richard
/
python-cheatsheet
mirror of https://github.com/gto76/python-cheatsheet.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
Browse Source

Pandas

pull/69/head
Jure Šorn 4 years ago
parent
dde0e308dc
commit
e246cd4047
2 changed files with 20 additions and 18 deletions
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 19
      README.md
  2. 19
      index.html

19
README.md
View File

@ -3377,8 +3377,9 @@ plotly.express.line(df, x='Date', y='Total Deaths per Million', color='Continent
```python
# $ pip3 install pandas plotly
import pandas, datetime
import pandas as pd
import plotly.graph_objects as go
import datetime
def main():
display_data(wrangle_data(*scrape_data()))
@ -3388,8 +3389,8 @@ def scrape_data():
BASE_URL = 'https://query1.finance.yahoo.com/v7/finance/download/'
now = int(datetime.datetime.now().timestamp())
url = f'{BASE_URL}{id_}?period1=1579651200&period2={now}&interval=1d&events=history'
return pandas.read_csv(url, usecols=['Date', 'Close']).set_index('Date').Close
covid = pd.read_csv('https://covid.ourworldindata.org/data/owid-covid-data.csv',
return pd.read_csv(url, usecols=['Date', 'Close']).set_index('Date').Close
covid = pd.read_csv('https://covid.ourworldindata.org/data/owid-covid-data.csv',
usecols=['date', 'total_cases'])
covid = covid.groupby('date').sum()
dow, gold, bitcoin = [scrape_yahoo(id_) for id_ in ('^DJI', 'GC=F', 'BTC-USD')]
@ -3397,12 +3398,12 @@ def scrape_data():
return covid, dow, gold, bitcoin
def wrangle_data(covid, dow, gold, bitcoin):
df = pandas.concat([covid, dow, gold, bitcoin], axis=1)
df = pd.concat([dow, gold, bitcoin], axis=1)
df = df.sort_index().interpolate()
df = df.loc['2020-02-23':].iloc[:-2]
df = df.interpolate()
df.iloc[:, 1:] = df.rolling(10, min_periods=1, center=True).mean().iloc[:, 1:]
df.iloc[:, 1:] = df.iloc[:, 1:] / df.iloc[0, 1:] * 100
return df
df = df.rolling(10, min_periods=1, center=True).mean()
df = df / df.iloc[0] * 100
return pd.concat([covid, df], axis=1, join='inner')
def display_data(df):
def get_trace(col_name):
@ -3478,7 +3479,7 @@ $ pyinstaller script.py --add-data '<path>:.' # Adds file to the root of the ex
from collections import namedtuple
from dataclasses import make_dataclass
from enum import Enum
from sys import argv
from sys import argv, exit
import re

19
index.html
View File

@ -2861,8 +2861,9 @@ plotly.express.line(df, x=<span class="hljs-string">'Date'</span>, y=<span class
<div><h3 id="confirmedcovidcasesdowjonesgoldandbitcoinprice">Confirmed Covid Cases, Dow Jones, Gold, and Bitcoin Price</h3><p></p><div id="e23ccacc-a456-478b-b467-7282a2165921" class="plotly-graph-div" style="height:400px; width:100%;"></div><pre><code class="python language-python hljs"><span class="hljs-comment"># $ pip3 install pandas plotly</span>
<span class="hljs-keyword">import</span> pandas, datetime
<span class="hljs-keyword">import</span> pandas <span class="hljs-keyword">as</span> pd
<span class="hljs-keyword">import</span> plotly.graph_objects <span class="hljs-keyword">as</span> go
<span class="hljs-keyword">import</span> datetime
<span class="hljs-function"><span class="hljs-keyword">def</span> <span class="hljs-title">main</span><span class="hljs-params">()</span>:</span>
display_data(wrangle_data(*scrape_data()))
@ -2872,8 +2873,8 @@ plotly.express.line(df, x=<span class="hljs-string">'Date'</span>, y=<span class
BASE_URL = <span class="hljs-string">'https://query1.finance.yahoo.com/v7/finance/download/'</span>
now = int(datetime.datetime.now().timestamp())
url = <span class="hljs-string">f'<span class="hljs-subst">{BASE_URL}</span><span class="hljs-subst">{id_}</span>?period1=1579651200&amp;period2=<span class="hljs-subst">{now}</span>&amp;interval=1d&amp;events=history'</span>
