From f5f90d2d680991cb6ac1a586d806599115458ddc Mon Sep 17 00:00:00 2001
From: Mark Santcroos <m.a.santcroos@lumc.nl>
Date: Wed, 20 Sep 2017 10:34:12 +0200
Subject: [PATCH] Update.
---
pandas/pandas.ipynb | 3915 ++++++++++++++++++++++++++++++++++++++-----
1 file changed, 3506 insertions(+), 409 deletions(-)
diff --git a/pandas/pandas.ipynb b/pandas/pandas.ipynb
index 31cfbf3..84acfe8 100644
--- a/pandas/pandas.ipynb
+++ b/pandas/pandas.ipynb
@@ -83,7 +83,7 @@
},
{
"cell_type": "code",
- "execution_count": 96,
+ "execution_count": 471,
"metadata": {
"collapsed": true
},
@@ -95,7 +95,7 @@
},
{
"cell_type": "code",
- "execution_count": 97,
+ "execution_count": 472,
"metadata": {},
"outputs": [
{
@@ -104,7 +104,7 @@
"u'0.20.1'"
]
},
- "execution_count": 97,
+ "execution_count": 472,
"metadata": {},
"output_type": "execute_result"
}
@@ -129,7 +129,7 @@
},
{
"cell_type": "code",
- "execution_count": 98,
+ "execution_count": 473,
"metadata": {},
"outputs": [
{
@@ -144,7 +144,7 @@
"dtype: float64"
]
},
- "execution_count": 98,
+ "execution_count": 473,
"metadata": {},
"output_type": "execute_result"
}
@@ -164,7 +164,7 @@
},
{
"cell_type": "code",
- "execution_count": 99,
+ "execution_count": 474,
"metadata": {},
"outputs": [
{
@@ -175,7 +175,7 @@
" dtype='datetime64[ns]', freq='D')"
]
},
- "execution_count": 99,
+ "execution_count": 474,
"metadata": {},
"output_type": "execute_result"
}
@@ -188,21 +188,21 @@
},
{
"cell_type": "code",
- "execution_count": 100,
+ "execution_count": 475,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "array([[ 0.23051414, -0.28580632, 0.35457973, 1.63813223],\n",
- " [ 1.46610552, 0.36143299, -0.69967186, 0.5909181 ],\n",
- " [ 0.85840437, -0.20824091, -0.32334378, -0.26983698],\n",
- " [ 0.26830511, -0.78065576, -0.22962856, 0.77808124],\n",
- " [ 1.83936044, 1.14887577, 1.2779539 , 0.70010126],\n",
- " [-1.19054289, 0.91047078, -0.0720562 , -0.41625165]])"
+ "array([[-0.19285917, 0.32914174, 1.05612678, 0.90109364],\n",
+ " [-0.52196454, -0.77643073, -0.05150983, 0.87993839],\n",
+ " [ 0.82601868, -0.44544422, 2.14961986, 1.79456143],\n",
+ " [ 0.37800763, -0.55051725, 1.70024071, 0.85985274],\n",
+ " [-0.35328306, 2.52404431, -0.73611908, -0.32295207],\n",
+ " [ 0.68458742, -0.49398027, 0.17228974, -0.11312861]])"
]
},
- "execution_count": 100,
+ "execution_count": 475,
"metadata": {},
"output_type": "execute_result"
}
@@ -215,7 +215,7 @@
},
{
"cell_type": "code",
- "execution_count": 101,
+ "execution_count": 476,
"metadata": {},
"outputs": [],
"source": [
@@ -224,7 +224,7 @@
},
{
"cell_type": "code",
- "execution_count": 102,
+ "execution_count": 477,
"metadata": {},
"outputs": [
{
@@ -257,45 +257,45 @@
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
- " <td>0.230514</td>\n",
- " <td>-0.285806</td>\n",
- " <td>0.354580</td>\n",
- " <td>1.638132</td>\n",
+ " <td>-0.192859</td>\n",
+ " <td>0.329142</td>\n",
+ " <td>1.056127</td>\n",
+ " <td>0.901094</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
- " <td>1.466106</td>\n",
- " <td>0.361433</td>\n",
- " <td>-0.699672</td>\n",
- " <td>0.590918</td>\n",
+ " <td>-0.521965</td>\n",
+ " <td>-0.776431</td>\n",
+ " <td>-0.051510</td>\n",
+ " <td>0.879938</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
- " <td>0.858404</td>\n",
- " <td>-0.208241</td>\n",
- " <td>-0.323344</td>\n",
- " <td>-0.269837</td>\n",
+ " <td>0.826019</td>\n",
+ " <td>-0.445444</td>\n",
+ " <td>2.149620</td>\n",
+ " <td>1.794561</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
- " <td>0.268305</td>\n",
- " <td>-0.780656</td>\n",
- " <td>-0.229629</td>\n",
- " <td>0.778081</td>\n",
+ " <td>0.378008</td>\n",
+ " <td>-0.550517</td>\n",
+ " <td>1.700241</td>\n",
+ " <td>0.859853</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
- " <td>1.839360</td>\n",
- " <td>1.148876</td>\n",
- " <td>1.277954</td>\n",
- " <td>0.700101</td>\n",
+ " <td>-0.353283</td>\n",
+ " <td>2.524044</td>\n",
+ " <td>-0.736119</td>\n",
+ " <td>-0.322952</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
- " <td>-1.190543</td>\n",
- " <td>0.910471</td>\n",
- " <td>-0.072056</td>\n",
- " <td>-0.416252</td>\n",
+ " <td>0.684587</td>\n",
+ " <td>-0.493980</td>\n",
+ " <td>0.172290</td>\n",
+ " <td>-0.113129</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
@@ -303,15 +303,15 @@
],
"text/plain": [
" A B D C\n",
- "0 0.230514 -0.285806 0.354580 1.638132\n",
- "1 1.466106 0.361433 -0.699672 0.590918\n",
- "2 0.858404 -0.208241 -0.323344 -0.269837\n",
- "3 0.268305 -0.780656 -0.229629 0.778081\n",
- "4 1.839360 1.148876 1.277954 0.700101\n",
- "5 -1.190543 0.910471 -0.072056 -0.416252"
+ "0 -0.192859 0.329142 1.056127 0.901094\n",
+ "1 -0.521965 -0.776431 -0.051510 0.879938\n",
+ "2 0.826019 -0.445444 2.149620 1.794561\n",
+ "3 0.378008 -0.550517 1.700241 0.859853\n",
+ "4 -0.353283 2.524044 -0.736119 -0.322952\n",
+ "5 0.684587 -0.493980 0.172290 -0.113129"
]
},
- "execution_count": 102,
+ "execution_count": 477,
"metadata": {},
"output_type": "execute_result"
}
@@ -322,7 +322,7 @@
},
{
"cell_type": "code",
- "execution_count": 103,
+ "execution_count": 478,
"metadata": {},
"outputs": [],
"source": [
@@ -331,7 +331,7 @@
},
{
"cell_type": "code",
- "execution_count": 104,
+ "execution_count": 479,
"metadata": {},
"outputs": [
{
@@ -364,45 +364,45 @@
" <tbody>\n",
" <tr>\n",
" <th>2017-09-01</th>\n",
- " <td>0.230514</td>\n",
- " <td>-0.285806</td>\n",
- " <td>0.354580</td>\n",
- " <td>1.638132</td>\n",
+ " <td>-0.192859</td>\n",
+ " <td>0.329142</td>\n",
+ " <td>1.056127</td>\n",
+ " <td>0.901094</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-02</th>\n",
- " <td>1.466106</td>\n",
- " <td>0.361433</td>\n",
- " <td>-0.699672</td>\n",
- " <td>0.590918</td>\n",
+ " <td>-0.521965</td>\n",
+ " <td>-0.776431</td>\n",
+ " <td>-0.051510</td>\n",
+ " <td>0.879938</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-03</th>\n",
- " <td>0.858404</td>\n",
- " <td>-0.208241</td>\n",
- " <td>-0.323344</td>\n",
- " <td>-0.269837</td>\n",
+ " <td>0.826019</td>\n",
+ " <td>-0.445444</td>\n",
+ " <td>2.149620</td>\n",
+ " <td>1.794561</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-04</th>\n",
- " <td>0.268305</td>\n",
- " <td>-0.780656</td>\n",
- " <td>-0.229629</td>\n",
- " <td>0.778081</td>\n",
+ " <td>0.378008</td>\n",
+ " <td>-0.550517</td>\n",
+ " <td>1.700241</td>\n",
+ " <td>0.859853</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-05</th>\n",
- " <td>1.839360</td>\n",
- " <td>1.148876</td>\n",
- " <td>1.277954</td>\n",
- " <td>0.700101</td>\n",
+ " <td>-0.353283</td>\n",
+ " <td>2.524044</td>\n",
+ " <td>-0.736119</td>\n",
+ " <td>-0.322952</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-06</th>\n",
- " <td>-1.190543</td>\n",
- " <td>0.910471</td>\n",
- " <td>-0.072056</td>\n",
- " <td>-0.416252</td>\n",
+ " <td>0.684587</td>\n",
+ " <td>-0.493980</td>\n",
+ " <td>0.172290</td>\n",
+ " <td>-0.113129</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
@@ -410,15 +410,15 @@
],
"text/plain": [
" A B D C\n",
- "2017-09-01 0.230514 -0.285806 0.354580 1.638132\n",
- "2017-09-02 1.466106 0.361433 -0.699672 0.590918\n",
- "2017-09-03 0.858404 -0.208241 -0.323344 -0.269837\n",
- "2017-09-04 0.268305 -0.780656 -0.229629 0.778081\n",
- "2017-09-05 1.839360 1.148876 1.277954 0.700101\n",
- "2017-09-06 -1.190543 0.910471 -0.072056 -0.416252"
+ "2017-09-01 -0.192859 0.329142 1.056127 0.901094\n",
+ "2017-09-02 -0.521965 -0.776431 -0.051510 0.879938\n",
+ "2017-09-03 0.826019 -0.445444 2.149620 1.794561\n",
+ "2017-09-04 0.378008 -0.550517 1.700241 0.859853\n",
+ "2017-09-05 -0.353283 2.524044 -0.736119 -0.322952\n",
+ "2017-09-06 0.684587 -0.493980 0.172290 -0.113129"
]
},
- "execution_count": 104,
+ "execution_count": 479,
"metadata": {},
"output_type": "execute_result"
}
@@ -429,7 +429,7 @@
},
{
"cell_type": "code",
- "execution_count": 105,
+ "execution_count": 480,
"metadata": {},
"outputs": [
{
@@ -510,7 +510,7 @@
"3 1.0 2017-09-20 1.0 3 EMC researcher"
]
},
- "execution_count": 105,
+ "execution_count": 480,
"metadata": {},
"output_type": "execute_result"
}
@@ -529,7 +529,7 @@
},
{
"cell_type": "code",
- "execution_count": 106,
+ "execution_count": 481,
"metadata": {},
"outputs": [
{
@@ -544,7 +544,7 @@
"dtype: object"
]
},
- "execution_count": 106,
+ "execution_count": 481,
"metadata": {},
"output_type": "execute_result"
}
@@ -562,7 +562,7 @@
},
{
"cell_type": "code",
- "execution_count": 107,
+ "execution_count": 482,
"metadata": {
"collapsed": true
},
@@ -587,7 +587,7 @@
},
{
"cell_type": "code",
- "execution_count": 108,
+ "execution_count": 483,
"metadata": {},
"outputs": [
{
@@ -620,38 +620,38 @@
" <tbody>\n",
" <tr>\n",
" <th>2017-09-01</th>\n",
- " <td>0.230514</td>\n",
- " <td>-0.285806</td>\n",
- " <td>0.354580</td>\n",
- " <td>1.638132</td>\n",
+ " <td>-0.192859</td>\n",
+ " <td>0.329142</td>\n",
+ " <td>1.056127</td>\n",
+ " <td>0.901094</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-02</th>\n",
- " <td>1.466106</td>\n",
- " <td>0.361433</td>\n",
- " <td>-0.699672</td>\n",
- " <td>0.590918</td>\n",
+ " <td>-0.521965</td>\n",
+ " <td>-0.776431</td>\n",
+ " <td>-0.051510</td>\n",
+ " <td>0.879938</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-03</th>\n",
- " <td>0.858404</td>\n",
- " <td>-0.208241</td>\n",
- " <td>-0.323344</td>\n",
- " <td>-0.269837</td>\n",
+ " <td>0.826019</td>\n",
+ " <td>-0.445444</td>\n",
+ " <td>2.149620</td>\n",
+ " <td>1.794561</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-04</th>\n",
- " <td>0.268305</td>\n",
- " <td>-0.780656</td>\n",
- " <td>-0.229629</td>\n",
- " <td>0.778081</td>\n",
+ " <td>0.378008</td>\n",
+ " <td>-0.550517</td>\n",
+ " <td>1.700241</td>\n",
+ " <td>0.859853</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-05</th>\n",
- " <td>1.839360</td>\n",
- " <td>1.148876</td>\n",
- " <td>1.277954</td>\n",
- " <td>0.700101</td>\n",
+ " <td>-0.353283</td>\n",
+ " <td>2.524044</td>\n",
+ " <td>-0.736119</td>\n",
+ " <td>-0.322952</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
@@ -659,14 +659,14 @@
],
"text/plain": [
" A B D C\n",
- "2017-09-01 0.230514 -0.285806 0.354580 1.638132\n",
- "2017-09-02 1.466106 0.361433 -0.699672 0.590918\n",
- "2017-09-03 0.858404 -0.208241 -0.323344 -0.269837\n",
- "2017-09-04 0.268305 -0.780656 -0.229629 0.778081\n",
- "2017-09-05 1.839360 1.148876 1.277954 0.700101"
+ "2017-09-01 -0.192859 0.329142 1.056127 0.901094\n",
+ "2017-09-02 -0.521965 -0.776431 -0.051510 0.879938\n",
+ "2017-09-03 0.826019 -0.445444 2.149620 1.794561\n",
+ "2017-09-04 0.378008 -0.550517 1.700241 0.859853\n",
+ "2017-09-05 -0.353283 2.524044 -0.736119 -0.322952"
]
},
- "execution_count": 108,
+ "execution_count": 483,
"metadata": {},
"output_type": "execute_result"
}
@@ -677,7 +677,7 @@
},
{
"cell_type": "code",
- "execution_count": 109,
+ "execution_count": 484,
"metadata": {},
"outputs": [
{
@@ -710,17 +710,17 @@
" <tbody>\n",
" <tr>\n",
" <th>2017-09-05</th>\n",
- " <td>1.839360</td>\n",
- " <td>1.148876</td>\n",
- " <td>1.277954</td>\n",
- " <td>0.700101</td>\n",
+ " <td>-0.353283</td>\n",
+ " <td>2.524044</td>\n",
+ " <td>-0.736119</td>\n",
+ " <td>-0.322952</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-06</th>\n",
- " <td>-1.190543</td>\n",
- " <td>0.910471</td>\n",
- " <td>-0.072056</td>\n",
- " <td>-0.416252</td>\n",
+ " <td>0.684587</td>\n",
+ " <td>-0.493980</td>\n",
+ " <td>0.172290</td>\n",
+ " <td>-0.113129</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
@@ -728,11 +728,11 @@
],
"text/plain": [
" A B D C\n",
- "2017-09-05 1.839360 1.148876 1.277954 0.700101\n",
- "2017-09-06 -1.190543 0.910471 -0.072056 -0.416252"
+ "2017-09-05 -0.353283 2.524044 -0.736119 -0.322952\n",
+ "2017-09-06 0.684587 -0.493980 0.172290 -0.113129"
]
},
- "execution_count": 109,
+ "execution_count": 484,
"metadata": {},
"output_type": "execute_result"
}
@@ -750,7 +750,7 @@
},
{
"cell_type": "code",
- "execution_count": 110,
+ "execution_count": 485,
"metadata": {},
"outputs": [
{
@@ -761,7 +761,7 @@
" dtype='datetime64[ns]', freq='D')"
]
},
- "execution_count": 110,
+ "execution_count": 485,
"metadata": {},
"output_type": "execute_result"
}
@@ -772,7 +772,7 @@
},
{
"cell_type": "code",
- "execution_count": 111,
+ "execution_count": 486,
"metadata": {},
"outputs": [
{
@@ -781,7 +781,7 @@
"Index([u'A', u'B', u'D', u'C'], dtype='object')"
]
},
- "execution_count": 111,
+ "execution_count": 486,
"metadata": {},
"output_type": "execute_result"
}
@@ -792,21 +792,21 @@
},
{
"cell_type": "code",
- "execution_count": 112,
+ "execution_count": 487,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "array([[ 0.23051414, -0.28580632, 0.35457973, 1.63813223],\n",
- " [ 1.46610552, 0.36143299, -0.69967186, 0.5909181 ],\n",
- " [ 0.85840437, -0.20824091, -0.32334378, -0.26983698],\n",
- " [ 0.26830511, -0.78065576, -0.22962856, 0.77808124],\n",
- " [ 1.83936044, 1.14887577, 1.2779539 , 0.70010126],\n",
- " [-1.19054289, 0.91047078, -0.0720562 , -0.41625165]])"
+ "array([[-0.19285917, 0.32914174, 1.05612678, 0.90109364],\n",
+ " [-0.52196454, -0.77643073, -0.05150983, 0.87993839],\n",
+ " [ 0.82601868, -0.44544422, 2.14961986, 1.79456143],\n",
+ " [ 0.37800763, -0.55051725, 1.70024071, 0.85985274],\n",
+ " [-0.35328306, 2.52404431, -0.73611908, -0.32295207],\n",
+ " [ 0.68458742, -0.49398027, 0.17228974, -0.11312861]])"
]
},
- "execution_count": 112,
+ "execution_count": 487,
"metadata": {},
"output_type": "execute_result"
}
@@ -824,7 +824,7 @@
},
{
"cell_type": "code",
- "execution_count": 113,
+ "execution_count": 488,
"metadata": {},
"outputs": [
{
@@ -864,52 +864,52 @@
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
- " <td>0.578691</td>\n",
- " <td>0.191013</td>\n",
- " <td>0.051306</td>\n",
- " <td>0.503524</td>\n",
+ " <td>0.136751</td>\n",
+ " <td>0.097802</td>\n",
+ " <td>0.715108</td>\n",
+ " <td>0.666561</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
- " <td>1.077292</td>\n",
- " <td>0.747672</td>\n",
- " <td>0.692115</td>\n",
- " <td>0.755390</td>\n",
+ " <td>0.568525</td>\n",
+ " <td>1.246603</td>\n",
+ " <td>1.107521</td>\n",
+ " <td>0.774252</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
- " <td>-1.190543</td>\n",
- " <td>-0.780656</td>\n",
- " <td>-0.699672</td>\n",
- " <td>-0.416252</td>\n",
+ " <td>-0.521965</td>\n",
+ " <td>-0.776431</td>\n",
+ " <td>-0.736119</td>\n",
+ " <td>-0.322952</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
- " <td>0.239962</td>\n",
- " <td>-0.266415</td>\n",
- " <td>-0.299915</td>\n",
- " <td>-0.054648</td>\n",
+ " <td>-0.313177</td>\n",
+ " <td>-0.536383</td>\n",
+ " <td>0.004440</td>\n",
+ " <td>0.130117</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
- " <td>0.563355</td>\n",
- " <td>0.076596</td>\n",
- " <td>-0.150842</td>\n",
- " <td>0.645510</td>\n",
+ " <td>0.092574</td>\n",
+ " <td>-0.469712</td>\n",
+ " <td>0.614208</td>\n",
+ " <td>0.869896</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
- " <td>1.314180</td>\n",
- " <td>0.773211</td>\n",
- " <td>0.247921</td>\n",
- " <td>0.758586</td>\n",
+ " <td>0.607942</td>\n",
+ " <td>0.135495</td>\n",
+ " <td>1.539212</td>\n",
+ " <td>0.895805</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
- " <td>1.839360</td>\n",
- " <td>1.148876</td>\n",
- " <td>1.277954</td>\n",
- " <td>1.638132</td>\n",
+ " <td>0.826019</td>\n",
+ " <td>2.524044</td>\n",
+ " <td>2.149620</td>\n",
+ " <td>1.794561</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
@@ -918,16 +918,16 @@
"text/plain": [
" A B D C\n",
"count 6.000000 6.000000 6.000000 6.000000\n",
- "mean 0.578691 0.191013 0.051306 0.503524\n",
- "std 1.077292 0.747672 0.692115 0.755390\n",
- "min -1.190543 -0.780656 -0.699672 -0.416252\n",
- "25% 0.239962 -0.266415 -0.299915 -0.054648\n",
- "50% 0.563355 0.076596 -0.150842 0.645510\n",
- "75% 1.314180 0.773211 0.247921 0.758586\n",
- "max 1.839360 1.148876 1.277954 1.638132"
+ "mean 0.136751 0.097802 0.715108 0.666561\n",
+ "std 0.568525 1.246603 1.107521 0.774252\n",
+ "min -0.521965 -0.776431 -0.736119 -0.322952\n",
+ "25% -0.313177 -0.536383 0.004440 0.130117\n",
+ "50% 0.092574 -0.469712 0.614208 0.869896\n",
+ "75% 0.607942 0.135495 1.539212 0.895805\n",
+ "max 0.826019 2.524044 2.149620 1.794561"
]
},
- "execution_count": 113,
+ "execution_count": 488,
"metadata": {},
"output_type": "execute_result"
}
@@ -945,7 +945,7 @@
},
{
"cell_type": "code",
- "execution_count": 114,
+ "execution_count": 489,
"metadata": {},
"outputs": [
{
@@ -980,39 +980,39 @@
" <tbody>\n",
" <tr>\n",
" <th>A</th>\n",
- " <td>0.230514</td>\n",
- " <td>1.466106</td>\n",
- " <td>0.858404</td>\n",
- " <td>0.268305</td>\n",
- " <td>1.839360</td>\n",
- " <td>-1.190543</td>\n",
+ " <td>-0.192859</td>\n",
+ " <td>-0.521965</td>\n",
+ " <td>0.826019</td>\n",
+ " <td>0.378008</td>\n",
+ " <td>-0.353283</td>\n",
+ " <td>0.684587</td>\n",
" </tr>\n",
" <tr>\n",
" <th>B</th>\n",
- " <td>-0.285806</td>\n",
- " <td>0.361433</td>\n",
- " <td>-0.208241</td>\n",
- " <td>-0.780656</td>\n",
- " <td>1.148876</td>\n",
- " <td>0.910471</td>\n",
+ " <td>0.329142</td>\n",
+ " <td>-0.776431</td>\n",
+ " <td>-0.445444</td>\n",
+ " <td>-0.550517</td>\n",
+ " <td>2.524044</td>\n",
+ " <td>-0.493980</td>\n",
" </tr>\n",
" <tr>\n",
" <th>D</th>\n",
- " <td>0.354580</td>\n",
- " <td>-0.699672</td>\n",
- " <td>-0.323344</td>\n",
- " <td>-0.229629</td>\n",
- " <td>1.277954</td>\n",
- " <td>-0.072056</td>\n",
+ " <td>1.056127</td>\n",
+ " <td>-0.051510</td>\n",
+ " <td>2.149620</td>\n",
+ " <td>1.700241</td>\n",
+ " <td>-0.736119</td>\n",
+ " <td>0.172290</td>\n",
" </tr>\n",
" <tr>\n",
" <th>C</th>\n",
- " <td>1.638132</td>\n",
- " <td>0.590918</td>\n",
- " <td>-0.269837</td>\n",
- " <td>0.778081</td>\n",
- " <td>0.700101</td>\n",
- " <td>-0.416252</td>\n",
+ " <td>0.901094</td>\n",
+ " <td>0.879938</td>\n",
+ " <td>1.794561</td>\n",
+ " <td>0.859853</td>\n",
+ " <td>-0.322952</td>\n",
+ " <td>-0.113129</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
@@ -1020,13 +1020,13 @@
],
"text/plain": [
" 2017-09-01 2017-09-02 2017-09-03 2017-09-04 2017-09-05 2017-09-06\n",
- "A 0.230514 1.466106 0.858404 0.268305 1.839360 -1.190543\n",
- "B -0.285806 0.361433 -0.208241 -0.780656 1.148876 0.910471\n",
- "D 0.354580 -0.699672 -0.323344 -0.229629 1.277954 -0.072056\n",
- "C 1.638132 0.590918 -0.269837 0.778081 0.700101 -0.416252"
+ "A -0.192859 -0.521965 0.826019 0.378008 -0.353283 0.684587\n",
+ "B 0.329142 -0.776431 -0.445444 -0.550517 2.524044 -0.493980\n",
+ "D 1.056127 -0.051510 2.149620 1.700241 -0.736119 0.172290\n",
+ "C 0.901094 0.879938 1.794561 0.859853 -0.322952 -0.113129"
]
},
- "execution_count": 114,
+ "execution_count": 489,
"metadata": {},
"output_type": "execute_result"
}
@@ -1044,7 +1044,7 @@
},
{
"cell_type": "code",
- "execution_count": 121,
+ "execution_count": 490,
"metadata": {},
"outputs": [
{
@@ -1077,45 +1077,45 @@
" <tbody>\n",
" <tr>\n",
" <th>2017-09-01</th>\n",
- " <td>0.230514</td>\n",
- " <td>-0.285806</td>\n",
- " <td>1.638132</td>\n",
- " <td>0.354580</td>\n",
+ " <td>-0.192859</td>\n",
+ " <td>0.329142</td>\n",
+ " <td>0.901094</td>\n",
+ " <td>1.056127</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-02</th>\n",
- " <td>1.466106</td>\n",
- " <td>0.361433</td>\n",
- " <td>0.590918</td>\n",
- " <td>-0.699672</td>\n",
+ " <td>-0.521965</td>\n",
+ " <td>-0.776431</td>\n",
+ " <td>0.879938</td>\n",
+ " <td>-0.051510</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-03</th>\n",
- " <td>0.858404</td>\n",
- " <td>-0.208241</td>\n",
- " <td>-0.269837</td>\n",
- " <td>-0.323344</td>\n",
+ " <td>0.826019</td>\n",
+ " <td>-0.445444</td>\n",
+ " <td>1.794561</td>\n",
+ " <td>2.149620</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-04</th>\n",
- " <td>0.268305</td>\n",
- " <td>-0.780656</td>\n",
- " <td>0.778081</td>\n",
- " <td>-0.229629</td>\n",
+ " <td>0.378008</td>\n",
+ " <td>-0.550517</td>\n",
+ " <td>0.859853</td>\n",
+ " <td>1.700241</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-05</th>\n",
- " <td>1.839360</td>\n",
- " <td>1.148876</td>\n",
- " <td>0.700101</td>\n",
- " <td>1.277954</td>\n",
+ " <td>-0.353283</td>\n",
+ " <td>2.524044</td>\n",
+ " <td>-0.322952</td>\n",
+ " <td>-0.736119</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-06</th>\n",
- " <td>-1.190543</td>\n",
- " <td>0.910471</td>\n",
- " <td>-0.416252</td>\n",
- " <td>-0.072056</td>\n",
+ " <td>0.684587</td>\n",
+ " <td>-0.493980</td>\n",
+ " <td>-0.113129</td>\n",
+ " <td>0.172290</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
@@ -1123,15 +1123,15 @@
],
"text/plain": [
" A B C D\n",
- "2017-09-01 0.230514 -0.285806 1.638132 0.354580\n",
- "2017-09-02 1.466106 0.361433 0.590918 -0.699672\n",
- "2017-09-03 0.858404 -0.208241 -0.269837 -0.323344\n",
- "2017-09-04 0.268305 -0.780656 0.778081 -0.229629\n",
- "2017-09-05 1.839360 1.148876 0.700101 1.277954\n",
- "2017-09-06 -1.190543 0.910471 -0.416252 -0.072056"
+ "2017-09-01 -0.192859 0.329142 0.901094 1.056127\n",
+ "2017-09-02 -0.521965 -0.776431 0.879938 -0.051510\n",
+ "2017-09-03 0.826019 -0.445444 1.794561 2.149620\n",
+ "2017-09-04 0.378008 -0.550517 0.859853 1.700241\n",
+ "2017-09-05 -0.353283 2.524044 -0.322952 -0.736119\n",
+ "2017-09-06 0.684587 -0.493980 -0.113129 0.172290"
]
},
- "execution_count": 121,
+ "execution_count": 490,
"metadata": {},
"output_type": "execute_result"
}
@@ -1143,7 +1143,7 @@
},
{
"cell_type": "code",
- "execution_count": 116,
+ "execution_count": 491,
"metadata": {},
"outputs": [
{
@@ -1175,46 +1175,46 @@
" </thead>\n",
" <tbody>\n",
" <tr>\n",
- " <th>2017-09-04</th>\n",
- " <td>0.268305</td>\n",
- " <td>-0.780656</td>\n",
- " <td>-0.229629</td>\n",
- " <td>0.778081</td>\n",
+ " <th>2017-09-02</th>\n",
+ " <td>-0.521965</td>\n",
+ " <td>-0.776431</td>\n",
+ " <td>-0.051510</td>\n",
+ " <td>0.879938</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>2017-09-01</th>\n",
- " <td>0.230514</td>\n",
- " <td>-0.285806</td>\n",
- " <td>0.354580</td>\n",
- " <td>1.638132</td>\n",
+ " <th>2017-09-04</th>\n",
+ " <td>0.378008</td>\n",
+ " <td>-0.550517</td>\n",
+ " <td>1.700241</td>\n",
+ " <td>0.859853</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>2017-09-03</th>\n",
- " <td>0.858404</td>\n",
- " <td>-0.208241</td>\n",
- " <td>-0.323344</td>\n",
- " <td>-0.269837</td>\n",
+ " <th>2017-09-06</th>\n",
+ " <td>0.684587</td>\n",
+ " <td>-0.493980</td>\n",
+ " <td>0.172290</td>\n",
+ " <td>-0.113129</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>2017-09-02</th>\n",
- " <td>1.466106</td>\n",
- " <td>0.361433</td>\n",
- " <td>-0.699672</td>\n",
- " <td>0.590918</td>\n",
+ " <th>2017-09-03</th>\n",
+ " <td>0.826019</td>\n",
+ " <td>-0.445444</td>\n",
+ " <td>2.149620</td>\n",
+ " <td>1.794561</td>\n",
" </tr>\n",
" <tr>\n",
- " <th>2017-09-06</th>\n",
- " <td>-1.190543</td>\n",
- " <td>0.910471</td>\n",
- " <td>-0.072056</td>\n",
- " <td>-0.416252</td>\n",
+ " <th>2017-09-01</th>\n",
+ " <td>-0.192859</td>\n",
+ " <td>0.329142</td>\n",
+ " <td>1.056127</td>\n",
+ " <td>0.901094</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-05</th>\n",
- " <td>1.839360</td>\n",
- " <td>1.148876</td>\n",
- " <td>1.277954</td>\n",
- " <td>0.700101</td>\n",
+ " <td>-0.353283</td>\n",
+ " <td>2.524044</td>\n",
+ " <td>-0.736119</td>\n",
+ " <td>-0.322952</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
@@ -1222,15 +1222,15 @@
],
"text/plain": [
" A B D C\n",
- "2017-09-04 0.268305 -0.780656 -0.229629 0.778081\n",
- "2017-09-01 0.230514 -0.285806 0.354580 1.638132\n",
- "2017-09-03 0.858404 -0.208241 -0.323344 -0.269837\n",
- "2017-09-02 1.466106 0.361433 -0.699672 0.590918\n",
- "2017-09-06 -1.190543 0.910471 -0.072056 -0.416252\n",
- "2017-09-05 1.839360 1.148876 1.277954 0.700101"
+ "2017-09-02 -0.521965 -0.776431 -0.051510 0.879938\n",
+ "2017-09-04 0.378008 -0.550517 1.700241 0.859853\n",
+ "2017-09-06 0.684587 -0.493980 0.172290 -0.113129\n",
+ "2017-09-03 0.826019 -0.445444 2.149620 1.794561\n",
+ "2017-09-01 -0.192859 0.329142 1.056127 0.901094\n",
+ "2017-09-05 -0.353283 2.524044 -0.736119 -0.322952"
]
},
- "execution_count": 116,
+ "execution_count": 491,
"metadata": {},
"output_type": "execute_result"
}
@@ -1256,22 +1256,22 @@
},
{
"cell_type": "code",
- "execution_count": 125,
+ "execution_count": 492,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "2017-09-01 0.230514\n",
- "2017-09-02 1.466106\n",
- "2017-09-03 0.858404\n",
- "2017-09-04 0.268305\n",
- "2017-09-05 1.839360\n",
- "2017-09-06 -1.190543\n",
+ "2017-09-01 -0.192859\n",
+ "2017-09-02 -0.521965\n",
+ "2017-09-03 0.826019\n",
+ "2017-09-04 0.378008\n",
+ "2017-09-05 -0.353283\n",
+ "2017-09-06 0.684587\n",
"Freq: D, Name: A, dtype: float64"
]
},
- "execution_count": 125,
+ "execution_count": 492,
"metadata": {},
"output_type": "execute_result"
}
@@ -1283,7 +1283,7 @@
},
{
"cell_type": "code",
- "execution_count": 130,
+ "execution_count": 493,
"metadata": {},
"outputs": [
{
@@ -1316,24 +1316,24 @@
" <tbody>\n",
" <tr>\n",
" <th>2017-09-02</th>\n",
- " <td>1.466106</td>\n",
- " <td>0.361433</td>\n",
- " <td>-0.699672</td>\n",
- " <td>0.590918</td>\n",
+ " <td>-0.521965</td>\n",
+ " <td>-0.776431</td>\n",
+ " <td>-0.051510</td>\n",
+ " <td>0.879938</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-03</th>\n",
- " <td>0.858404</td>\n",
- " <td>-0.208241</td>\n",
- " <td>-0.323344</td>\n",
- " <td>-0.269837</td>\n",
+ " <td>0.826019</td>\n",
+ " <td>-0.445444</td>\n",
+ " <td>2.149620</td>\n",
+ " <td>1.794561</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-04</th>\n",
- " <td>0.268305</td>\n",
- " <td>-0.780656</td>\n",
- " <td>-0.229629</td>\n",
- " <td>0.778081</td>\n",
+ " <td>0.378008</td>\n",
+ " <td>-0.550517</td>\n",
+ " <td>1.700241</td>\n",
+ " <td>0.859853</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
@@ -1341,12 +1341,12 @@
],
"text/plain": [
" A B D C\n",
- "2017-09-02 1.466106 0.361433 -0.699672 0.590918\n",
- "2017-09-03 0.858404 -0.208241 -0.323344 -0.269837\n",
- "2017-09-04 0.268305 -0.780656 -0.229629 0.778081"
+ "2017-09-02 -0.521965 -0.776431 -0.051510 0.879938\n",
+ "2017-09-03 0.826019 -0.445444 2.149620 1.794561\n",
+ "2017-09-04 0.378008 -0.550517 1.700241 0.859853"
]
},
- "execution_count": 130,
+ "execution_count": 493,
"metadata": {},
"output_type": "execute_result"
}
@@ -1358,7 +1358,7 @@
},
{
"cell_type": "code",
- "execution_count": 135,
+ "execution_count": 494,
"metadata": {},
"outputs": [
{
@@ -1391,24 +1391,24 @@
" <tbody>\n",
" <tr>\n",
" <th>2017-09-02</th>\n",
- " <td>1.466106</td>\n",
- " <td>0.361433</td>\n",
- " <td>-0.699672</td>\n",
- " <td>0.590918</td>\n",
+ " <td>-0.521965</td>\n",
+ " <td>-0.776431</td>\n",
+ " <td>-0.051510</td>\n",
+ " <td>0.879938</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-03</th>\n",
- " <td>0.858404</td>\n",
- " <td>-0.208241</td>\n",
- " <td>-0.323344</td>\n",
- " <td>-0.269837</td>\n",
+ " <td>0.826019</td>\n",
+ " <td>-0.445444</td>\n",
+ " <td>2.149620</td>\n",
+ " <td>1.794561</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-04</th>\n",
- " <td>0.268305</td>\n",
- " <td>-0.780656</td>\n",
- " <td>-0.229629</td>\n",
- " <td>0.778081</td>\n",
+ " <td>0.378008</td>\n",
+ " <td>-0.550517</td>\n",
+ " <td>1.700241</td>\n",
+ " <td>0.859853</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
@@ -1416,12 +1416,12 @@
],
"text/plain": [
" A B D C\n",
- "2017-09-02 1.466106 0.361433 -0.699672 0.590918\n",
- "2017-09-03 0.858404 -0.208241 -0.323344 -0.269837\n",
- "2017-09-04 0.268305 -0.780656 -0.229629 0.778081"
+ "2017-09-02 -0.521965 -0.776431 -0.051510 0.879938\n",
+ "2017-09-03 0.826019 -0.445444 2.149620 1.794561\n",
+ "2017-09-04 0.378008 -0.550517 1.700241 0.859853"
]
},
- "execution_count": 135,
+ "execution_count": 494,
"metadata": {},
"output_type": "execute_result"
}
@@ -1433,20 +1433,20 @@
},
{
"cell_type": "code",
- "execution_count": 138,
+ "execution_count": 495,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "A 1.466106\n",
- "B 0.361433\n",
- "D -0.699672\n",
- "C 0.590918\n",
+ "A -0.521965\n",
+ "B -0.776431\n",
+ "D -0.051510\n",
+ "C 0.879938\n",
"Name: 2017-09-02 00:00:00, dtype: float64"
]
},
- "execution_count": 138,
+ "execution_count": 495,
"metadata": {},
"output_type": "execute_result"
}
@@ -1458,7 +1458,7 @@
},
{
"cell_type": "code",
- "execution_count": 145,
+ "execution_count": 496,
"metadata": {},
"outputs": [
{
@@ -1489,33 +1489,33 @@
" <tbody>\n",
" <tr>\n",
" <th>2017-09-01</th>\n",
- " <td>0.230514</td>\n",
- " <td>-0.285806</td>\n",
+ " <td>-0.192859</td>\n",
+ " <td>0.329142</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-02</th>\n",
- " <td>1.466106</td>\n",
- " <td>0.361433</td>\n",
+ " <td>-0.521965</td>\n",
+ " <td>-0.776431</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-03</th>\n",
- " <td>0.858404</td>\n",
- " <td>-0.208241</td>\n",
+ " <td>0.826019</td>\n",
+ " <td>-0.445444</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-04</th>\n",
- " <td>0.268305</td>\n",
- " <td>-0.780656</td>\n",
+ " <td>0.378008</td>\n",
+ " <td>-0.550517</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-05</th>\n",
- " <td>1.839360</td>\n",
- " <td>1.148876</td>\n",
+ " <td>-0.353283</td>\n",
+ " <td>2.524044</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-06</th>\n",
- " <td>-1.190543</td>\n",
- " <td>0.910471</td>\n",
+ " <td>0.684587</td>\n",
+ " <td>-0.493980</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
@@ -1523,15 +1523,15 @@
],
"text/plain": [
" A B\n",
- "2017-09-01 0.230514 -0.285806\n",
- "2017-09-02 1.466106 0.361433\n",
- "2017-09-03 0.858404 -0.208241\n",
- "2017-09-04 0.268305 -0.780656\n",
- "2017-09-05 1.839360 1.148876\n",
- "2017-09-06 -1.190543 0.910471"
+ "2017-09-01 -0.192859 0.329142\n",
+ "2017-09-02 -0.521965 -0.776431\n",
+ "2017-09-03 0.826019 -0.445444\n",
+ "2017-09-04 0.378008 -0.550517\n",
+ "2017-09-05 -0.353283 2.524044\n",
+ "2017-09-06 0.684587 -0.493980"
]
},
- "execution_count": 145,
+ "execution_count": 496,
"metadata": {},
"output_type": "execute_result"
}
@@ -1543,7 +1543,7 @@
},
{
"cell_type": "code",
- "execution_count": 149,
+ "execution_count": 497,
"metadata": {},
"outputs": [
{
@@ -1574,18 +1574,18 @@
" <tbody>\n",
" <tr>\n",
" <th>2017-09-02</th>\n",
- " <td>0.361433</td>\n",
- " <td>0.590918</td>\n",
+ " <td>-0.776431</td>\n",
+ " <td>0.879938</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-03</th>\n",
- " <td>-0.208241</td>\n",
- " <td>-0.269837</td>\n",
+ " <td>-0.445444</td>\n",
+ " <td>1.794561</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-04</th>\n",
- " <td>-0.780656</td>\n",
- " <td>0.778081</td>\n",
+ " <td>-0.550517</td>\n",
+ " <td>0.859853</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
@@ -1593,12 +1593,12 @@
],
"text/plain": [
" B C\n",
- "2017-09-02 0.361433 0.590918\n",
- "2017-09-03 -0.208241 -0.269837\n",
- "2017-09-04 -0.780656 0.778081"
+ "2017-09-02 -0.776431 0.879938\n",
+ "2017-09-03 -0.445444 1.794561\n",
+ "2017-09-04 -0.550517 0.859853"
]
},
- "execution_count": 149,
+ "execution_count": 497,
"metadata": {},
"output_type": "execute_result"
}
@@ -1610,18 +1610,18 @@
},
{
"cell_type": "code",
- "execution_count": 151,
+ "execution_count": 498,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "A 1.466106\n",
- "B 0.361433\n",
+ "A -0.521965\n",
+ "B -0.776431\n",
"Name: 2017-09-02 00:00:00, dtype: float64"
]
},
- "execution_count": 151,
+ "execution_count": 498,
"metadata": {},
"output_type": "execute_result"
}
@@ -1633,16 +1633,16 @@
},
{
"cell_type": "code",
- "execution_count": 153,
+ "execution_count": 499,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "1.4661055188464265"
+ "-0.52196454176237395"
]
},
- "execution_count": 153,
+ "execution_count": 499,
"metadata": {},
"output_type": "execute_result"
}
@@ -1662,20 +1662,20 @@
},
{
"cell_type": "code",
- "execution_count": 157,
+ "execution_count": 500,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "A 0.268305\n",
- "B -0.780656\n",
- "D -0.229629\n",
- "C 0.778081\n",
+ "A 0.378008\n",
+ "B -0.550517\n",
+ "D 1.700241\n",
+ "C 0.859853\n",
"Name: 2017-09-04 00:00:00, dtype: float64"
]
},
- "execution_count": 157,
+ "execution_count": 500,
"metadata": {},
"output_type": "execute_result"
}
@@ -1687,7 +1687,7 @@
},
{
"cell_type": "code",
- "execution_count": 163,
+ "execution_count": 501,
"metadata": {},
"outputs": [
{
@@ -1718,13 +1718,13 @@
" <tbody>\n",
" <tr>\n",
" <th>2017-09-04</th>\n",
- " <td>-0.229629</td>\n",
- " <td>0.778081</td>\n",
+ " <td>1.700241</td>\n",
+ " <td>0.859853</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-05</th>\n",
- " <td>1.277954</td>\n",
- " <td>0.700101</td>\n",
+ " <td>-0.736119</td>\n",
+ " <td>-0.322952</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
@@ -1732,11 +1732,11 @@
],
"text/plain": [
" D C\n",
- "2017-09-04 -0.229629 0.778081\n",
- "2017-09-05 1.277954 0.700101"
+ "2017-09-04 1.700241 0.859853\n",
+ "2017-09-05 -0.736119 -0.322952"
]
},
- "execution_count": 163,
+ "execution_count": 501,
"metadata": {},
"output_type": "execute_result"
}
@@ -1748,7 +1748,7 @@
},
{
"cell_type": "code",
- "execution_count": 164,
+ "execution_count": 502,
"metadata": {},
"outputs": [
{
@@ -1781,29 +1781,29 @@
" <tbody>\n",
" <tr>\n",
" <th>2017-09-02</th>\n",
- " <td>1.466106</td>\n",
- " <td>0.361433</td>\n",
- " <td>-0.699672</td>\n",
- " <td>0.590918</td>\n",
+ " <td>-0.521965</td>\n",
+ " <td>-0.776431</td>\n",
+ " <td>-0.05151</td>\n",
+ " <td>0.879938</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-03</th>\n",
- " <td>0.858404</td>\n",
- " <td>-0.208241</td>\n",
- " <td>-0.323344</td>\n",
- " <td>-0.269837</td>\n",
+ " <td>0.826019</td>\n",
+ " <td>-0.445444</td>\n",
+ " <td>2.14962</td>\n",
+ " <td>1.794561</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
- " A B D C\n",
- "2017-09-02 1.466106 0.361433 -0.699672 0.590918\n",
- "2017-09-03 0.858404 -0.208241 -0.323344 -0.269837"
+ " A B D C\n",
+ "2017-09-02 -0.521965 -0.776431 -0.05151 0.879938\n",
+ "2017-09-03 0.826019 -0.445444 2.14962 1.794561"
]
},
- "execution_count": 164,
+ "execution_count": 502,
"metadata": {},
"output_type": "execute_result"
}
@@ -1814,7 +1814,7 @@
},
{
"cell_type": "code",
- "execution_count": 165,
+ "execution_count": 503,
"metadata": {},
"outputs": [
{
@@ -1845,33 +1845,33 @@
" <tbody>\n",
" <tr>\n",
" <th>2017-09-01</th>\n",
- " <td>-0.285806</td>\n",
- " <td>0.354580</td>\n",
+ " <td>0.329142</td>\n",
+ " <td>1.056127</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-02</th>\n",
- " <td>0.361433</td>\n",
- " <td>-0.699672</td>\n",
+ " <td>-0.776431</td>\n",
+ " <td>-0.051510</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-03</th>\n",
- " <td>-0.208241</td>\n",
- " <td>-0.323344</td>\n",
+ " <td>-0.445444</td>\n",
+ " <td>2.149620</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-04</th>\n",
- " <td>-0.780656</td>\n",
- " <td>-0.229629</td>\n",
+ " <td>-0.550517</td>\n",
+ " <td>1.700241</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-05</th>\n",
- " <td>1.148876</td>\n",
- " <td>1.277954</td>\n",
+ " <td>2.524044</td>\n",
+ " <td>-0.736119</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2017-09-06</th>\n",
- " <td>0.910471</td>\n",
- " <td>-0.072056</td>\n",
+ " <td>-0.493980</td>\n",
+ " <td>0.172290</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
@@ -1879,15 +1879,15 @@
],
"text/plain": [
" B D\n",
- "2017-09-01 -0.285806 0.354580\n",
- "2017-09-02 0.361433 -0.699672\n",
- "2017-09-03 -0.208241 -0.323344\n",
- "2017-09-04 -0.780656 -0.229629\n",
- "2017-09-05 1.148876 1.277954\n",
- "2017-09-06 0.910471 -0.072056"
+ "2017-09-01 0.329142 1.056127\n",
+ "2017-09-02 -0.776431 -0.051510\n",
+ "2017-09-03 -0.445444 2.149620\n",
+ "2017-09-04 -0.550517 1.700241\n",
+ "2017-09-05 2.524044 -0.736119\n",
+ "2017-09-06 -0.493980 0.172290"
]
},
- "execution_count": 165,
+ "execution_count": 503,
"metadata": {},
"output_type": "execute_result"
}
@@ -1898,16 +1898,16 @@
},
{
"cell_type": "code",
- "execution_count": 166,
+ "execution_count": 504,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
- "0.36143299164038073"
+ "-0.77643072890241949"
]
},
- "execution_count": 166,
+ "execution_count": 504,
"metadata": {},
"output_type": "execute_result"
}
@@ -1916,6 +1916,3103 @@
"df.iloc[1,1]"
]
},
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Boolean indexing"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 505,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>A</th>\n",
+ " <th>B</th>\n",
+ " <th>D</th>\n",
+ " <th>C</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>2017-09-03</th>\n",
+ " <td>0.826019</td>\n",
+ " <td>-0.445444</td>\n",
