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 and Plotly sections added

pull/57/head
Jure Šorn 4 years ago
parent
c74ce25221
commit
a1b1276724
3 changed files with 574 additions and 1 deletions
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 312
      README.md
  2. 249
      index.html
  3. 14
      web/convert_table.py

312
README.md
View File

@ -3063,6 +3063,318 @@ if __name__ == '__main__':
```
Pandas
------
```python
# $ pip3 install pandas
import pandas as pd
from pandas import Series, DataFrame
```
### Series
**Ordered dictionary with a name.**
```python
>>> Series([1, 2], index=['x', 'y'], name='a')
x 1
y 2
Name: a, dtype: int64
```
```python
<Sr> = Series(<list>) # Assigns RangeIndex starting at 0.
<Sr> = Series(<dict>) # Takes dictionary's keys for index.
<Sr> = Series(<dict/Series>, index=<list>) # Only keeps items with keys specified in index.
```
```python
keys = <Sr>.index # Returns a sequence of keys as Index object.
vals = <Sr>.values # Returns a sequence of values as numpy array.
```
```python
<el> = <Sr>.loc[key] # Or: <Sr>.iloc[index]
<Sr> = <Sr>.loc[keys] # Or: <Sr>.iloc[indexes]
<Sr> = <Sr>.loc[from_key : to_key_inclusive] # Or: <Sr>.iloc[from_i : to_i_exclusive]
```
```python
<el> = <Sr>[key/index] # Or: <Sr>.key
<Sr> = <Sr>[keys/indexes] # Or: <Sr>[<key_range/range>]
<Sr> = <Sr>[<bools>] # Or: <Sr>.i/loc[<bools>]
```
```python
<Sr> = <Sr> ><== <el/Sr> # Returns Series of bools.
<Sr> = <Sr> +-*/ <el/Sr> # Non-matching keys get value NaN.
```
```python
<Sr> = pd.concat(<coll_of_Sr>) # Combines items.
<Sr> = <Sr>.append(<Sr>) # Appends new items.
<Sr> = <Sr>.combine_first(<Sr>) # Adds items that are not yet present (extends).
```
### DataFrame
**Table with labeled rows and columns.**
```python
>>> DataFrame([[1, 2], [3, 4]], index=['a', 'b'], columns=['x', 'y'])
x y
a 1 2
b 3 4
```
```python
<DF> = DataFrame(<list_of_rows>) # Rows can be either lists, dicts or series.
<DF> = DataFrame(<dict_of_columns>) # Columns can be either lists, dicts or series.
```
```python
row_keys = <Sr>.index # Also: `col_keys = <Sr>.columns`.
values = <Sr>.values # Returns values as 2D numpy array.
```
```python
<el> = <DF>.loc[row_key, column_key] # Or: <DF>.iloc[row_index, column_index]
<Sr/DF> = <DF>.loc[row_key/s] # Or: <DF>.iloc[row_index/es]
<Sr/DF> = <DF>.loc[:, column_key/s] # Or: <DF>.iloc[:, column_index/es]
<DF> = <DF>.loc[row_bools, column_bools] # Or: <DF>.iloc[row_bools, column_bools]
```
```python
<Sr/DF> = <DF>[column_key/s] # Or: <DF>.column_key
<DF> = <DF>[row_bools] # Keeps rows as specified by bools.
<DF> = <DF>[<DF_of_bools>] # Assigns NaN to False values.
```
```python
<DF> = <DF> ><== <el/Sr/DF> # Returns DataFrame of bools.
<DF> = <DF> +-*/ <el/Sr/DF> # Non-matching keys get value NaN.
```
```python
<DF> = <DF>.set_index(column_key) # Replaces row keys with values from a column.
<DF> = <DF>.reset_index() # Moves row keys to their own column.
<DF> = <DF>.transpose() # Rotates the table.
<DF> = <DF>.melt(id_vars=column_key/s) # Melts on columns.
```
### Merge, Join, Concat
```python
>>> l = DataFrame([[1, 2], [3, 4]], index=['a', 'b'], columns=['x', 'y'])
x y
a 1 2
b 3 4
>>> r = DataFrame([[4, 5], [6, 7]], index=['b', 'c'], columns=['y', 'z'])
y z
b 4 5
c 6 7
```
```python
┏━━━━━━━━━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━┯━━━━━━━━━━━━┯━━━━━━━━━━━━┓
┃ how/join │ 'outer' │ 'inner' │ 'left' ┃
┠────────────────────────┼───────────────┼────────────┼────────────┨
┃ l.merge(r, on='y', │ x y z │ x y z │ x y z ┃
┃ how=…) │ 0 1 2 . │ 3 4 5 │ 1 2 . ┃
┃ │ 1 3 4 5 │ │ 3 4 5 ┃
┃ │ 2 . 6 7 │ │ ┃
┠────────────────────────┼───────────────┼────────────┼────────────┨
┃ l.join(r, lsuffix='l', │ x yl yr z │ │ x yl yr z ┃
┃ rsuffix='r', │ a 1 2 . . │ x yl yr z │ 1 2 . . ┃
┃ how=…) │ b 3 4 4 5 │ 3 4 4 5 │ 3 4 4 5 ┃
┃ │ c . . 6 7 │ │ ┃
┠────────────────────────┼───────────────┼────────────┼────────────┨
┃ pd.concat([l, r], │ x y z │ y │ ┃
┃ axis=0, │ a 1 2 . │ 2 │ ┃
┃ join=…) │ b 3 4 . │ 4 │ ┃
┃ │ b . 4 5 │ 4 │ ┃
┃ │ c . 6 7 │ 6 │ ┃
┠────────────────────────┼───────────────┼────────────┼────────────┨
┃ pd.concat([l, r], │ x y y z │ │ ┃
┃ axis=1, │ a 1 2 . . │ x y y z │ ┃
┃ join=…) │ b 3 4 4 5 │ 3 4 4 5 │ ┃
┃ │ c . . 6 7 │ │ ┃
┠────────────────────────┼───────────────┼────────────┼────────────┨
┃ l.combine_first(r) │ x y z │ │ ┃
┃ │ a 1 2 . │ │ ┃
┃ │ b 3 4 5 │ │ ┃
┃ │ c . 6 7 │ │ ┃
┗━━━━━━━━━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━┷━━━━━━━━━━━━┷━━━━━━━━━━━━┛
```
### GroupBy
```python
<DF_Gb> = <DF>.groupby(column_key/s) # Columns that were used for groupin becme row_k.
<DFs> = list(<DF_Gb>) # Returns list of group_key - DataFrame tuples.
<DF> = <DF_Gb>.get_group(group_key)
<Sr_Gb> = <DF_Gb>[column_key] # Or: <DF_Gb>.column_key
<Srs> = list(<Sr_Gb>) # Returns list of group_key - Series tuples.
```
### Operations
```python
<el/Sr/DF> = <Sr/DF/GB>.sum/max/mean() # …/idxmax/all()
<Sr/DF> = <Sr/DF/GB>.diff/cumsum/rank() # …/pct_change()
```
```python
<Sr/DF> = <Sr/DF/GB>.ffill()
<Sr/DF> = <Sr/DF/GB>.fillna(value)
<Sr/DF> = <Sr/DF>.interpolate()
```
```python
<Sr/DF> = <Sr/DF/GB>.apply(<func>) # Invokes function on every value/column/group.
<DF> = <DF>.applymap(<func>) # Apply a function to a Dataframe elementwise.
<Sr/DF> = <Sr/DF/GB>.aggregate(<func>) # Invokes function on every column > number.
<Sr/DF> = <Sr/DF/GB>.transform(<func>)
<Sr/DF> = <Sr/DF>.combine(<Sr/DF>, <func>)
```
### Rolling
```python
<Rl> = <Sr/DF/GB>.rolling(window_size) # Also: `min_periods, center=False`.
<Rl> = <Rl>[column_key/s] # Or: <Rl>.column_key
<Sr/DF> = <Rl>.sum/max/mean()
<Sr/DF> = <Rl>.apply(<func>) # Invokes function on every window.
<Sr/DF> = <Rl>.aggregate(<func>) # Invokes function on every window.
```
### Encode
```python
<DF> = pd.read_json/html('<str/path/url>')
<DF> = pd.read_csv/pickle/excel('<path/url>')
<DF> = pd.read_sql('<query>', <connection>)
<DF> = pd.read_clipboard()
```
### Decode
```python
<dict> = <DF>.to_dict(['d/l/s/sp/r/i'])
<str> = <DF>.to_json/html/csv/markdown/latex([<path>])
<DF>.to_pickle/excel(<path>)
<DF>.to_sql('<table_name>', <connection>)
```
Plotly
------
### Top 10 Countries by Percentage of Population With Confirmed COVID-19 Infection
```text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
+----------------------------------------------------------------------------------------------
```
```python
import pandas as pd
import plotly.express
covid = pd.read_csv('https://covid.ourworldindata.org/data/owid-covid-data.csv',
usecols=['iso_code', 'date', 'total_deaths', 'population'])
continents = pd.read_csv('https://datahub.io/JohnSnowLabs/country-and-continent-codes-' + \
'list/r/country-and-continent-codes-list-csv.csv',
usecols=['Three_Letter_Country_Code', 'Continent_Name'])
merged = pd.merge(covid, continents, left_on='iso_code', right_on='Three_Letter_Country_Code')
summed = merged.groupby(['Continent_Name', 'date']).sum().reset_index()
summed['Total Deaths per Million'] = summed.total_deaths * 1e6 / summed.population
summed = summed[('2020-03-14' < summed.date) & (summed.date < '2020-05-31')]
summed = summed.rename({'date': 'Date', 'Continent_Name': 'Continent'}, axis='columns')
plotly.express.line(summed, x='Date', y='Total Deaths per Million', color='Continent').show()
```
### Confirmed Cases of COVID-19, Dow Jones Index, Gold, and Bitcoin Price
```text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
+----------------------------------------------------------------------------------------------
```
```python
import pandas, datetime
import plotly.graph_objects as go
def main():
display_data(mangle_data(*scrape_data()))
def scrape_data():
def scrape_yah(id_):
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',
usecols=['date', 'total_cases'])
covid = covid.groupby('date').sum()
dow_jones, gold, bitcoin = scrape_yah('^DJI'), scrape_yah('GC=F'), scrape_yah('BTC-USD')
dow_jones.name, gold.name, bitcoin.name = 'Dow Jones', 'Gold', 'Bitcoin'
return covid, dow_jones, gold, bitcoin
def mangle_data(covid, dow_jones, gold, bitcoin):
out = pandas.concat([covid, dow_jones, gold, bitcoin], axis=1)
out = out.loc['2020-02-23':].iloc[:-2]
out = out.interpolate()
out.iloc[:, 1:] = out.rolling(10, 1, center=True).mean().iloc[:, 1:]
out.iloc[:, 1:] = out.iloc[:, 1:] / out.iloc[0, 1:] * 100
return out
def display_data(out):
def get_trace(col_name):
return go.Scatter(x=out.index, y=out[col_name], name=col_name, yaxis='y2')
traces = [get_trace(col_name) for col_name in out.columns[1:]]
traces.append(go.Scatter(x=out.index, y=out.total_cases, name='Total Cases', yaxis='y1'))
figure = go.Figure()
figure.add_traces(traces)
figure.update_layout(
yaxis1=dict(title='Total Cases', rangemode='tozero'),
yaxis2=dict(title='%', rangemode='tozero', overlaying='y', side='right'),
legend=dict(x=1.1)
).show()
if __name__ == '__main__':
main()
```
Basic Script Template
---------------------
```python

249
index.html
View File

@ -2608,6 +2608,255 @@ SIZE, MAX_SPEED = <span class="hljs-number">50</span>, P(<span class="hljs-numbe
main()
</code></pre></div>
<div><h2 id="pandas"><a href="#pandas" name="pandas">#</a>Pandas</h2><pre><code class="python language-python hljs"><span class="hljs-comment"># $ pip3 install pandas</span>
<span class="hljs-keyword">import</span> pandas <span class="hljs-keyword">as</span> pd
<span class="hljs-keyword">from</span> pandas <span class="hljs-keyword">import</span> Series, DataFrame
</code></pre></div>
<div><h3 id="series">Series</h3><p><strong>Ordered dictionary with a name.</strong></p><pre><code class="python language-python hljs"><span class="hljs-meta">&gt;&gt;&gt; </span>Series([<span class="hljs-number">1</span>, <span class="hljs-number">2</span>], index=[<span class="hljs-string">'x'</span>, <span class="hljs-string">'y'</span>], name=<span class="hljs-string">'a'</span>)
x <span class="hljs-number">1</span>
y <span class="hljs-number">2</span>
Name: a, dtype: int64
</code></pre></div>
<pre><code class="python language-python hljs">&lt;Sr&gt; = Series(&lt;list&gt;) <span class="hljs-comment"># Assigns RangeIndex starting at 0.</span>
&lt;Sr&gt; = Series(&lt;dict&gt;) <span class="hljs-comment"># Takes dictionary's keys for index.</span>
&lt;Sr&gt; = Series(&lt;dict/Series&gt;, index=&lt;list&gt;) <span class="hljs-comment"># Only keeps items with keys specified in index.</span>
</code></pre>
<pre><code class="python language-python hljs">keys = &lt;Sr&gt;.index <span class="hljs-comment"># Returns a sequence of keys as Index object.</span>
vals = &lt;Sr&gt;.values <span class="hljs-comment"># Returns a sequence of values as numpy array.</span>
</code></pre>
<pre><code class="python language-python hljs">&lt;el&gt; = &lt;Sr&gt;.loc[key] <span class="hljs-comment"># Or: &lt;Sr&gt;.iloc[index]</span>
&lt;Sr&gt; = &lt;Sr&gt;.loc[keys] <span class="hljs-comment"># Or: &lt;Sr&gt;.iloc[indexes]</span>
&lt;Sr&gt; = &lt;Sr&gt;.loc[from_key : to_key_inclusive] <span class="hljs-comment"># Or: &lt;Sr&gt;.iloc[from_i : to_i_exclusive]</span>
</code></pre>
<pre><code class="python language-python hljs">&lt;el&gt; = &lt;Sr&gt;[key/index] <span class="hljs-comment"># Or: &lt;Sr&gt;.key</span>
&lt;Sr&gt; = &lt;Sr&gt;[keys/indexes] <span class="hljs-comment"># Or: &lt;Sr&gt;[&lt;key_range/range&gt;]</span>
&lt;Sr&gt; = &lt;Sr&gt;[&lt;bools&gt;] <span class="hljs-comment"># Or: &lt;Sr&gt;.i/loc[&lt;bools&gt;]</span>
</code></pre>
<pre><code class="python language-python hljs">&lt;Sr&gt; = &lt;Sr&gt; &gt;&lt;== &lt;el/Sr&gt; <span class="hljs-comment"># Returns Series of bools.</span>
&lt;Sr&gt; = &lt;Sr&gt; +-*/ &lt;el/Sr&gt; <span class="hljs-comment"># Non-matching keys get value NaN.</span>
</code></pre>
<pre><code class="python language-python hljs">&lt;Sr&gt; = pd.concat(&lt;coll_of_Sr&gt;) <span class="hljs-comment"># Combines items.</span>
&lt;Sr&gt; = &lt;Sr&gt;.append(&lt;Sr&gt;) <span class="hljs-comment"># Appends new items.</span>
&lt;Sr&gt; = &lt;Sr&gt;.combine_first(&lt;Sr&gt;) <span class="hljs-comment"># Adds items that are not yet present (extends).</span>
</code></pre>
<div><h3 id="dataframe">DataFrame</h3><p><strong>Table with labeled rows and columns.</strong></p><pre><code class="python language-python hljs"><span class="hljs-meta">&gt;&gt;&gt; </span>DataFrame([[<span class="hljs-number">1</span>, <span class="hljs-number">2</span>], [<span class="hljs-number">3</span>, <span class="hljs-number">4</span>]], index=[<span class="hljs-string">'a'</span>, <span class="hljs-string">'b'</span>], columns=[<span class="hljs-string">'x'</span>, <span class="hljs-string">'y'</span>])
x y
a <span class="hljs-number">1</span> <span class="hljs-number">2</span>
b <span class="hljs-number">3</span> <span class="hljs-number">4</span>
</code></pre></div>
<pre><code class="python language-python hljs">&lt;DF&gt; = DataFrame(&lt;list_of_rows&gt;) <span class="hljs-comment"># Rows can be either lists, dicts or series.</span>
&lt;DF&gt; = DataFrame(&lt;dict_of_columns&gt;) <span class="hljs-comment"># Columns can be either lists, dicts or series.</span>
</code></pre>
<pre><code class="python language-python hljs">row_keys = &lt;Sr&gt;.index <span class="hljs-comment"># Also: `col_keys = &lt;Sr&gt;.columns`.</span>
values = &lt;Sr&gt;.values <span class="hljs-comment"># Returns values as 2D numpy array.</span>
</code></pre>
<pre><code class="python language-python hljs">&lt;el&gt; = &lt;DF&gt;.loc[row_key, column_key] <span class="hljs-comment"># Or: &lt;DF&gt;.iloc[row_index, column_index]</span>
&lt;Sr/DF&gt; = &lt;DF&gt;.loc[row_key/s] <span class="hljs-comment"># Or: &lt;DF&gt;.iloc[row_index/es]</span>
&lt;Sr/DF&gt; = &lt;DF&gt;.loc[:, column_key/s] <span class="hljs-comment"># Or: &lt;DF&gt;.iloc[:, column_index/es]</span>
