Created
January 27, 2019 10:49
-
-
Save mrbkdad/126d2610a412cf1c412809554371a86c to your computer and use it in GitHub Desktop.
Python basic course 3
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"cells": [ | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"## 셀 명령\n", | |
"\n", | |
"- 시작 !" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"!dir" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": { | |
"scrolled": true | |
}, | |
"outputs": [], | |
"source": [ | |
"!type \"data\\GDPR Ticketing Report.csv\"" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"## Pandas\n", | |
"1. 엑셀 작업용 파이썬 라이브러리\n", | |
"2. 샘플 - GDPRS 자료\n", | |
"3. DataFrame, Series 객체" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"import pandas as pd" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"df = pd.read_csv(\"data/GDPR Ticketing 2019-01-20T22_51_51+0000.csv\")\n", | |
"df.head()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": { | |
"scrolled": true | |
}, | |
"outputs": [], | |
"source": [ | |
"df.columns.values" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"p_ehs = df[['Summary','Issue key','Custom field (Email Address (Mirrored))','Custom field (First Name (Mirrored))',\n", | |
" 'Custom field (Last Name (Mirrored))','Custom field (Request Type (Mirrored))']]\n", | |
"p_ehs.columns = ['Summary','IssueKey','EmailAddress','FirstName', 'LastName','RequestType']\n", | |
"p_ehs.head(3)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"p_ehs.describe()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"p_ehs['RequestCnt'] = 1\n", | |
"# p_ehs['new'] = p_ehs['RequestCnt'] * p_ehs['B']\n", | |
"p_ehs.head(3)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"p_ehs.describe()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"type(p_ehs),type(p_ehs.IssueKey)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"p_ehs['IssueKey'][:5]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"p_ehs.IssueKey[:5]" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"p_ehs.RequestType.unique()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": { | |
"scrolled": true | |
}, | |
"outputs": [], | |
"source": [ | |
"p_ehs[p_ehs.RequestType == 'Right to erasure']" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": { | |
"scrolled": true | |
}, | |
"outputs": [], | |
"source": [ | |
"p_ehs.EmailAddress.str.split('@')" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": { | |
"scrolled": true | |
}, | |
"outputs": [], | |
"source": [ | |
"p_ehs.EmailAddress.map(lambda x:x.split('@')[1])" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"p_ehs['EmailDomain']=p_ehs.EmailAddress.map(lambda x:x.split('@')[1])" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"p_ehs.head(3)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"p_ehs.EmailDomain.unique()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"pd.DataFrame(p_ehs.groupby('EmailDomain').count()['RequestType'])" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"p_ehs['cat']=p_ehs['EmailDomain']+'-'+p_ehs['RequestType']\n", | |
"p_ehs.head(3)" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"cat_df = pd.DataFrame(p_ehs.groupby('cat').count()['RequestType'])\n", | |
"cat_df" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"cat_df = cat_df.reset_index()\n", | |
"cat_df.columns = ['cat','cnt']\n", | |
"cat_df" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"cat_df = cat_df.sort_values('cat')\n", | |
"cat_df" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"cat_df.to_csv('data/GDPR Ticketing Report.csv')" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"%matplotlib inline" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": { | |
"scrolled": true | |
}, | |
"outputs": [], | |
"source": [ | |
"import matplotlib as mpl\n", | |
"import matplotlib.pylab as plt\n", | |
"cat_df = cat_df.set_index(['cat'])\n", | |
"cat_df" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"cat_df.plot()\n", | |
"#plt.legend()\n", | |
"plt.xlabel('category')\n", | |
"plt.show()" | |
] | |
}, | |
{ | |
"cell_type": "markdown", | |
"metadata": {}, | |
"source": [ | |
"## 인터넷 데이터 이용\n", | |
"\n", | |
"- pandas_datareader 패키지의 DataReader 이용\n", | |
"- https://pandas-datareader.readthedocs.io/en/latest/index.html\n", | |
"- FRED, Fama/French, World Bank, OECD, Eurostat, EDGAR Index, TSP Fund Data\n", | |
"- Oanda currency historical rate, Nasdaq Trader Symbol Definitions\n", | |
"- https://fred.stlouisfed.org/series/GDP\n", | |
"- https://fred.stlouisfed.org/series/CPIAUCSL\n", | |
"- https://fred.stlouisfed.org/series/CPILFESL\n", | |
"<pre>\n", | |
"import pandas_datareader as pdr\n", | |
"import datetime\n", | |
"dt_start = datetime.datetime(2015, 1, 1)\n", | |
"dt_end = \"2016, 6, 30\"\n", | |
"gdp = pdr.get_data_fred('GDP', dt_start, dt_end)\n", | |
"inflation = pdr.get_data_fred([\"CPIAUCSL\", \"CPILFESL\"], dt_start, dt_end)\n", | |
"</pre>\n" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"df = pd.read_csv(\"https://raw.githubusercontent.com/datascienceschool/docker_rpython/master/data/titanic.csv\")\n", | |
"df.head()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"df = pd.read_csv(\"data/titanic.txt\")\n", | |
"df.head()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [ | |
"df.tail()" | |
] | |
}, | |
{ | |
"cell_type": "code", | |
"execution_count": null, | |
"metadata": {}, | |
"outputs": [], | |
"source": [] | |
} | |
], | |
"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": "3.6.5" | |
} | |
}, | |
"nbformat": 4, | |
"nbformat_minor": 2 | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment