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

Working on Pandas

pull/57/head
Jure Šorn 4 years ago
parent
f9ae0a3d86
commit
cc94902871
2 changed files with 100 additions and 106 deletions
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 101
      README.md
  2. 105
      index.html

101
README.md
View File

@ -3111,13 +3111,12 @@ Name: a, dtype: int64
<Sr>.update(<Sr>) # Updates items that are already present.
```
#### Apply, Aggregate, Transform:
#### Aggregate, Transform, Map:
```python
<el> = <Sr>.sum/max/mean/idxmax/all() # Or: <Sr>.aggregate(<agg_func>)
<Sr> = <Sr>.rank/diff/cumsum/pct_change() # Or: <Sr>.agg/transform(<trans_func>)
<Sr> = <Sr>.rank/diff/cumsum/ffill/interpl() # Or: <Sr>.agg/transform(<trans_func>)
<Sr> = <Sr>.fillna(<el>) # Or: <Sr>.apply/agg/transform/map(<map_func>)
```
* **Also: `'ffill()'` and `'interpolate()'`.**
* **The way `'aggregate()'` and `'transform()'` find out whether a function accepts an element or the whole Series is by passing it a single value at first and if it raises an error, then they pass it the whole Series.**
```python
@ -3128,23 +3127,22 @@ dtype: int64
```
```python
+-------------+---------------+---------------+---------------+
| | 'sum' | ['sum'] | {'s': 'sum'} |
+-------------+---------------+---------------+---------------+
| sr.apply(…) | | | |
| sr.agg(…) | 3 | sum 3 | s 3 |
| | | | |
+-------------+---------------+---------------+---------------+
┏━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━┓
┃ │ 'sum' │ ['sum'] │ {'s': 'sum'} ┃
┠─────────────┼─────────────┼─────────────┼───────────────┨
┃ sr.apply(…) │ 3 │ sum 3 │ s 3 ┃
┃ sr.agg(…) │ │ │ ┃
┗━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━┛
```
```python
+-------------+---------------+---------------+---------------+
| | 'rank' | ['rank'] | {'r': 'rank'} |
+-------------+---------------+---------------+---------------+
| sr.apply(…) | | rank | |
| sr.agg(…) | x 1 | x 1 | r x 1 |
| sr.trans(…) | y 2 | y 2 | y 2 |
+-------------+---------------+---------------+---------------+
┏━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━┓
┃ │ 'rank' │ ['rank'] │ {'r': 'rank'} ┃
┠─────────────┼─────────────┼─────────────┼───────────────┨
┃ sr.apply(…) │ │ rank │ ┃
┃ sr.agg(…) │ x 1 │ x 1 │ r x 1 ┃
┃ sr.trans(…) │ y 2 │ y 2 │ y 2 ┃
┗━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━┛
```
### DataFrame
@ -3201,7 +3199,7 @@ c 6 7
```python
┏━━━━━━━━━━━━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━┯━━━━━━━━━━━━┯━━━━━━━━━━━━┯━━━━━━━━━━━━━━━━━━━━━━━━━━┓
┃ how/join │ 'outer' │ 'inner' │ 'left' │ description ┃
┃ how/join │ 'outer' │ 'inner' │ 'left' │ description ┃
┠────────────────────────┼───────────────┼────────────┼────────────┼──────────────────────────┨
┃ l.merge(r, on='y', │ x y z │ x y z │ x y z │ Joins/merges on column. ┃
┃ how=…) │ 0 1 2 . │ 3 4 5 │ 1 2 . │ Also accepts left_on and ┃
@ -3231,13 +3229,12 @@ c 6 7
┗━━━━━━━━━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━┷━━━━━━━━━━━━┷━━━━━━━━━━━━┷━━━━━━━━━━━━━━━━━━━━━━━━━━┛
```
#### Apply, Aggregate, Transform:
#### Aggregate, Transform, Map:
```python
<Sr> = <DF>.sum/max/mean/idxmax/all() # Or: <DF>.apply/agg/transform(<agg_func>)
<DF> = <DF>.rank/diff/cumsum/pct_change() # Or: <DF>.apply/agg/transform(<trans_func>)
<DF> = <DF>.rank/diff/cumsum/ffill/interpl() # Or: <DF>.apply/agg/transform(<trans_func>)
<DF> = <DF>.fillna(<el>) # Or: <DF>.applymap(<map_func>)
```
* **Also: `'ffill()'` and `'interpolate()'`.**
* **All operations operate on columns by default. Use `'axis=1'` parameter to process the rows instead.**
```python
@ -3248,24 +3245,24 @@ b 3 4
```
```python
+-------------+---------------+---------------+---------------+
| | 'sum' | ['sum'] | {'x': 'sum'} |
+-------------+---------------+---------------+---------------+
| df.apply(…) | | x y | |
| df.agg(…) | x 4 | sum 4 6 | x 4 |
| | y 6 | | |
+-------------+---------------+---------------+---------------+
┏━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━┓
┃ │ 'sum' │ ['sum'] │ {'x': 'sum'} ┃
┠─────────────┼─────────────┼─────────────┼───────────────┨
┃ df.apply(…) │ │ x y │ ┃
┃ df.agg(…) │ x 4 │ sum 4 6 │ x 4 ┃
┃ │ y 6 │ │ ┃
┗━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━┛
```
```python
+-------------+---------------+---------------+---------------+
| | 'rank' | ['rank'] | {'x': 'rank'} |
+-------------+---------------+---------------+---------------+
| df.apply(…) | x y | x y | x |
| df.agg(…) | a 1 1 | rank rank | a 1 |
| df.trans(…) | b 2 2 | a 1 1 | b 2 |
| | | b 2 2 | |
+-------------+---------------+---------------+---------------+
┏━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━┓
┃ │ 'rank' │ ['rank'] │ {'x': 'rank'} ┃
┠─────────────┼─────────────┼─────────────┼───────────────┨
┃ df.apply(…) │ x y │ x y │ x ┃
┃ df.agg(…) │ a 1 1 │ rank rank │ a 1 ┃
┃ df.trans(…) │ b 2 2 │ a 1 1 │ b 2 ┃
┃ │ │ b 2 2 │ ┃
┗━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━┛
```
#### Encode, Decode:
@ -3284,7 +3281,7 @@ b 3 4
```
### GroupBy
**Object that groups together rows of a dataframe based on the value of passed column.**
**Object that groups together rows of a dataframe based on the value of the passed column.**
```python
>>> df = DataFrame([[1, 2, 3], [4, 5, 6], [7, 8, 6]], index=list('abc'), columns=list('xyz'))
@ -3302,7 +3299,7 @@ c 7 8
<DF> = <GB>.get_group(group_key) # Selects a group by value of grouping column.
```
#### Apply, Aggregate, Transform:
#### Aggregate, Transform, Map:
```python
<DF> = <GB>.sum/max/mean/idxmax/all() # Or: <GB>.apply/agg(<agg_func>)
<DF> = <GB>.rank/diff/cumsum/ffill() # Or: <GB>.aggregate(<trans_func>)
@ -3318,20 +3315,20 @@ c 7 8
```
```python
+-------------+-------------+-------------+-------------+---------------+
| | 'sum' | 'rank' | ['rank'] | {'x': 'rank'} |
+-------------+-------------+-------------+-------------+---------------+
| gb.agg(…) | x y | x y | x y | x |
| | z | a 1 1 | rank rank | a 1 |
| | 3 1 2 | b 1 1 | a 1 1 | b 1 |
| | 6 11 13 | c 2 2 | b 1 1 | c 2 |
| | | | c 2 2 | |
+-------------+-------------+-------------+-------------+---------------+
| gb.trans(…) | x y | x y | | |
| | a 1 2 | a 1 1 | | |
| | b 11 13 | b 1 1 | | |
| | c 11 13 | c 1 1 | | |
+-------------+-------------+-------------+-------------+---------------+
┏━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━┓
┃ │ 'sum' │ 'rank' │ ['rank'] │ {'x': 'rank'} ┃
┠─────────────┼─────────────┼─────────────┼─────────────┼───────────────┨
┃ gb.agg(…) │ x y │ x y │ x y │ x ┃
┃ │ z │ a 1 1 │ rank rank │ a 1 ┃
┃ │ 3 1 2 │ b 1 1 │ a 1 1 │ b 1 ┃
┃ │ 6 11 13 │ c 2 2 │ b 1 1 │ c 2 ┃
┃ │ │ │ c 2 2 │ ┃
┠─────────────┼─────────────┼─────────────┼─────────────┼───────────────┨
┃ gb.trans(…) │ x y │ x y │ │ ┃
┃ │ a 1 2 │ a 1 1 │ │ ┃
┃ │ b 11 13 │ b 1 1 │ │ ┃
┃ │ c 11 13 │ c 1 1 │ │ ┃
┗━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━┛
```
### Rolling

105
index.html
View File

@ -2639,13 +2639,12 @@ Name: a, dtype: int64
&lt;Sr&gt; = &lt;Sr&gt;.combine_first(&lt;Sr&gt;) <span class="hljs-comment"># Adds items that are not yet present.</span>
&lt;Sr&gt;.update(&lt;Sr&gt;) <span class="hljs-comment"># Updates items that are already present.</span>
</code></pre>
<div><h4 id="applyaggregatetransform">Apply, Aggregate, Transform:</h4><pre><code class="python language-python hljs">&lt;el&gt; = &lt;Sr&gt;.sum/max/mean/idxmax/all() <span class="hljs-comment"># Or: &lt;Sr&gt;.aggregate(&lt;agg_func&gt;)</span>
&lt;Sr&gt; = &lt;Sr&gt;.rank/diff/cumsum/pct_change() <span class="hljs-comment"># Or: &lt;Sr&gt;.agg/transform(&lt;trans_func&gt;)</span>
<div><h4 id="aggregatetransformmap">Aggregate, Transform, Map:</h4><pre><code class="python language-python hljs">&lt;el&gt; = &lt;Sr&gt;.sum/max/mean/idxmax/all() <span class="hljs-comment"># Or: &lt;Sr&gt;.aggregate(&lt;agg_func&gt;)</span>
&lt;Sr&gt; = &lt;Sr&gt;.rank/diff/cumsum/ffill/interpl() <span class="hljs-comment"># Or: &lt;Sr&gt;.agg/transform(&lt;trans_func&gt;)</span>
&lt;Sr&gt; = &lt;Sr&gt;.fillna(&lt;el&gt;) <span class="hljs-comment"># Or: &lt;Sr&gt;.apply/agg/transform/map(&lt;map_func&gt;)</span>
</code></pre></div>
<ul>
<li><strong>Also: <code class="python hljs"><span class="hljs-string">'ffill()'</span></code> and <code class="python hljs"><span class="hljs-string">'interpolate()'</span></code>.</strong></li>
<li><strong>The way <code class="python hljs"><span class="hljs-string">'aggregate()'</span></code> and <code class="python hljs"><span class="hljs-string">'transform()'</span></code> find out whether a function accepts an element or the whole Series is by passing it a single value at first and if it raises an error, then they pass it the whole Series.</strong></li>
</ul>
<pre><code class="python language-python hljs"><span class="hljs-meta">&gt;&gt;&gt; </span>sr = 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>])
@ -2653,21 +2652,20 @@ x <span class="hljs-number">1</span>
y <span class="hljs-number">2</span>
dtype: int64
</code></pre>
<pre><code class="python language-python hljs">+-------------+---------------+---------------+---------------+
| | <span class="hljs-string">'sum'</span> | [<span class="hljs-string">'sum'</span>] | {<span class="hljs-string">'s'</span>: <span class="hljs-string">'sum'</span>} |
+-------------+---------------+---------------+---------------+
| sr.apply(…) | | | |
| sr.agg(…) | <span class="hljs-number">3</span> | sum <span class="hljs-number">3</span> | s <span class="hljs-number">3</span> |
| | | | |
+-------------+---------------+---------------+---------------+
</code></pre>
<pre><code class="python language-python hljs">+-------------+---------------+---------------+---------------+
| | <span class="hljs-string">'rank'</span> | [<span class="hljs-string">'rank'</span>] | {<span class="hljs-string">'r'</span>: <span class="hljs-string">'rank'</span>} |
+-------------+---------------+---------------+---------------+
| sr.apply(…) | | rank | |
| sr.agg(…) | x <span class="hljs-number">1</span> | x <span class="hljs-number">1</span> | r x <span class="hljs-number">1</span> |
| sr.trans(…) | y <span class="hljs-number">2</span> | y <span class="hljs-number">2</span> | y <span class="hljs-number">2</span> |
+-------------+---------------+---------------+---------------+
<pre><code class="python language-python hljs">┏━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━┓
┃ │ <span class="hljs-string">'sum'</span> │ [<span class="hljs-string">'sum'</span>] │ {<span class="hljs-string">'s'</span>: <span class="hljs-string">'sum'</span>} ┃
┠─────────────┼─────────────┼─────────────┼───────────────┨
┃ sr.apply(…) │ <span class="hljs-number">3</span> │ sum <span class="hljs-number">3</span> │ s <span class="hljs-number">3</span> ┃
┃ sr.agg(…) │ │ │ ┃
┗━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━┛
</code></pre>
<pre><code class="python language-python hljs">┏━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━┓
┃ │ <span class="hljs-string">'rank'</span> │ [<span class="hljs-string">'rank'</span>] │ {<span class="hljs-string">'r'</span>: <span class="hljs-string">'rank'</span>} ┃
┠─────────────┼─────────────┼─────────────┼───────────────┨
┃ sr.apply(…) │ │ rank │ ┃
┃ sr.agg(…) │ x <span class="hljs-number">1</span> │ x <span class="hljs-number">1</span> │ r x <span class="hljs-number">1</span> ┃
┃ sr.trans(…) │ y <span class="hljs-number">2</span> │ y <span class="hljs-number">2</span> │ y <span class="hljs-number">2</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
@ -2707,7 +2705,7 @@ 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> │ description ┃
┃ how/join │ <span class="hljs-string">'outer'</span> │ <span class="hljs-string">'inner'</span> │ <span class="hljs-string">'left'</span> │ description ┃
┠────────────────────────┼───────────────┼────────────┼────────────┼──────────────────────────┨
┃ l.merge(r, on=<span class="hljs-string">'y'</span>, │ x y z │ x y z │ x y z │ Joins/merges on column. ┃
┃ 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> . │ Also accepts left_on <span class="hljs-keyword">and</span> ┃
@ -2736,13 +2734,12 @@ c <span class="hljs-number">6</span> <span class="hljs-number">7</span>
┃ │ c . <span class="hljs-number">6</span> <span class="hljs-number">7</span> │ │ │ ┃
┗━━━━━━━━━━━━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━┷━━━━━━━━━━━━┷━━━━━━━━━━━━┷━━━━━━━━━━━━━━━━━━━━━━━━━━┛
</code></pre>
<div><h4 id="applyaggregatetransform-1">Apply, Aggregate, Transform:</h4><pre><code class="python language-python hljs">&lt;Sr&gt; = &lt;DF&gt;.sum/max/mean/idxmax/all() <span class="hljs-comment"># Or: &lt;DF&gt;.apply/agg/transform(&lt;agg_func&gt;)</span>
&lt;DF&gt; = &lt;DF&gt;.rank/diff/cumsum/pct_change() <span class="hljs-comment"># Or: &lt;DF&gt;.apply/agg/transform(&lt;trans_func&gt;)</span>
<div><h4 id="aggregatetransformmap-1">Aggregate, Transform, Map:</h4><pre><code class="python language-python hljs">&lt;Sr&gt; = &lt;DF&gt;.sum/max/mean/idxmax/all() <span class="hljs-comment"># Or: &lt;DF&gt;.apply/agg/transform(&lt;agg_func&gt;)</span>
&lt;DF&gt; = &lt;DF&gt;.rank/diff/cumsum/ffill/interpl() <span class="hljs-comment"># Or: &lt;DF&gt;.apply/agg/transform(&lt;trans_func&gt;)</span>
&lt;DF&gt; = &lt;DF&gt;.fillna(&lt;el&gt;) <span class="hljs-comment"># Or: &lt;DF&gt;.applymap(&lt;map_func&gt;)</span>
</code></pre></div>
<ul>
<li><strong>Also: <code class="python hljs"><span class="hljs-string">'ffill()'</span></code> and <code class="python hljs"><span class="hljs-string">'interpolate()'</span></code>.</strong></li>
<li><strong>All operations operate on columns by default. Use <code class="python hljs"><span class="hljs-string">'axis=1'</span></code> parameter to process the rows instead.</strong> </li>
</ul>
<pre><code class="python language-python hljs"><span class="hljs-meta">&gt;&gt;&gt; </span>df = 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>])
@ -2750,22 +2747,22 @@ c <span class="hljs-number">6</span> <span class="hljs-number">7</span>
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>
<pre><code class="python language-python hljs">+-------------+---------------+---------------+---------------+
| | <span class="hljs-string">'sum'</span> | [<span class="hljs-string">'sum'</span>] | {<span class="hljs-string">'x'</span>: <span class="hljs-string">'sum'</span>} |
+-------------+---------------+---------------+---------------+
| df.apply(…) | | x y | |
| df.agg(…) | x <span class="hljs-number">4</span> | sum <span class="hljs-number">4</span> <span class="hljs-number">6</span> | x <span class="hljs-number">4</span> |
| | y <span class="hljs-number">6</span> | | |
+-------------+---------------+---------------+---------------+
</code></pre>
<pre><code class="python language-python hljs">+-------------+---------------+---------------+---------------+
| | <span class="hljs-string">'rank'</span> | [<span class="hljs-string">'rank'</span>] | {<span class="hljs-string">'x'</span>: <span class="hljs-string">'rank'</span>} |
+-------------+---------------+---------------+---------------+
| df.apply(…) | x y | x y | x |
| df.agg(…) | a <span class="hljs-number">1</span> <span class="hljs-number">1</span> | rank rank | a <span class="hljs-number">1</span> |
| df.trans(…) | b <span class="hljs-number">2</span> <span class="hljs-number">2</span> | a <span class="hljs-number">1</span> <span class="hljs-number">1</span> | b <span class="hljs-number">2</span> |
| | | b <span class="hljs-number">2</span> <span class="hljs-number">2</span> | |
+-------------+---------------+---------------+---------------+
<pre><code class="python language-python hljs">┏━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━┓
┃ │ <span class="hljs-string">'sum'</span> │ [<span class="hljs-string">'sum'</span>] │ {<span class="hljs-string">'x'</span>: <span class="hljs-string">'sum'</span>} ┃
┠─────────────┼─────────────┼─────────────┼───────────────┨
┃ df.apply(…) │ │ x y │ ┃
┃ df.agg(…) │ x <span class="hljs-number">4</span> │ sum <span class="hljs-number">4</span> <span class="hljs-number">6</span> │ x <span class="hljs-number">4</span> ┃
┃ │ y <span class="hljs-number">6</span> │ │ ┃
┗━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━┛
</code></pre>
<pre><code class="python language-python hljs">┏━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━┓
┃ │ <span class="hljs-string">'rank'</span> │ [<span class="hljs-string">'rank'</span>] │ {<span class="hljs-string">'x'</span>: <span class="hljs-string">'rank'</span>} ┃
┠─────────────┼─────────────┼─────────────┼───────────────┨
┃ df.apply(…) │ x y │ x y │ x ┃
┃ df.agg(…) │ a <span class="hljs-number">1</span> <span class="hljs-number">1</span> │ rank rank │ a <span class="hljs-number">1</span> ┃
┃ df.trans(…) │ b <span class="hljs-number">2</span> <span class="hljs-number">2</span> │ a <span class="hljs-number">1</span> <span class="hljs-number">1</span> │ b <span class="hljs-number">2</span> ┃
┃ │ │ b <span class="hljs-number">2</span> <span class="hljs-number">2</span> │ ┃
┗━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━┛
</code></pre>
<div><h4 id="encodedecode">Encode, Decode:</h4><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>)
@ -2778,7 +2775,7 @@ b <span class="hljs-number">3</span> <span class="hljs-number">4</span>