+ " <td>2.149620</td>\n",
+ " <td>1.794561</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-04</th>\n",
+ " <td>0.378008</td>\n",
+ " <td>-0.550517</td>\n",
+ " <td>1.700241</td>\n",
+ " <td>0.859853</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-06</th>\n",
+ " <td>0.684587</td>\n",
+ " <td>-0.493980</td>\n",
+ " <td>0.172290</td>\n",
+ " <td>-0.113129</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " A B D C\n",
+ "2017-09-03 0.826019 -0.445444 2.149620 1.794561\n",
+ "2017-09-04 0.378008 -0.550517 1.700241 0.859853\n",
+ "2017-09-06 0.684587 -0.493980 0.172290 -0.113129"
+ ]
+ },
+ "execution_count": 505,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Using a single column’s values to select data.\n",
+ "df[df.A > 0]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 506,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>A</th>\n",
+ " <th>B</th>\n",
+ " <th>D</th>\n",
+ " <th>C</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>2017-09-01</th>\n",
+ " <td>-0.192859</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-02</th>\n",
+ " <td>-0.521965</td>\n",
+ " <td>-0.776431</td>\n",
+ " <td>-0.051510</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-03</th>\n",
+ " <td>NaN</td>\n",
+ " <td>-0.445444</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-04</th>\n",
+ " <td>NaN</td>\n",
+ " <td>-0.550517</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-05</th>\n",
+ " <td>-0.353283</td>\n",
+ " <td>NaN</td>\n",
+ " <td>-0.736119</td>\n",
+ " <td>-0.322952</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-06</th>\n",
+ " <td>NaN</td>\n",
+ " <td>-0.493980</td>\n",
+ " <td>NaN</td>\n",
+ " <td>-0.113129</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " A B D C\n",
+ "2017-09-01 -0.192859 NaN NaN NaN\n",
+ "2017-09-02 -0.521965 -0.776431 -0.051510 NaN\n",
+ "2017-09-03 NaN -0.445444 NaN NaN\n",
+ "2017-09-04 NaN -0.550517 NaN NaN\n",
+ "2017-09-05 -0.353283 NaN -0.736119 -0.322952\n",
+ "2017-09-06 NaN -0.493980 NaN -0.113129"
+ ]
+ },
+ "execution_count": 506,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Selecting values from a DataFrame where a boolean condition is met.\n",
+ "df[df < 0]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 507,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>A</th>\n",
+ " <th>B</th>\n",
+ " <th>D</th>\n",
+ " <th>C</th>\n",
+ " <th>E</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>2017-09-01</th>\n",
+ " <td>-0.192859</td>\n",
+ " <td>0.329142</td>\n",
+ " <td>1.056127</td>\n",
+ " <td>0.901094</td>\n",
+ " <td>one</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-02</th>\n",
+ " <td>-0.521965</td>\n",
+ " <td>-0.776431</td>\n",
+ " <td>-0.051510</td>\n",
+ " <td>0.879938</td>\n",
+ " <td>one</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-03</th>\n",
+ " <td>0.826019</td>\n",
+ " <td>-0.445444</td>\n",
+ " <td>2.149620</td>\n",
+ " <td>1.794561</td>\n",
+ " <td>two</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-04</th>\n",
+ " <td>0.378008</td>\n",
+ " <td>-0.550517</td>\n",
+ " <td>1.700241</td>\n",
+ " <td>0.859853</td>\n",
+ " <td>three</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-05</th>\n",
+ " <td>-0.353283</td>\n",
+ " <td>2.524044</td>\n",
+ " <td>-0.736119</td>\n",
+ " <td>-0.322952</td>\n",
+ " <td>four</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-06</th>\n",
+ " <td>0.684587</td>\n",
+ " <td>-0.493980</td>\n",
+ " <td>0.172290</td>\n",
+ " <td>-0.113129</td>\n",
+ " <td>three</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " A B D C E\n",
+ "2017-09-01 -0.192859 0.329142 1.056127 0.901094 one\n",
+ "2017-09-02 -0.521965 -0.776431 -0.051510 0.879938 one\n",
+ "2017-09-03 0.826019 -0.445444 2.149620 1.794561 two\n",
+ "2017-09-04 0.378008 -0.550517 1.700241 0.859853 three\n",
+ "2017-09-05 -0.353283 2.524044 -0.736119 -0.322952 four\n",
+ "2017-09-06 0.684587 -0.493980 0.172290 -0.113129 three"
+ ]
+ },
+ "execution_count": 507,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Create new copy and add extra column\n",
+ "df3 = df.copy()\n",
+ "df3['E'] = ['one', 'one','two','three','four','three']\n",
+ "df3"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 508,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>A</th>\n",
+ " <th>B</th>\n",
+ " <th>D</th>\n",
+ " <th>C</th>\n",
+ " <th>E</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>2017-09-03</th>\n",
+ " <td>0.826019</td>\n",
+ " <td>-0.445444</td>\n",
+ " <td>2.149620</td>\n",
+ " <td>1.794561</td>\n",
+ " <td>two</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-05</th>\n",
+ " <td>-0.353283</td>\n",
+ " <td>2.524044</td>\n",
+ " <td>-0.736119</td>\n",
+ " <td>-0.322952</td>\n",
+ " <td>four</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " A B D C E\n",
+ "2017-09-03 0.826019 -0.445444 2.149620 1.794561 two\n",
+ "2017-09-05 -0.353283 2.524044 -0.736119 -0.322952 four"
+ ]
+ },
+ "execution_count": 508,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Use isin() filtering\n",
+ "df3[df3['E'].isin(['two','four'])]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Modifying data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 509,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "2017-09-02 1\n",
+ "2017-09-03 2\n",
+ "2017-09-04 3\n",
+ "2017-09-05 4\n",
+ "2017-09-06 5\n",
+ "2017-09-07 6\n",
+ "Freq: D, dtype: int64"
+ ]
+ },
+ "execution_count": 509,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "s1 = pd.Series([1,2,3,4,5,6], index=pd.date_range('20170902', periods=6))\n",
+ "\n",
+ "s1"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 510,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>A</th>\n",
+ " <th>B</th>\n",
+ " <th>D</th>\n",
+ " <th>C</th>\n",
+ " <th>F</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>2017-09-01</th>\n",
+ " <td>-0.192859</td>\n",
+ " <td>0.329142</td>\n",
+ " <td>1.056127</td>\n",
+ " <td>0.901094</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-02</th>\n",
+ " <td>-0.521965</td>\n",
+ " <td>-0.776431</td>\n",
+ " <td>-0.051510</td>\n",
+ " <td>0.879938</td>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-03</th>\n",
+ " <td>0.826019</td>\n",
+ " <td>-0.445444</td>\n",
+ " <td>2.149620</td>\n",
+ " <td>1.794561</td>\n",
+ " <td>2.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-04</th>\n",
+ " <td>0.378008</td>\n",
+ " <td>-0.550517</td>\n",
+ " <td>1.700241</td>\n",
+ " <td>0.859853</td>\n",
+ " <td>3.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-05</th>\n",
+ " <td>-0.353283</td>\n",
+ " <td>2.524044</td>\n",
+ " <td>-0.736119</td>\n",
+ " <td>-0.322952</td>\n",
+ " <td>4.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-06</th>\n",
+ " <td>0.684587</td>\n",
+ " <td>-0.493980</td>\n",
+ " <td>0.172290</td>\n",
+ " <td>-0.113129</td>\n",
+ " <td>5.0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " A B D C F\n",
+ "2017-09-01 -0.192859 0.329142 1.056127 0.901094 NaN\n",
+ "2017-09-02 -0.521965 -0.776431 -0.051510 0.879938 1.0\n",
+ "2017-09-03 0.826019 -0.445444 2.149620 1.794561 2.0\n",
+ "2017-09-04 0.378008 -0.550517 1.700241 0.859853 3.0\n",
+ "2017-09-05 -0.353283 2.524044 -0.736119 -0.322952 4.0\n",
+ "2017-09-06 0.684587 -0.493980 0.172290 -0.113129 5.0"
+ ]
+ },
+ "execution_count": 510,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Add column F, align by original index\n",
+ "df['F'] = s1\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 511,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>A</th>\n",
+ " <th>B</th>\n",
+ " <th>D</th>\n",
+ " <th>C</th>\n",
+ " <th>F</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>2017-09-01</th>\n",
+ " <td>-0.192859</td>\n",
+ " <td>0.329142</td>\n",
+ " <td>1.056127</td>\n",
+ " <td>0.901094</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-02</th>\n",
+ " <td>0.000000</td>\n",
+ " <td>-0.776431</td>\n",
+ " <td>-0.051510</td>\n",
+ " <td>0.879938</td>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-03</th>\n",
+ " <td>0.826019</td>\n",
+ " <td>-0.445444</td>\n",
+ " <td>2.149620</td>\n",
+ " <td>1.794561</td>\n",
+ " <td>2.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-04</th>\n",
+ " <td>0.378008</td>\n",
+ " <td>-0.550517</td>\n",
+ " <td>1.700241</td>\n",
+ " <td>0.859853</td>\n",
+ " <td>3.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-05</th>\n",
+ " <td>-0.353283</td>\n",
+ " <td>2.524044</td>\n",
+ " <td>-0.736119</td>\n",
+ " <td>-0.322952</td>\n",
+ " <td>4.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-06</th>\n",
+ " <td>0.684587</td>\n",
+ " <td>-0.493980</td>\n",
+ " <td>0.172290</td>\n",
+ " <td>-0.113129</td>\n",
+ " <td>5.0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " A B D C F\n",
+ "2017-09-01 -0.192859 0.329142 1.056127 0.901094 NaN\n",
+ "2017-09-02 0.000000 -0.776431 -0.051510 0.879938 1.0\n",
+ "2017-09-03 0.826019 -0.445444 2.149620 1.794561 2.0\n",
+ "2017-09-04 0.378008 -0.550517 1.700241 0.859853 3.0\n",
+ "2017-09-05 -0.353283 2.524044 -0.736119 -0.322952 4.0\n",
+ "2017-09-06 0.684587 -0.493980 0.172290 -0.113129 5.0"
+ ]
+ },
+ "execution_count": 511,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Setting values by label\n",
