการ และเปลี่ยนชื่อ Column ให้เข้าใจง่ายขึ้น"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "e33c0782",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df2 = df2[['PROVINCE_CODE_select','PROVINCE_NAME','ProvinceEng','DISTRICT_NAME','DISTRICT_NAME_ENG','SUBDISTRICT_NAME',\n",
+    "'TambonEngShort','TambonID']].rename(columns={'PROVINCE_CODE_select':'PROVINCE_CODE','ProvinceEng':'PROVINCE_NAME_ENG','TambonEngShort':'SUBDISTRICT_NAME_ENG'})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "082cca53",
+   "metadata": {},
+   "source": [
+    "# เช็คค่า null หรือหาว่า Column ไหนมีค่าว่างบ้าง"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "12cd25cc",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "PROVINCE_CODE           0\n",
+       "PROVINCE_NAME           0\n",
+       "PROVINCE_NAME_ENG       0\n",
+       "DISTRICT_NAME           0\n",
+       "DISTRICT_NAME_ENG       3\n",
+       "SUBDISTRICT_NAME        0\n",
+       "SUBDISTRICT_NAME_ENG    2\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df2.isnull().sum()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a1883112",
+   "metadata": {},
+   "source": [
+    "# สร้างไฟล์ ชื่อ MasterProvince โดยใช้ Encoding UTF-8-SIG"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "75171c18",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df2\n",
+    "df2.to_csv('MasterProvince.csv',encoding='utf-8-sig',index=False)"
+   ]
+  }
+ ],
+ "metadata": {
+  "interpreter": {
+   "hash": "4eef419ba9ceb6eca7081c30889866f44cdc1b4757b2edefb98cfaa8dd738cfa"
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}