&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><h3 id="groupby">GroupBy</h3><p><strong>Object that groups together rows of a dataframe based on the value of passed column.</strong></p><pre><code class="python language-python hljs"><span class="hljs-meta">&gt;&gt;&gt; </span>df = 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>, <span class="hljs-number">5</span>, <span class="hljs-number">6</span>], [<span class="hljs-number">7</span>, <span class="hljs-number">8</span>, <span class="hljs-number">6</span>]], index=list(<span class="hljs-string">'abc'</span>), columns=list(<span class="hljs-string">'xyz'</span>))
<div><h3 id="groupby">GroupBy</h3><p><strong>Object that groups together rows of a dataframe based on the value of the passed column.</strong></p><pre><code class="python language-python hljs"><span class="hljs-meta">&gt;&gt;&gt; </span>df = 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>, <span class="hljs-number">5</span>, <span class="hljs-number">6</span>], [<span class="hljs-number">7</span>, <span class="hljs-number">8</span>, <span class="hljs-number">6</span>]], index=list(<span class="hljs-string">'abc'</span>), columns=list(<span class="hljs-string">'xyz'</span>))
<span class="hljs-meta">&gt;&gt;&gt; </span>df.groupby(<span class="hljs-string">'z'</span>).get_group(<span class="hljs-number">3</span>)
x y
a <span class="hljs-number">1</span> <span class="hljs-number">2</span>
@ -2792,7 +2789,7 @@ c <span class="hljs-number">7</span> <span class="hljs-number">8</span>
<pre><code class="python language-python hljs">&lt;GB&gt; = &lt;DF&gt;.groupby(column_key/s) <span class="hljs-comment"># DF is split into groups based on passed column.</span>
&lt;DF&gt; = &lt;GB&gt;.get_group(group_key) <span class="hljs-comment"># Selects a group by value of grouping column.</span>
</code></pre>
<div><h4 id="applyaggregatetransform-2">Apply, Aggregate, Transform:</h4><pre><code class="python language-python hljs">&lt;DF&gt; = &lt;GB&gt;.sum/max/mean/idxmax/all() <span class="hljs-comment"># Or: &lt;GB&gt;.apply/agg(&lt;agg_func&gt;)</span>
<div><h4 id="aggregatetransformmap-2">Aggregate, Transform, Map:</h4><pre><code class="python language-python hljs">&lt;DF&gt; = &lt;GB&gt;.sum/max/mean/idxmax/all() <span class="hljs-comment"># Or: &lt;GB&gt;.apply/agg(&lt;agg_func&gt;)</span>
&lt;DF&gt; = &lt;GB&gt;.rank/diff/cumsum/ffill() <span class="hljs-comment"># Or: &lt;GB&gt;.aggregate(&lt;trans_func&gt;) </span>
&lt;DF&gt; = &lt;GB&gt;.fillna(&lt;el&gt;) <span class="hljs-comment"># Or: &lt;GB&gt;.transform(&lt;map_func&gt;)</span>
</code></pre></div>
@ -2803,20 +2800,20 @@ c <span class="hljs-number">7</span> <span class="hljs-number">8</span>
<span class="hljs-number">6</span>: b <span class="hljs-number">4</span> <span class="hljs-number">5</span> <span class="hljs-number">6</span>
c <span class="hljs-number">7</span> <span class="hljs-number">8</span> <span class="hljs-number">6</span>
</code></pre>
<pre><code class="python language-python hljs">+-------------+-------------+-------------+-------------+---------------+
| | <span class="hljs-string">'sum'</span> | <span class="hljs-string">'rank'</span> | [<span class="hljs-string">'rank'</span>] | {<span class="hljs-string">'x'</span>: <span class="hljs-string">'rank'</span>} |
+-------------+-------------+-------------+-------------+---------------+
| gb.agg(…) | x y | x y | x y | x |
| | z | a <span class="hljs-number">1</span> <span class="hljs-number">1</span> | rank rank | a <span class="hljs-number">1</span> |
| | <span class="hljs-number">3</span> <span class="hljs-number">1</span> <span class="hljs-number">2</span> | b <span class="hljs-number">1</span> <span class="hljs-number">1</span> | a <span class="hljs-number">1</span> <span class="hljs-number">1</span> | b <span class="hljs-number">1</span> |