+ "df.at['20170902','A'] = 0\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 512,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>A</th>\n",
+ " <th>B</th>\n",
+ " <th>D</th>\n",
+ " <th>C</th>\n",
+ " <th>F</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>2017-09-01</th>\n",
+ " <td>-0.192859</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>1.056127</td>\n",
+ " <td>0.901094</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-02</th>\n",
+ " <td>0.000000</td>\n",
+ " <td>-0.776431</td>\n",
+ " <td>-0.051510</td>\n",
+ " <td>0.879938</td>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-03</th>\n",
+ " <td>0.826019</td>\n",
+ " <td>-0.445444</td>\n",
+ " <td>2.149620</td>\n",
+ " <td>1.794561</td>\n",
+ " <td>2.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-04</th>\n",
+ " <td>0.378008</td>\n",
+ " <td>-0.550517</td>\n",
+ " <td>1.700241</td>\n",
+ " <td>0.859853</td>\n",
+ " <td>3.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-05</th>\n",
+ " <td>-0.353283</td>\n",
+ " <td>2.524044</td>\n",
+ " <td>-0.736119</td>\n",
+ " <td>-0.322952</td>\n",
+ " <td>4.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-06</th>\n",
+ " <td>0.684587</td>\n",
+ " <td>-0.493980</td>\n",
+ " <td>0.172290</td>\n",
+ " <td>-0.113129</td>\n",
+ " <td>5.0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " A B D C F\n",
+ "2017-09-01 -0.192859 0.000000 1.056127 0.901094 NaN\n",
+ "2017-09-02 0.000000 -0.776431 -0.051510 0.879938 1.0\n",
+ "2017-09-03 0.826019 -0.445444 2.149620 1.794561 2.0\n",
+ "2017-09-04 0.378008 -0.550517 1.700241 0.859853 3.0\n",
+ "2017-09-05 -0.353283 2.524044 -0.736119 -0.322952 4.0\n",
+ "2017-09-06 0.684587 -0.493980 0.172290 -0.113129 5.0"
+ ]
+ },
+ "execution_count": 512,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df.iat[0,1] = 0\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 513,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>A</th>\n",
+ " <th>B</th>\n",
+ " <th>D</th>\n",
+ " <th>C</th>\n",
+ " <th>F</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>2017-09-01</th>\n",
+ " <td>-0.192859</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>5</td>\n",
+ " <td>0.901094</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-02</th>\n",
+ " <td>0.000000</td>\n",
+ " <td>-0.776431</td>\n",
+ " <td>5</td>\n",
+ " <td>0.879938</td>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-03</th>\n",
+ " <td>0.826019</td>\n",
+ " <td>-0.445444</td>\n",
+ " <td>5</td>\n",
+ " <td>1.794561</td>\n",
+ " <td>2.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-04</th>\n",
+ " <td>0.378008</td>\n",
+ " <td>-0.550517</td>\n",
+ " <td>5</td>\n",
+ " <td>0.859853</td>\n",
+ " <td>3.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-05</th>\n",
+ " <td>-0.353283</td>\n",
+ " <td>2.524044</td>\n",
+ " <td>5</td>\n",
+ " <td>-0.322952</td>\n",
+ " <td>4.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-06</th>\n",
+ " <td>0.684587</td>\n",
+ " <td>-0.493980</td>\n",
+ " <td>5</td>\n",
+ " <td>-0.113129</td>\n",
+ " <td>5.0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " A B D C F\n",
+ "2017-09-01 -0.192859 0.000000 5 0.901094 NaN\n",
+ "2017-09-02 0.000000 -0.776431 5 0.879938 1.0\n",
+ "2017-09-03 0.826019 -0.445444 5 1.794561 2.0\n",
+ "2017-09-04 0.378008 -0.550517 5 0.859853 3.0\n",
+ "2017-09-05 -0.353283 2.524044 5 -0.322952 4.0\n",
+ "2017-09-06 0.684587 -0.493980 5 -0.113129 5.0"
+ ]
+ },
+ "execution_count": 513,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Setting a column based on a numpy array\n",
+ "df.loc[:,'D'] = np.array([5] * len(df))\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Setting with where()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 514,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>A</th>\n",
+ " <th>B</th>\n",
+ " <th>D</th>\n",
+ " <th>C</th>\n",
+ " <th>F</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>2017-09-01</th>\n",
+ " <td>-0.192859</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>-5</td>\n",
+ " <td>-0.901094</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-02</th>\n",
+ " <td>0.000000</td>\n",
+ " <td>-0.776431</td>\n",
+ " <td>-5</td>\n",
+ " <td>-0.879938</td>\n",
+ " <td>-1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-03</th>\n",
+ " <td>-0.826019</td>\n",
+ " <td>-0.445444</td>\n",
+ " <td>-5</td>\n",
+ " <td>-1.794561</td>\n",
+ " <td>-2.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-04</th>\n",
+ " <td>-0.378008</td>\n",
+ " <td>-0.550517</td>\n",
+ " <td>-5</td>\n",
+ " <td>-0.859853</td>\n",
+ " <td>-3.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-05</th>\n",
+ " <td>-0.353283</td>\n",
+ " <td>-2.524044</td>\n",
+ " <td>-5</td>\n",
+ " <td>-0.322952</td>\n",
+ " <td>-4.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-06</th>\n",
+ " <td>-0.684587</td>\n",
+ " <td>-0.493980</td>\n",
+ " <td>-5</td>\n",
+ " <td>-0.113129</td>\n",
+ " <td>-5.0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " A B D C F\n",
+ "2017-09-01 -0.192859 0.000000 -5 -0.901094 NaN\n",
+ "2017-09-02 0.000000 -0.776431 -5 -0.879938 -1.0\n",
+ "2017-09-03 -0.826019 -0.445444 -5 -1.794561 -2.0\n",
+ "2017-09-04 -0.378008 -0.550517 -5 -0.859853 -3.0\n",
+ "2017-09-05 -0.353283 -2.524044 -5 -0.322952 -4.0\n",
+ "2017-09-06 -0.684587 -0.493980 -5 -0.113129 -5.0"
+ ]
+ },
+ "execution_count": 514,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df2 = df.copy()\n",
+ "df2[df2 > 0] = -df2\n",
+ "df2"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Missing data\n",
+ "\n",
+ "- pandas uses the value np.nan to represent missing data\n",
+ "- It is by default not included in computations. "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 515,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>A</th>\n",
+ " <th>B</th>\n",
+ " <th>D</th>\n",
+ " <th>C</th>\n",
+ " <th>F</th>\n",
+ " <th>E</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>2017-09-01</th>\n",
+ " <td>-0.192859</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>5</td>\n",
+ " <td>0.901094</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-02</th>\n",
+ " <td>0.000000</td>\n",
+ " <td>-0.776431</td>\n",
+ " <td>5</td>\n",
+ " <td>0.879938</td>\n",
+ " <td>1.0</td>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-03</th>\n",
+ " <td>0.826019</td>\n",
+ " <td>-0.445444</td>\n",
+ " <td>5</td>\n",
+ " <td>1.794561</td>\n",
+ " <td>2.0</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-04</th>\n",
+ " <td>0.378008</td>\n",
+ " <td>-0.550517</td>\n",
+ " <td>5</td>\n",
+ " <td>0.859853</td>\n",
+ " <td>3.0</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " A B D C F E\n",
+ "2017-09-01 -0.192859 0.000000 5 0.901094 NaN 1.0\n",
+ "2017-09-02 0.000000 -0.776431 5 0.879938 1.0 1.0\n",
+ "2017-09-03 0.826019 -0.445444 5 1.794561 2.0 NaN\n",
+ "2017-09-04 0.378008 -0.550517 5 0.859853 3.0 NaN"
+ ]
+ },
+ "execution_count": 515,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# reindex (copy) a subset of the data and add an empty column E\n",
+ "df1 = df.reindex(index=dates[0:4], columns=list(df.columns) + ['E'])\n",
+ "# Set E to 1 for first two rows\n",
+ "df1.loc[dates[0]:dates[1],'E'] = 1\n",
+ "df1"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 516,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>A</th>\n",
+ " <th>B</th>\n",
+ " <th>D</th>\n",
+ " <th>C</th>\n",
+ " <th>F</th>\n",
+ " <th>E</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>2017-09-02</th>\n",
+ " <td>0.0</td>\n",
+ " <td>-0.776431</td>\n",
+ " <td>5</td>\n",
+ " <td>0.879938</td>\n",
+ " <td>1.0</td>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " A B D C F E\n",
+ "2017-09-02 0.0 -0.776431 5 0.879938 1.0 1.0"
+ ]
+ },
+ "execution_count": 516,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Drop all rows that have any unknown values\n",
+ "df1.dropna(how='any')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 517,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>A</th>\n",
+ " <th>B</th>\n",
+ " <th>D</th>\n",
+ " <th>C</th>\n",
+ " <th>F</th>\n",
+ " <th>E</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>2017-09-01</th>\n",
+ " <td>-0.192859</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>5</td>\n",
+ " <td>0.901094</td>\n",
+ " <td>42.0</td>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-02</th>\n",
+ " <td>0.000000</td>\n",
+ " <td>-0.776431</td>\n",
+ " <td>5</td>\n",
+ " <td>0.879938</td>\n",
+ " <td>1.0</td>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-03</th>\n",
+ " <td>0.826019</td>\n",
+ " <td>-0.445444</td>\n",
+ " <td>5</td>\n",
+ " <td>1.794561</td>\n",
+ " <td>2.0</td>\n",
+ " <td>42.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-04</th>\n",
+ " <td>0.378008</td>\n",
+ " <td>-0.550517</td>\n",
+ " <td>5</td>\n",
+ " <td>0.859853</td>\n",
+ " <td>3.0</td>\n",
+ " <td>42.0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " A B D C F E\n",
+ "2017-09-01 -0.192859 0.000000 5 0.901094 42.0 1.0\n",
+ "2017-09-02 0.000000 -0.776431 5 0.879938 1.0 1.0\n",
+ "2017-09-03 0.826019 -0.445444 5 1.794561 2.0 42.0\n",
+ "2017-09-04 0.378008 -0.550517 5 0.859853 3.0 42.0"
+ ]
+ },
+ "execution_count": 517,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Replace NA with value\n",
+ "df1.fillna(value=42)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 518,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>A</th>\n",
+ " <th>B</th>\n",
+ " <th>D</th>\n",
+ " <th>C</th>\n",
+ " <th>F</th>\n",
+ " <th>E</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>2017-09-01</th>\n",
+ " <td>False</td>\n",
+ " <td>False</td>\n",
+ " <td>False</td>\n",
+ " <td>False</td>\n",
+ " <td>True</td>\n",
+ " <td>False</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-02</th>\n",
+ " <td>False</td>\n",
+ " <td>False</td>\n",
+ " <td>False</td>\n",
+ " <td>False</td>\n",
+ " <td>False</td>\n",
+ " <td>False</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-03</th>\n",
+ " <td>False</td>\n",
+ " <td>False</td>\n",
+ " <td>False</td>\n",
+ " <td>False</td>\n",
+ " <td>False</td>\n",
+ " <td>True</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-04</th>\n",
+ " <td>False</td>\n",
+ " <td>False</td>\n",
+ " <td>False</td>\n",
+ " <td>False</td>\n",
+ " <td>False</td>\n",
+ " <td>True</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " A B D C F E\n",
+ "2017-09-01 False False False False True False\n",
+ "2017-09-02 False False False False False False\n",
+ "2017-09-03 False False False False False True\n",
+ "2017-09-04 False False False False False True"
+ ]
+ },
+ "execution_count": 518,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Show the boolean mask\n",
+ "pd.isnull(df1)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Operations"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Basic (stat) operators"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 519,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "A 0.223745\n",
+ "B 0.042945\n",
+ "D 5.000000\n",
+ "C 0.666561\n",
+ "F 3.000000\n",
+ "dtype: float64"
+ ]
+ },
+ "execution_count": 519,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Mean per column\n",
+ "df.mean() # similar to axis=0"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 520,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "2017-09-01 1.427059\n",
+ "2017-09-02 1.220702\n",
+ "2017-09-03 1.835027\n",
+ "2017-09-04 1.737469\n",
+ "2017-09-05 2.169562\n",
+ "2017-09-06 2.015496\n",
+ "Freq: D, dtype: float64"
+ ]
+ },
+ "execution_count": 520,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Mean per row\n",
+ "df.mean(axis=1)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Apply"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 521,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>A</th>\n",
+ " <th>B</th>\n",
+ " <th>D</th>\n",
+ " <th>C</th>\n",
+ " <th>F</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>2017-09-01</th>\n",
+ " <td>0.192859</td>\n",
+ " <td>-0.000000</td>\n",
+ " <td>-5</td>\n",
+ " <td>-0.901094</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-02</th>\n",
+ " <td>-0.000000</td>\n",
+ " <td>0.776431</td>\n",
+ " <td>-5</td>\n",
+ " <td>-0.879938</td>\n",
+ " <td>-1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-03</th>\n",
+ " <td>-0.826019</td>\n",
+ " <td>0.445444</td>\n",
+ " <td>-5</td>\n",
+ " <td>-1.794561</td>\n",
+ " <td>-2.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-04</th>\n",
+ " <td>-0.378008</td>\n",
+ " <td>0.550517</td>\n",
+ " <td>-5</td>\n",
+ " <td>-0.859853</td>\n",
+ " <td>-3.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-05</th>\n",
+ " <td>0.353283</td>\n",
+ " <td>-2.524044</td>\n",
+ " <td>-5</td>\n",
+ " <td>0.322952</td>\n",
+ " <td>-4.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2017-09-06</th>\n",
+ " <td>-0.684587</td>\n",
+ " <td>0.493980</td>\n",
+ " <td>-5</td>\n",
+ " <td>0.113129</td>\n",
+ " <td>-5.0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " A B D C F\n",
+ "2017-09-01 0.192859 -0.000000 -5 -0.901094 NaN\n",
+ "2017-09-02 -0.000000 0.776431 -5 -0.879938 -1.0\n",
+ "2017-09-03 -0.826019 0.445444 -5 -1.794561 -2.0\n",
+ "2017-09-04 -0.378008 0.550517 -5 -0.859853 -3.0\n",
+ "2017-09-05 0.353283 -2.524044 -5 0.322952 -4.0\n",
+ "2017-09-06 -0.684587 0.493980 -5 0.113129 -5.0"
+ ]
+ },
+ "execution_count": 521,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Create my own function that returns the negated value\n",
+ "def my_func(val):\n",
+ " return -val\n",
+ "# Apply my function to all values\n",
+ "df.apply(my_func)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Histogramming"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 522,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "0 2\n",
+ "1 1\n",
+ "2 2\n",
+ "3 2\n",
+ "4 5\n",
+ "5 5\n",
+ "6 1\n",
+ "7 1\n",
+ "8 2\n",
+ "9 3\n",
+ "dtype: int64"
+ ]
+ },
+ "execution_count": 522,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "s = pd.Series(np.random.randint(0, 7, size=10))\n",
+ "s"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 523,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "2 4\n",
+ "1 3\n",
+ "5 2\n",
+ "3 1\n",
+ "dtype: int64"
+ ]
+ },
+ "execution_count": 523,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "s.value_counts()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Concatinating data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 524,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>0</th>\n",
+ " <th>1</th>\n",
+ " <th>2</th>\n",
+ " <th>3</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>-0.330694</td>\n",
+ " <td>0.872756</td>\n",
+ " <td>2.112683</td>\n",
+ " <td>-1.388585</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>0.057223</td>\n",
+ " <td>0.618802</td>\n",
+ " <td>-0.914080</td>\n",
+ " <td>0.252215</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>-1.139711</td>\n",
+ " <td>0.816206</td>\n",
+ " <td>1.008724</td>\n",
+ " <td>-1.672792</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>0.072709</td>\n",
+ " <td>0.074521</td>\n",
+ " <td>-0.089053</td>\n",
+ " <td>-0.132791</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>0.502954</td>\n",
+ " <td>1.068275</td>\n",
+ " <td>0.415517</td>\n",
+ " <td>1.218068</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>-1.710858</td>\n",
+ " <td>-0.176961</td>\n",
+ " <td>1.161903</td>\n",
+ " <td>-1.412063</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6</th>\n",
+ " <td>0.876638</td>\n",
+ " <td>-0.302195</td>\n",
+ " <td>-1.360723</td>\n",
+ " <td>-2.326562</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7</th>\n",
+ " <td>-0.888707</td>\n",
+ " <td>-0.609472</td>\n",
+ " <td>-0.241537</td>\n",
+ " <td>-1.974217</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8</th>\n",
+ " <td>-0.301339</td>\n",
+ " <td>-0.329511</td>\n",
+ " <td>-0.040340</td>\n",
+ " <td>0.168655</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9</th>\n",
+ " <td>-0.432671</td>\n",
+ " <td>-0.518209</td>\n",
+ " <td>1.575212</td>\n",
+ " <td>-0.901535</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " 0 1 2 3\n",
+ "0 -0.330694 0.872756 2.112683 -1.388585\n",
+ "1 0.057223 0.618802 -0.914080 0.252215\n",
+ "2 -1.139711 0.816206 1.008724 -1.672792\n",
+ "3 0.072709 0.074521 -0.089053 -0.132791\n",
+ "4 0.502954 1.068275 0.415517 1.218068\n",
+ "5 -1.710858 -0.176961 1.161903 -1.412063\n",
+ "6 0.876638 -0.302195 -1.360723 -2.326562\n",
+ "7 -0.888707 -0.609472 -0.241537 -1.974217\n",
+ "8 -0.301339 -0.329511 -0.040340 0.168655\n",
+ "9 -0.432671 -0.518209 1.575212 -0.901535"
+ ]
+ },
+ "execution_count": 524,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df = pd.DataFrame(np.random.randn(10, 4))\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 525,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[ 0 1 2 3\n",
+ " 0 -0.330694 0.872756 2.112683 -1.388585\n",
+ " 1 0.057223 0.618802 -0.914080 0.252215\n",
+ " 2 -1.139711 0.816206 1.008724 -1.672792,\n",
+ " 0 1 2 3\n",
+ " 3 0.072709 0.074521 -0.089053 -0.132791\n",
+ " 4 0.502954 1.068275 0.415517 1.218068\n",
+ " 5 -1.710858 -0.176961 1.161903 -1.412063\n",
+ " 6 0.876638 -0.302195 -1.360723 -2.326562,\n",
+ " 0 1 2 3\n",
+ " 7 -0.888707 -0.609472 -0.241537 -1.974217\n",
+ " 8 -0.301339 -0.329511 -0.040340 0.168655\n",
+ " 9 -0.432671 -0.518209 1.575212 -0.901535]"
+ ]
+ },
+ "execution_count": 525,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "chunks = [df[:3], df[3:7], df[7:]]\n",
+ "chunks"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 526,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>0</th>\n",
+ " <th>1</th>\n",
+ " <th>2</th>\n",
+ " <th>3</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>-0.330694</td>\n",
+ " <td>0.872756</td>\n",
+ " <td>2.112683</td>\n",
+ " <td>-1.388585</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>0.057223</td>\n",
+ " <td>0.618802</td>\n",
+ " <td>-0.914080</td>\n",
+ " <td>0.252215</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>-1.139711</td>\n",
+ " <td>0.816206</td>\n",
+ " <td>1.008724</td>\n",
+ " <td>-1.672792</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>0.072709</td>\n",
+ " <td>0.074521</td>\n",
+ " <td>-0.089053</td>\n",
