{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Reading & Writing Files"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Plain Text"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Read"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['1. This is file foo.',\n",
" '2. Just for demo, no practical utilities.',\n",
" '3. hahahah',\n",
" '4. This is line 4',\n",
" '',\n",
" '6. Line 5 (previous line) is empty']"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"with open('prac/foo.txt', 'r', encoding='utf-8') as f:\n",
" file = [line.strip() for line in f]\n",
"\n",
"file"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Write"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"with open('prac/write.txt', 'w', encoding='utf-8') as f:\n",
" for line in file:\n",
" f.write(line + '\\n')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## JSON"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Read JSON\n",
"\n",
"#### Read from file"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"373\n"
]
},
{
"data": {
"text/plain": [
"{'alias': 'midnightlab',\n",
" 'availableLayouts': ['classic'],\n",
" 'canPost': False,\n",
" 'canUseNickname': True,\n",
" 'createdAt': '2016-05-14T19:15:15.698Z',\n",
" 'description': '午夜實驗室10/6、10/7即將在華山登場！這裏提供大家交流活動資訊與討論，請大家要遵守 Dcard 板規喔！',\n",
" 'fullyAnonymous': False,\n",
" 'id': '7f125e07-4460-4ea5-80b5-33f0e9aafa0c',\n",
" 'ignorePost': False,\n",
" 'invisible': True,\n",
" 'isSchool': False,\n",
" 'limitCountries': [],\n",
" 'limitStage': 0,\n",
" 'mediaThreshold': {},\n",
" 'name': '午夜實驗室',\n",
" 'nsfw': False,\n",
" 'postCount': {'last30Days': 0},\n",
" 'postThumbnail': {'size': 'small'},\n",
" 'read': False,\n",
" 'shouldCategorized': False,\n",
" 'subcategories': [],\n",
" 'subscribed': False,\n",
" 'subscriptionCount': 1837,\n",
" 'titlePlaceholder': '',\n",
" 'topics': ['午夜實驗室'],\n",
" 'updatedAt': '2018-11-05T03:24:32.914Z'}"
]
},
"execution_count": 1,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import json\n",
"\n",
"with open(\"prac/dcard_forums.json\") as f:\n",
" data = json.load(f)\n",
"\n",
"print(len(data))\n",
"data[0]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Read from string"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'a': 1, 'b': 2, 'c': 3, 'd': 4, 'e': 5}"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"jsonData = \"\"\"\n",
"{\"a\":1,\n",
"\"b\":2,\n",
"\"c\":3,\n",
"\"d\":4,\n",
"\"e\":5}\n",
"\"\"\"\n",
"\n",
"json.loads(jsonData)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Write JSON\n",
"\n",
"#### Write to file"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"with open(\"prac/afile.json\", \"w\", encoding=\"utf-8\") as f:\n",
" json.dump(data, f, ensure_ascii=False)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'{\"a\": 1, \"b\": 2}'"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"a_dict = {'a': 1, 'b': 2}\n",
"json.dumps(a_dict)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## CSV"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Read: `DictReader`"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[OrderedDict([('證券代碼', '4938 '),\n",
" ('簡稱', '和碩 '),\n",
" ('年月日', '20110103'),\n",
" ('開盤價(元)', ' 29.32'),\n",
" ('最高價(元)', ' 29.42'),\n",
" ('最低價(元)', ' 29.21'),\n",
" ('收盤價(元)', ' 29.28'),\n",
" ('成交值(千元)', ' 89508')]),\n",
" OrderedDict([('證券代碼', '4938 '),\n",
" ('簡稱', '和碩 '),\n",
" ('年月日', '20110104'),\n",
" ('開盤價(元)', ' 29.42'),\n",
" ('最高價(元)', ' 29.56'),\n",
" ('最低價(元)', ' 29.28'),\n",
" ('收盤價(元)', ' 29.42'),\n",
" ('成交值(千元)', ' 107340')]),\n",
" OrderedDict([('證券代碼', '4938 '),\n",
" ('簡稱', '和碩 '),\n",
" ('年月日', '20110105'),\n",
" ('開盤價(元)', ' 29.42'),\n",
" ('最高價(元)', ' 29.42'),\n",
" ('最低價(元)', ' 28.16'),\n",
" ('收盤價(元)', ' 28.72'),\n",
" ('成交值(千元)', ' 193077')])]\n"
]
}
],
"source": [
"import csv\n",