| | <span class="hljs-number">6</span> <span class="hljs-number">11</span> <span class="hljs-number">13</span> | c <span class="hljs-number">2</span> <span class="hljs-number">2</span> | b <span class="hljs-number">1</span> <span class="hljs-number">1</span> | c <span class="hljs-number">2</span> |
| | | | c <span class="hljs-number">2</span> <span class="hljs-number">2</span> | |
+-------------+-------------+-------------+-------------+---------------+
| gb.trans(…) | x y | x y | | |
| | a <span class="hljs-number">1</span> <span class="hljs-number">2</span> | a <span class="hljs-number">1</span> <span class="hljs-number">1</span> | | |
| | b <span class="hljs-number">11</span> <span class="hljs-number">13</span> | b <span class="hljs-number">1</span> <span class="hljs-number">1</span> | | |
| | c <span class="hljs-number">11</span> <span class="hljs-number">13</span> | c <span class="hljs-number">1</span> <span class="hljs-number">1</span> | | |
+-------------+-------------+-------------+-------------+---------------+
<pre><code class="python language-python hljs">┏━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━┯━━━━━━━━━━━━━━━┓
┃ │ <span class="hljs-string">'sum'</span> │ <span class="hljs-string">'rank'</span> │ [<span class="hljs-string">'rank'</span>] │ {<span class="hljs-string">'x'</span>: <span class="hljs-string">'rank'</span>} ┃
┠─────────────┼─────────────┼─────────────┼─────────────┼───────────────┨
┃ gb.agg(…) │ x y │ x y │ x y │ x ┃
┃ │ z │ a <span class="hljs-number">1</span> <span class="hljs-number">1</span> │ rank rank │ a <span class="hljs-number">1</span> ┃
┃ │ <span class="hljs-number">3</span> <span class="hljs-number">1</span> <span class="hljs-number">2</span> │ b <span class="hljs-number">1</span> <span class="hljs-number">1</span> │ a <span class="hljs-number">1</span> <span class="hljs-number">1</span> │ b <span class="hljs-number">1</span> ┃
┃ │ <span class="hljs-number">6</span> <span class="hljs-number">11</span> <span class="hljs-number">13</span> │ c <span class="hljs-number">2</span> <span class="hljs-number">2</span> │ b <span class="hljs-number">1</span> <span class="hljs-number">1</span> │ c <span class="hljs-number">2</span> ┃
┃ │ │ │ c <span class="hljs-number">2</span> <span class="hljs-number">2</span> │ ┃
┠─────────────┼─────────────┼─────────────┼─────────────┼───────────────┨
┃ gb.trans(…) │ x y │ x y │ │ ┃
┃ │ a <span class="hljs-number">1</span> <span class="hljs-number">2</span> │ a <span class="hljs-number">1</span> <span class="hljs-number">1</span> │ │ ┃
┃ │ b <span class="hljs-number">11</span> <span class="hljs-number">13</span> │ b <span class="hljs-number">1</span> <span class="hljs-number">1</span> │ │ ┃
┃ │ c <span class="hljs-number">11</span> <span class="hljs-number">13</span> │ c <span class="hljs-number">1</span> <span class="hljs-number">1</span> │ │ ┃
┗━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━┷━━━━━━━━━━━━━━━┛
</code></pre>
<div><h3 id="rolling">Rolling</h3><p><strong>Object for rolling window calculations.</strong></p><pre><code class="python language-python hljs">&lt;R_Sr/R_DF/R_GB&gt; = &lt;Sr/DF/GB&gt;.rolling(window_size) <span class="hljs-comment"># Also: `min_periods=None, center=False`.</span>
&lt;R_Sr/R_DF&gt; = &lt;R_DF/R_GB&gt;[column_key/s] <span class="hljs-comment"># Or: &lt;R&gt;.column_key</span>

Write Preview
Loading…
Cancel
Save