<span class="hljs-keyword">return</span> pandas.read_csv(url, usecols=[<span class="hljs-string">'Date'</span>, <span class="hljs-string">'Close'</span>]).set_index(<span class="hljs-string">'Date'</span>).Close
covid = pd.read_csv(<span class="hljs-string">'https://covid.ourworldindata.org/data/owid-covid-data.csv'</span>,
<span class="hljs-keyword">return</span> pd.read_csv(url, usecols=[<span class="hljs-string">'Date'</span>, <span class="hljs-string">'Close'</span>]).set_index(<span class="hljs-string">'Date'</span>).Close
covid = pd.read_csv(<span class="hljs-string">'https://covid.ourworldindata.org/data/owid-covid-data.csv'</span>,
usecols=[<span class="hljs-string">'date'</span>, <span class="hljs-string">'total_cases'</span>])
covid = covid.groupby(<span class="hljs-string">'date'</span>).sum()
dow, gold, bitcoin = [scrape_yahoo(id_) <span class="hljs-keyword">for</span> id_ <span class="hljs-keyword">in</span> (<span class="hljs-string">'^DJI'</span>, <span class="hljs-string">'GC=F'</span>, <span class="hljs-string">'BTC-USD'</span>)]
@ -2881,12 +2882,12 @@ plotly.express.line(df, x=<span class="hljs-string">'Date'</span>, y=<span class
<span class="hljs-keyword">return</span> covid, dow, gold, bitcoin
<span class="hljs-function"><span class="hljs-keyword">def</span> <span class="hljs-title">wrangle_data</span><span class="hljs-params">(covid, dow, gold, bitcoin)</span>:</span>
df = pandas.concat([covid, dow, gold, bitcoin], axis=<span class="hljs-number">1</span>)
df = pd.concat([dow, gold, bitcoin], axis=<span class="hljs-number">1</span>)
df = df.sort_index().interpolate()
df = df.loc[<span class="hljs-string">'2020-02-23'</span>:].iloc[:<span class="hljs-number">-2</span>]
df = df.interpolate()
df.iloc[:, <span class="hljs-number">1</span>:] = df.rolling(<span class="hljs-number">10</span>, min_periods=<span class="hljs-number">1</span>, center=<span class="hljs-keyword">True</span>).mean().iloc[:, <span class="hljs-number">1</span>:]
df.iloc[:, <span class="hljs-number">1</span>:] = df.iloc[:, <span class="hljs-number">1</span>:] / df.iloc[<span class="hljs-number">0</span>, <span class="hljs-number">1</span>:] * <span class="hljs-number">100</span>
<span class="hljs-keyword">return</span> df
df = df.rolling(<span class="hljs-number">10</span>, min_periods=<span class="hljs-number">1</span>, center=<span class="hljs-keyword">True</span>).mean()
df = df / df.iloc[<span class="hljs-number">0</span>] * <span class="hljs-number">100</span>
<span class="hljs-keyword">return</span> pd.concat([covid, df], axis=<span class="hljs-number">1</span>, join=<span class="hljs-string">'inner'</span>)
<span class="hljs-function"><span class="hljs-keyword">def</span> <span class="hljs-title">display_data</span><span class="hljs-params">(df)</span>:</span>
<span class="hljs-function"><span class="hljs-keyword">def</span> <span class="hljs-title">get_trace</span><span class="hljs-params">(col_name)</span>:</span>
@ -2949,7 +2950,7 @@ $ pyinstaller script.py --add-data <span class="hljs-string">'&lt;path&gt;:.'</s
<span class="hljs-keyword">from</span> collections <span class="hljs-keyword">import</span> namedtuple
<span class="hljs-keyword">from</span> dataclasses <span class="hljs-keyword">import</span> make_dataclass
<span class="hljs-keyword">from</span> enum <span class="hljs-keyword">import</span> Enum
<span class="hljs-keyword">from</span> sys <span class="hljs-keyword">import</span> argv
<span class="hljs-keyword">from</span> sys <span class="hljs-keyword">import</span> argv, exit
<span class="hljs-keyword">import</span> re

Write Preview
Loading…
Cancel
Save