"import pprint as pp\n",
"\n",
"fpath = 'prac/stock.tsv'\n",
"file = open(fpath, \"r\", encoding='cp950')\n",
"csvFile = csv.DictReader(file, delimiter='\\t')\n",
"\n",
"pp.pprint(list(csvFile)[:3])\n",
"file.close()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"4938 89508\n",
"4938 107340\n",
"4938 193077\n",
"4938 259533\n",
"4938 330576\n"
]
}
],
"source": [
"fpath = 'prac/stock.tsv'\n",
"file = open(fpath, \"r\", encoding='cp950')\n",
"csvFile = csv.DictReader(file, delimiter='\\t')\n",
"\n",
"lineCount = 1\n",
"for row in csvFile:\n",
" print(int(row['證券代碼']), int(row['成交值(千元)']))\n",
" if lineCount == 5: break \n",
" lineCount += 1\n",
" \n",
"file.close()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Read: `reader`"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"FIELDNAMES: ['證券代碼', '簡稱', '年月日', '開盤價(元)', '最高價(元)', '最低價(元)', '收盤價(元)', '成交值(千元)']\n",
"['4938', '和碩', '20110103', '29.32', '29.42', '29.21', '29.28', '89508']\n",
"['4938', '和碩', '20110104', '29.42', '29.56', '29.28', '29.42', '107340']\n",
"['4938', '和碩', '20110105', '29.42', '29.42', '28.16', '28.72', '193077']\n",
"['4938', '和碩', '20110106', '28.93', '29.00', '28.02', '28.20', '259533']\n",
"['4938', '和碩', '20110107', '28.02', '28.16', '27.22', '27.32', '330576']\n"
]
}
],
"source": [
"with open(fpath, 'r', encoding='cp950') as f:\n",
" csvFile = csv.reader(f, delimiter='\\t')\n",
" header = next(csvFile)\n",
" print('FIELDNAMES:', header)\n",
" \n",
" lineCount = 1\n",
" for row in csvFile:\n",
" row = [ele.strip() for ele in row]\n",
" print(row)\n",
" \n",
" if lineCount == 5: break\n",
" lineCount += 1"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Read: Pandas"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>證券代碼</th>\n",
" <th>簡稱</th>\n",
" <th>年月日</th>\n",
" <th>開盤價(元)</th>\n",
" <th>最高價(元)</th>\n",
" <th>最低價(元)</th>\n",
" <th>收盤價(元)</th>\n",
" <th>成交值(千元)</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4938</td>\n",
" <td>和碩</td>\n",
" <td>20110103</td>\n",
" <td>29.32</td>\n",
" <td>29.42</td>\n",
" <td>29.21</td>\n",
" <td>29.28</td>\n",
" <td>89508</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>4938</td>\n",
" <td>和碩</td>\n",
" <td>20110104</td>\n",
" <td>29.42</td>\n",
" <td>29.56</td>\n",
" <td>29.28</td>\n",
" <td>29.42</td>\n",
" <td>107340</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4938</td>\n",
" <td>和碩</td>\n",
" <td>20110105</td>\n",
" <td>29.42</td>\n",
" <td>29.42</td>\n",
" <td>28.16</td>\n",
" <td>28.72</td>\n",
" <td>193077</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4938</td>\n",
" <td>和碩</td>\n",
" <td>20110106</td>\n",
" <td>28.93</td>\n",
" <td>29.00</td>\n",
" <td>28.02</td>\n",
" <td>28.20</td>\n",
" <td>259533</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4938</td>\n",
" <td>和碩</td>\n",
" <td>20110107</td>\n",
" <td>28.02</td>\n",
" <td>28.16</td>\n",
" <td>27.22</td>\n",
" <td>27.32</td>\n",
" <td>330576</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1229</th>\n",
" <td>4938</td>\n",
" <td>和碩</td>\n",
" <td>20151224</td>\n",
" <td>66.06</td>\n",
" <td>66.40</td>\n",
" <td>64.97</td>\n",
" <td>65.06</td>\n",
" <td>318025</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1230</th>\n",
" <td>4938</td>\n",
" <td>和碩</td>\n",
" <td>20151225</td>\n",
" <td>64.89</td>\n",
" <td>65.64</td>\n",
" <td>64.89</td>\n",
" <td>65.64</td>\n",
" <td>108529</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1231</th>\n",
" <td>4938</td>\n",
" <td>和碩</td>\n",
" <td>20151228</td>\n",
" <td>66.06</td>\n",
" <td>66.06</td>\n",
" <td>65.31</td>\n",
" <td>65.73</td>\n",
" <td>141813</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1232</th>\n",
" <td>4938</td>\n",
" <td>和碩</td>\n",
" <td>20151229</td>\n",
" <td>65.23</td>\n",
" <td>65.23</td>\n",
" <td>62.54</td>\n",
" <td>63.05</td>\n",
" <td>731616</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1233</th>\n",
" <td>4938</td>\n",
" <td>和碩</td>\n",
" <td>20151230</td>\n",
" <td>63.30</td>\n",
" <td>63.55</td>\n",
" <td>60.53</td>\n",
" <td>61.37</td>\n",
" <td>916988</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1234 rows × 8 columns</p>\n",
"</div>"
],
"text/plain": [
" 證券代碼 簡稱 年月日 開盤價(元) 最高價(元) 最低價(元) 收盤價(元) 成交值(千元)\n",
"0 4938 和碩 20110103 29.32 29.42 29.21 29.28 89508\n",
"1 4938 和碩 20110104 29.42 29.56 29.28 29.42 107340\n",
"2 4938 和碩 20110105 29.42 29.42 28.16 28.72 193077\n",
"3 4938 和碩 20110106 28.93 29.00 28.02 28.20 259533\n",
"4 4938 和碩 20110107 28.02 28.16 27.22 27.32 330576\n",
"... ... ... ... ... ... ... ... ...\n",
"1229 4938 和碩 20151224 66.06 66.40 64.97 65.06 318025\n",
"1230 4938 和碩 20151225 64.89 65.64 64.89 65.64 108529\n",
"1231 4938 和碩 20151228 66.06 66.06 65.31 65.73 141813\n",
"1232 4938 和碩 20151229 65.23 65.23 62.54 63.05 731616\n",
"1233 4938 和碩 20151230 63.30 63.55 60.53 61.37 916988\n",
"\n",
"[1234 rows x 8 columns]"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import pandas as pd\n",
"\n",
"df = pd.read_csv(\"prac/stock.tsv\", sep=\"\\t\", encoding=\"cp950\")\n",
"df"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Write `PdDataFrame.to_csv()`"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"df.to_csv(\"prac/stock.csv\", index=False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Write `PdDataFrame.to_json()`"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>證券代碼</th>\n",
" <th>簡稱</th>\n",
" <th>年月日</th>\n",
" <th>開盤價(元)</th>\n",
" <th>最高價(元)</th>\n",
" <th>最低價(元)</th>\n",
" <th>收盤價(元)</th>\n",
" <th>成交值(千元)</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4938</td>\n",
" <td>和碩</td>\n",
" <td>20110103</td>\n",
" <td>29.32</td>\n",
" <td>29.42</td>\n",
" <td>29.21</td>\n",
" <td>29.28</td>\n",
" <td>89508</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>4938</td>\n",
" <td>和碩</td>\n",
" <td>20110104</td>\n",
" <td>29.42</td>\n",
" <td>29.56</td>\n",
" <td>29.28</td>\n",
" <td>29.42</td>\n",
" <td>107340</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 證券代碼 簡稱 年月日 開盤價(元) 最高價(元) 最低價(元) 收盤價(元) 成交值(千元)\n",
"0 4938 和碩 20110103 29.32 29.42 29.21 29.28 89508\n",
"1 4938 和碩 20110104 29.42 29.56 29.28 29.42 107340"
]
},
"execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.iloc[:2,:]"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {},
"outputs": [],
"source": [
"df.iloc[:2,:].to_json(\"prac/stock.json\", orient=\"records\", force_ascii=False)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Details of `to_json()`\n",
"\n",
"See [doc](https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.to_json.html#pandas.DataFrame.to_json) for details."
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'[{\"證券代碼\":4938,\"簡稱\":\"和碩 \",\"年月日\":20110103,\"開盤價(元)\":29.32,\"最高價(元)\":29.42,\"最低價(元)\":29.21,\"收盤價(元)\":29.28,\"成交值(千元)\":89508},{\"證券代碼\":4938,\"簡稱\":\"和碩 \",\"年月日\":20110104,\"開盤價(元)\":29.42,\"最高價(元)\":29.56,\"最低價(元)\":29.28,\"收盤價(元)\":29.42,\"成交值(千元)\":107340}]'"
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"json_str = df.iloc[:2,:].to_json(orient=\"records\", force_ascii=False)\n",
"json_str"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[{'年月日': 20110103,\n",
" '成交值(千元)': 89508,\n",
" '收盤價(元)': 29.28,\n",
" '最低價(元)': 29.21,\n",
" '最高價(元)': 29.42,\n",
" '簡稱': '和碩 ',\n",
" '證券代碼': 4938,\n",
" '開盤價(元)': 29.32},\n",
" {'年月日': 20110104,\n",
" '成交值(千元)': 107340,\n",
" '收盤價(元)': 29.42,\n",
" '最低價(元)': 29.28,\n",
" '最高價(元)': 29.56,\n",
" '簡稱': '和碩 ',\n",
" '證券代碼': 4938,\n",
" '開盤價(元)': 29.42}]"
]
},
"execution_count": 37,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"json.loads(json_str)"
]
}
],
"metadata": {
"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": "3.7.1"
}
},
"nbformat": 4,
"nbformat_minor": 2
}