&lt;DF&gt; = &lt;DF&gt;.loc[row_bools, column_bools] <span class="hljs-comment"># Or: &lt;DF&gt;.iloc[row_bools, column_bools]</span>
</code></pre>
<pre><code class="python language-python hljs">&lt;Sr/DF&gt; = &lt;DF&gt;[column_key/s] <span class="hljs-comment"># Or: &lt;DF&gt;.column_key</span>
&lt;DF&gt; = &lt;DF&gt;[row_bools] <span class="hljs-comment"># Keeps rows as specified by bools.</span>
&lt;DF&gt; = &lt;DF&gt;[&lt;DF_of_bools&gt;] <span class="hljs-comment"># Assigns NaN to False values.</span>
</code></pre>
<pre><code class="python language-python hljs">&lt;DF&gt; = &lt;DF&gt; &gt;&lt;== &lt;el/Sr/DF&gt; <span class="hljs-comment"># Returns DataFrame of bools.</span>
&lt;DF&gt; = &lt;DF&gt; +-*/ &lt;el/Sr/DF&gt; <span class="hljs-comment"># Non-matching keys get value NaN.</span>
</code></pre>
<pre><code class="python language-python hljs">&lt;DF&gt; = &lt;DF&gt;.set_index(column_key) <span class="hljs-comment"># Replaces row keys with values from a column.</span>
&lt;DF&gt; = &lt;DF&gt;.reset_index() <span class="hljs-comment"># Moves row keys to their own column.</span>
&lt;DF&gt; = &lt;DF&gt;.transpose() <span class="hljs-comment"># Rotates the table.</span>
&lt;DF&gt; = &lt;DF&gt;.melt(id_vars=column_key/s) <span class="hljs-comment"># Melts on columns.</span>
</code></pre>
<div><h3 id="mergejoinconcat">Merge, Join, Concat</h3><pre><code class="python language-python hljs"><span class="hljs-meta">&gt;&gt;&gt; </span>l = DataFrame([[<span class="hljs-number">1</span>, <span class="hljs-number">2</span>], [<span class="hljs-number">3</span>, <span class="hljs-number">4</span>]], index=[<span class="hljs-string">'a'</span>, <span class="hljs-string">'b'</span>], columns=[<span class="hljs-string">'x'</span>, <span class="hljs-string">'y'</span>])
x y
a <span class="hljs-number">1</span> <span class="hljs-number">2</span>
b <span class="hljs-number">3</span> <span class="hljs-number">4</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>r = DataFrame([[<span class="hljs-number">4</span>, <span class="hljs-number">5</span>], [<span class="hljs-number">6</span>, <span class="hljs-number">7</span>]], index=[<span class="hljs-string">'b'</span>, <span class="hljs-string">'c'</span>], columns=[<span class="hljs-string">'y'</span>, <span class="hljs-string">'z'</span>])
y z
b <span class="hljs-number">4</span> <span class="hljs-number">5</span>
c <span class="hljs-number">6</span> <span class="hljs-number">7</span>
</code></pre></div>
<pre><code class="python language-python hljs">┏━━━━━━━━━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━┯━━━━━━━━━━━━┯━━━━━━━━━━━━┓
┃ how/join │ <span class="hljs-string">'outer'</span> │ <span class="hljs-string">'inner'</span> │ <span class="hljs-string">'left'</span> ┃
┠────────────────────────┼───────────────┼────────────┼────────────┨
┃ l.merge(r, on=<span class="hljs-string">'y'</span>, │ x y z │ x y z │ x y z ┃
┃ how=…) │ <span class="hljs-number">0</span> <span class="hljs-number">1</span> <span class="hljs-number">2</span> . │ <span class="hljs-number">3</span> <span class="hljs-number">4</span> <span class="hljs-number">5</span> │ <span class="hljs-number">1</span> <span class="hljs-number">2</span> . ┃
┃ │ <span class="hljs-number">1</span> <span class="hljs-number">3</span> <span class="hljs-number">4</span> <span class="hljs-number">5</span> │ │ <span class="hljs-number">3</span> <span class="hljs-number">4</span> <span class="hljs-number">5</span> ┃
┃ │ <span class="hljs-number">2</span> . <span class="hljs-number">6</span> <span class="hljs-number">7</span> │ │ ┃
┠────────────────────────┼───────────────┼────────────┼────────────┨
┃ l.join(r, lsuffix=<span class="hljs-string">'l'</span>, │ x yl yr z │ │ x yl yr z ┃
┃ rsuffix=<span class="hljs-string">'r'</span>, │ a <span class="hljs-number">1</span> <span class="hljs-number">2</span> . . │ x yl yr z │ <span class="hljs-number">1</span> <span class="hljs-number">2</span> . . ┃
┃ how=…) │ b <span class="hljs-number">3</span> <span class="hljs-number">4</span> <span class="hljs-number">4</span> <span class="hljs-number">5</span> │ <span class="hljs-number">3</span> <span class="hljs-number">4</span> <span class="hljs-number">4</span> <span class="hljs-number">5</span> │ <span class="hljs-number">3</span> <span class="hljs-number">4</span> <span class="hljs-number">4</span> <span class="hljs-number">5</span> ┃
┃ │ c . . <span class="hljs-number">6</span> <span class="hljs-number">7</span> │ │ ┃
┠────────────────────────┼───────────────┼────────────┼────────────┨
┃ pd.concat([l, r], │ x y z │ y │ ┃
┃ axis=<span class="hljs-number">0</span>, │ a <span class="hljs-number">1</span> <span class="hljs-number">2</span> . │ <span class="hljs-number">2</span> │ ┃
┃ join=…) │ b <span class="hljs-number">3</span> <span class="hljs-number">4</span> . │ <span class="hljs-number">4</span> │ ┃
┃ │ b . <span class="hljs-number">4</span> <span class="hljs-number">5</span> │ <span class="hljs-number">4</span> │ ┃
┃ │ c . <span class="hljs-number">6</span> <span class="hljs-number">7</span> │ <span class="hljs-number">6</span> │ ┃
┠────────────────────────┼───────────────┼────────────┼────────────┨
┃ pd.concat([l, r], │ x y y z │ │ ┃
┃ axis=<span class="hljs-number">1</span>, │ a <span class="hljs-number">1</span> <span class="hljs-number">2</span> . . │ x y y z │ ┃
┃ join=…) │ b <span class="hljs-number">3</span> <span class="hljs-number">4</span> <span class="hljs-number">4</span> <span class="hljs-number">5</span> │ <span class="hljs-number">3</span> <span class="hljs-number">4</span> <span class="hljs-number">4</span> <span class="hljs-number">5</span> │ ┃
┃ │ c . . <span class="hljs-number">6</span> <span class="hljs-number">7</span> │ │ ┃
┠────────────────────────┼───────────────┼────────────┼────────────┨
┃ l.combine_first(r) │ x y z │ │ ┃
┃ │ a <span class="hljs-number">1</span> <span class="hljs-number">2</span> . │ │ ┃
┃ │ b <span class="hljs-number">3</span> <span class="hljs-number">4</span> <span class="hljs-number">5</span> │ │ ┃
┃ │ c . <span class="hljs-number">6</span> <span class="hljs-number">7</span> │ │ ┃
┗━━━━━━━━━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━┷━━━━━━━━━━━━┷━━━━━━━━━━━━┛
</code></pre>
<div><h3 id="groupby">GroupBy</h3><pre><code class="python language-python hljs">&lt;DF_Gb&gt; = &lt;DF&gt;.groupby(column_key/s) <span class="hljs-comment"># Columns that were used for groupin becme row_k.</span>
&lt;DFs&gt; = list(&lt;DF_Gb&gt;) <span class="hljs-comment"># Returns list of group_key - DataFrame tuples.</span>
&lt;DF&gt; = &lt;DF_Gb&gt;.get_group(group_key)
&lt;Sr_Gb&gt; = &lt;DF_Gb&gt;[column_key] <span class="hljs-comment"># Or: &lt;DF_Gb&gt;.column_key</span>
&lt;Srs&gt; = list(&lt;Sr_Gb&gt;) <span class="hljs-comment"># Returns list of group_key - Series tuples.</span>
</code></pre></div>
<div><h3 id="operations">Operations</h3><pre><code class="python language-python hljs">&lt;el/Sr/DF&gt; = &lt;Sr/DF/GB&gt;.sum/max/mean() <span class="hljs-comment"># …/idxmax/all()</span>
&lt;Sr/DF&gt; = &lt;Sr/DF/GB&gt;.diff/cumsum/rank() <span class="hljs-comment"># …/pct_change()</span>
</code></pre></div>
<pre><code class="python language-python hljs">&lt;Sr/DF&gt; = &lt;Sr/DF/GB&gt;.ffill()
&lt;Sr/DF&gt; = &lt;Sr/DF/GB&gt;.fillna(value)
&lt;Sr/DF&gt; = &lt;Sr/DF&gt;.interpolate()
</code></pre>
<pre><code class="python language-python hljs">&lt;Sr/DF&gt; = &lt;Sr/DF/GB&gt;.apply(&lt;func&gt;) <span class="hljs-comment"># Invokes function on every value/column/group.</span>
&lt;DF&gt; = &lt;DF&gt;.applymap(&lt;func&gt;) <span class="hljs-comment"># Apply a function to a Dataframe elementwise.</span>
&lt;Sr/DF&gt; = &lt;Sr/DF/GB&gt;.aggregate(&lt;func&gt;) <span class="hljs-comment"># Invokes function on every column &gt; number.</span>
&lt;Sr/DF&gt; = &lt;Sr/DF/GB&gt;.transform(&lt;func&gt;)
&lt;Sr/DF&gt; = &lt;Sr/DF&gt;.combine(&lt;Sr/DF&gt;, &lt;func&gt;)
</code></pre>
<div><h3 id="rolling">Rolling</h3><pre><code class="python language-python hljs">&lt;Rl&gt; = &lt;Sr/DF/GB&gt;.rolling(window_size) <span class="hljs-comment"># Also: `min_periods, center=False`.</span>
&lt;Rl&gt; = &lt;Rl&gt;[column_key/s] <span class="hljs-comment"># Or: &lt;Rl&gt;.column_key</span>
&lt;Sr/DF&gt; = &lt;Rl&gt;.sum/max/mean()
&lt;Sr/DF&gt; = &lt;Rl&gt;.apply(&lt;func&gt;) <span class="hljs-comment"># Invokes function on every window.</span>
&lt;Sr/DF&gt; = &lt;Rl&gt;.aggregate(&lt;func&gt;) <span class="hljs-comment"># Invokes function on every window.</span>
</code></pre></div>
<div><h3 id="encode-2">Encode</h3><pre><code class="python language-python hljs">&lt;DF&gt; = pd.read_json/html(<span class="hljs-string">'&lt;str/path/url&gt;'</span>)
&lt;DF&gt; = pd.read_csv/pickle/excel(<span class="hljs-string">'&lt;path/url&gt;'</span>)
&lt;DF&gt; = pd.read_sql(<span class="hljs-string">'&lt;query&gt;'</span>, &lt;connection&gt;)
&lt;DF&gt; = pd.read_clipboard()
</code></pre></div>
<div><h3 id="decode-3">Decode</h3><pre><code class="python language-python hljs">&lt;dict&gt; = &lt;DF&gt;.to_dict([<span class="hljs-string">'d/l/s/sp/r/i'</span>])
&lt;str&gt; = &lt;DF&gt;.to_json/html/csv/markdown/latex([&lt;path&gt;])
&lt;DF&gt;.to_pickle/excel(&lt;path&gt;)
&lt;DF&gt;.to_sql(<span class="hljs-string">'&lt;table_name&gt;'</span>, &lt;connection&gt;)
</code></pre></div>
<div><h2 id="plotly"><a href="#plotly" name="plotly">#</a>Plotly</h2><div><h3 id="top10countriesbypercentageofpopulationwithconfirmedcovid19infection">Top 10 Countries by Percentage of Population With Confirmed COVID-19 Infection</h3><pre><code class="text language-text">|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
+----------------------------------------------------------------------------------------------
</code></pre></div></div>
<pre><code class="python language-python hljs"><span class="hljs-keyword">import</span> pandas <span class="hljs-keyword">as</span> pd
<span class="hljs-keyword">import</span> plotly.express
covid = pd.read_csv(<span class="hljs-string">'https://covid.ourworldindata.org/data/owid-covid-data.csv'</span>,
usecols=[<span class="hljs-string">'iso_code'</span>, <span class="hljs-string">'date'</span>, <span class="hljs-string">'total_deaths'</span>, <span class="hljs-string">'population'</span>])
continents = pd.read_csv(<span class="hljs-string">'https://datahub.io/JohnSnowLabs/country-and-continent-codes-'</span> + \
<span class="hljs-string">'list/r/country-and-continent-codes-list-csv.csv'</span>,
usecols=[<span class="hljs-string">'Three_Letter_Country_Code'</span>, <span class="hljs-string">'Continent_Name'</span>])
merged = pd.merge(covid, continents, left_on=<span class="hljs-string">'iso_code'</span>, right_on=<span class="hljs-string">'Three_Letter_Country_Code'</span>)
summed = merged.groupby([<span class="hljs-string">'Continent_Name'</span>, <span class="hljs-string">'date'</span>]).sum().reset_index()
summed[<span class="hljs-string">'Total Deaths per Million'</span>] = summed.total_deaths * <span class="hljs-number">1e6</span> / summed.population
summed = summed[(<span class="hljs-string">'2020-03-14'</span> &lt; summed.date) &amp; (summed.date &lt; <span class="hljs-string">'2020-05-31'</span>)]
summed = summed.rename({<span class="hljs-string">'date'</span>: <span class="hljs-string">'Date'</span>, <span class="hljs-string">'Continent_Name'</span>: <span class="hljs-string">'Continent'</span>}, axis=<span class="hljs-string">'columns'</span>)
plotly.express.line(summed, x=<span class="hljs-string">'Date'</span>, y=<span class="hljs-string">'Total Deaths per Million'</span>, color=<span class="hljs-string">'Continent'</span>).show()
</code></pre>
<div><h3 id="confirmedcasesofcovid19dowjonesindexgoldandbitcoinprice">Confirmed Cases of COVID-19, Dow Jones Index, Gold, and Bitcoin Price</h3><pre><code class="text language-text">|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
+----------------------------------------------------------------------------------------------
</code></pre></div>
<pre><code class="python language-python hljs"><span class="hljs-keyword">import</span> pandas, datetime
<span class="hljs-keyword">import</span> plotly.graph_objects <span class="hljs-keyword">as</span> go
<span class="hljs-function"><span class="hljs-keyword">def</span> <span class="hljs-title">main</span><span class="hljs-params">()</span>:</span>
display_data(mangle_data(*scrape_data()))
<span class="hljs-function"><span class="hljs-keyword">def</span> <span class="hljs-title">scrape_data</span><span class="hljs-params">()</span>:</span>
<span class="hljs-function"><span class="hljs-keyword">def</span> <span class="hljs-title">scrape_yah</span><span class="hljs-params">(id_)</span>:</span>
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>,
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_jones, gold, bitcoin = scrape_yah(<span class="hljs-string">'^DJI'</span>), scrape_yah(<span class="hljs-string">'GC=F'</span>), scrape_yah(<span class="hljs-string">'BTC-USD'</span>)
dow_jones.name, gold.name, bitcoin.name = <span class="hljs-string">'Dow Jones'</span>, <span class="hljs-string">'Gold'</span>, <span class="hljs-string">'Bitcoin'</span>
<span class="hljs-keyword">return</span> covid, dow_jones, gold, bitcoin
<span class="hljs-function"><span class="hljs-keyword">def</span> <span class="hljs-title">mangle_data</span><span class="hljs-params">(covid, dow_jones, gold, bitcoin)</span>:</span>
out = pandas.concat([covid, dow_jones, gold, bitcoin], axis=<span class="hljs-number">1</span>)
out = out.loc[<span class="hljs-string">'2020-02-23'</span>:].iloc[:<span class="hljs-number">-2</span>]
out = out.interpolate()
out.iloc[:, <span class="hljs-number">1</span>:] = out.rolling(<span class="hljs-number">10</span>, <span class="hljs-number">1</span>, center=<span class="hljs-keyword">True</span>).mean().iloc[:, <span class="hljs-number">1</span>:]
out.iloc[:, <span class="hljs-number">1</span>:] = out.iloc[:, <span class="hljs-number">1</span>:] / out.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> out
<span class="hljs-function"><span class="hljs-keyword">def</span> <span class="hljs-title">display_data</span><span class="hljs-params">(out)</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>
<span class="hljs-keyword">return</span> go.Scatter(x=out.index, y=out[col_name], name=col_name, yaxis=<span class="hljs-string">'y2'</span>)
traces = [get_trace(col_name) <span class="hljs-keyword">for</span> col_name <span class="hljs-keyword">in</span> out.columns[<span class="hljs-number">1</span>:]]
traces.append(go.Scatter(x=out.index, y=out.total_cases, name=<span class="hljs-string">'Total Cases'</span>, yaxis=<span class="hljs-string">'y1'</span>))
figure = go.Figure()
figure.add_traces(traces)
figure.update_layout(
yaxis1=dict(title=<span class="hljs-string">'Total Cases'</span>, rangemode=<span class="hljs-string">'tozero'</span>),
yaxis2=dict(title=<span class="hljs-string">'%'</span>, rangemode=<span class="hljs-string">'tozero'</span>, overlaying=<span class="hljs-string">'y'</span>, side=<span class="hljs-string">'right'</span>),
legend=dict(x=<span class="hljs-number">1.1</span>)
).show()
<span class="hljs-keyword">if</span> __name__ == <span class="hljs-string">'__main__'</span>:
main()
</code></pre>
<div><h2 id="basicscripttemplate"><a href="#basicscripttemplate" name="basicscripttemplate">#</a>Basic Script Template</h2><pre><code class="python language-python hljs"><span class="hljs-comment">#!/usr/bin/env python3</span>
<span class="hljs-comment">#</span>
<span class="hljs-comment"># Usage: .py</span>

14
web/convert_table.py
View File

@ -1,3 +1,5 @@
#!/usr/bin/env python3
def convert_table(lines):
def from_ascii():
out = []
@ -24,4 +26,14 @@ def convert_table(lines):
return '\n'.join(out)
if lines[0][0] == '+':
return from_ascii()
return from_unicode()
return from_unicode()
if __name__ == '__main__':
input_lines = []
try:
while True:
input_lines.append(input())
except EOFError:
pass
print(convert_table(input_lines))
Write Preview
Loading…
Cancel
Save