+ " <td>-0.132791</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>0.502954</td>\n",
+ " <td>1.068275</td>\n",
+ " <td>0.415517</td>\n",
+ " <td>1.218068</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>-1.710858</td>\n",
+ " <td>-0.176961</td>\n",
+ " <td>1.161903</td>\n",
+ " <td>-1.412063</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6</th>\n",
+ " <td>0.876638</td>\n",
+ " <td>-0.302195</td>\n",
+ " <td>-1.360723</td>\n",
+ " <td>-2.326562</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7</th>\n",
+ " <td>-0.888707</td>\n",
+ " <td>-0.609472</td>\n",
+ " <td>-0.241537</td>\n",
+ " <td>-1.974217</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8</th>\n",
+ " <td>-0.301339</td>\n",
+ " <td>-0.329511</td>\n",
+ " <td>-0.040340</td>\n",
+ " <td>0.168655</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9</th>\n",
+ " <td>-0.432671</td>\n",
+ " <td>-0.518209</td>\n",
+ " <td>1.575212</td>\n",
+ " <td>-0.901535</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " 0 1 2 3\n",
+ "0 -0.330694 0.872756 2.112683 -1.388585\n",
+ "1 0.057223 0.618802 -0.914080 0.252215\n",
+ "2 -1.139711 0.816206 1.008724 -1.672792\n",
+ "3 0.072709 0.074521 -0.089053 -0.132791\n",
+ "4 0.502954 1.068275 0.415517 1.218068\n",
+ "5 -1.710858 -0.176961 1.161903 -1.412063\n",
+ "6 0.876638 -0.302195 -1.360723 -2.326562\n",
+ "7 -0.888707 -0.609472 -0.241537 -1.974217\n",
+ "8 -0.301339 -0.329511 -0.040340 0.168655\n",
+ "9 -0.432671 -0.518209 1.575212 -0.901535"
+ ]
+ },
+ "execution_count": 526,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pd.concat(chunks)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Joining data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 527,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "left = pd.DataFrame({'key': ['foo', 'foo'], 'lval': [1, 2]})\n",
+ "right = pd.DataFrame({'key': ['foo', 'foo'], 'rval': [4, 5]})"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 528,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>key</th>\n",
+ " <th>lval</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>foo</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>foo</td>\n",
+ " <td>2</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " key lval\n",
+ "0 foo 1\n",
+ "1 foo 2"
+ ]
+ },
+ "execution_count": 528,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "left"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 529,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>key</th>\n",
+ " <th>rval</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>foo</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>foo</td>\n",
+ " <td>5</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " key rval\n",
+ "0 foo 4\n",
+ "1 foo 5"
+ ]
+ },
+ "execution_count": 529,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "right"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 530,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>key</th>\n",
+ " <th>lval</th>\n",
+ " <th>rval</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>foo</td>\n",
+ " <td>1</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>foo</td>\n",
+ " <td>1</td>\n",
+ " <td>5</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>foo</td>\n",
+ " <td>2</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>foo</td>\n",
+ " <td>2</td>\n",
+ " <td>5</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " key lval rval\n",
+ "0 foo 1 4\n",
+ "1 foo 1 5\n",
+ "2 foo 2 4\n",
+ "3 foo 2 5"
+ ]
+ },
+ "execution_count": 530,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pd.merge(left, right, on='key')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 531,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "left = pd.DataFrame({'key': ['foo', 'bar'], 'lval': [1, 2]})\n",
+ "right = pd.DataFrame({'key': ['foo', 'bar'], 'rval': [4, 5]})"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 532,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>key</th>\n",
+ " <th>lval</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>foo</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>bar</td>\n",
+ " <td>2</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " key lval\n",
+ "0 foo 1\n",
+ "1 bar 2"
+ ]
+ },
+ "execution_count": 532,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "left"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 533,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>key</th>\n",
+ " <th>rval</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>foo</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>bar</td>\n",
+ " <td>5</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " key rval\n",
+ "0 foo 4\n",
+ "1 bar 5"
+ ]
+ },
+ "execution_count": 533,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "right"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 534,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>key</th>\n",
+ " <th>lval</th>\n",
+ " <th>rval</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>foo</td>\n",
+ " <td>1</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>bar</td>\n",
+ " <td>2</td>\n",
+ " <td>5</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " key lval rval\n",
+ "0 foo 1 4\n",
+ "1 bar 2 5"
+ ]
+ },
+ "execution_count": 534,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "pd.merge(left, right, on='key')"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Appending rows"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 535,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>A</th>\n",
+ " <th>B</th>\n",
+ " <th>C</th>\n",
+ " <th>D</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>1.460591</td>\n",
+ " <td>-1.167721</td>\n",
+ " <td>-0.838375</td>\n",
+ " <td>-1.239544</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>1.670965</td>\n",
+ " <td>2.563498</td>\n",
+ " <td>-0.103847</td>\n",
+ " <td>-1.104923</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>-1.515473</td>\n",
+ " <td>0.327335</td>\n",
+ " <td>0.329841</td>\n",
+ " <td>-1.149319</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>0.421181</td>\n",
+ " <td>1.607888</td>\n",
+ " <td>-0.011656</td>\n",
+ " <td>-0.166280</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>1.967833</td>\n",
+ " <td>0.506429</td>\n",
+ " <td>1.675263</td>\n",
+ " <td>0.763151</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>-1.781919</td>\n",
+ " <td>-1.503685</td>\n",
+ " <td>0.366258</td>\n",
+ " <td>-1.276055</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6</th>\n",
+ " <td>-0.222054</td>\n",
+ " <td>1.231713</td>\n",
+ " <td>-0.358001</td>\n",
+ " <td>-0.407226</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7</th>\n",
+ " <td>0.717591</td>\n",
+ " <td>-0.060166</td>\n",
+ " <td>0.008006</td>\n",
+ " <td>-0.513181</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " A B C D\n",
+ "0 1.460591 -1.167721 -0.838375 -1.239544\n",
+ "1 1.670965 2.563498 -0.103847 -1.104923\n",
+ "2 -1.515473 0.327335 0.329841 -1.149319\n",
+ "3 0.421181 1.607888 -0.011656 -0.166280\n",
+ "4 1.967833 0.506429 1.675263 0.763151\n",
+ "5 -1.781919 -1.503685 0.366258 -1.276055\n",
+ "6 -0.222054 1.231713 -0.358001 -0.407226\n",
+ "7 0.717591 -0.060166 0.008006 -0.513181"
+ ]
+ },
+ "execution_count": 535,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df = pd.DataFrame(np.random.randn(8, 4), columns=['A','B','C','D'])\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 536,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "A 0.421181\n",
+ "B 1.607888\n",
+ "C -0.011656\n",
+ "D -0.166280\n",
+ "Name: 3, dtype: float64"
+ ]
+ },
+ "execution_count": 536,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "s = df.iloc[3]\n",
+ "s"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 537,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>A</th>\n",
+ " <th>B</th>\n",
+ " <th>C</th>\n",
+ " <th>D</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>1.460591</td>\n",
+ " <td>-1.167721</td>\n",
+ " <td>-0.838375</td>\n",
+ " <td>-1.239544</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>1.670965</td>\n",
+ " <td>2.563498</td>\n",
+ " <td>-0.103847</td>\n",
+ " <td>-1.104923</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>-1.515473</td>\n",
+ " <td>0.327335</td>\n",
+ " <td>0.329841</td>\n",
+ " <td>-1.149319</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>0.421181</td>\n",
+ " <td>1.607888</td>\n",
+ " <td>-0.011656</td>\n",
+ " <td>-0.166280</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>1.967833</td>\n",
+ " <td>0.506429</td>\n",
+ " <td>1.675263</td>\n",
+ " <td>0.763151</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>-1.781919</td>\n",
+ " <td>-1.503685</td>\n",
+ " <td>0.366258</td>\n",
+ " <td>-1.276055</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6</th>\n",
+ " <td>-0.222054</td>\n",
+ " <td>1.231713</td>\n",
+ " <td>-0.358001</td>\n",
+ " <td>-0.407226</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7</th>\n",
+ " <td>0.717591</td>\n",
+ " <td>-0.060166</td>\n",
+ " <td>0.008006</td>\n",
+ " <td>-0.513181</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>0.421181</td>\n",
+ " <td>1.607888</td>\n",
+ " <td>-0.011656</td>\n",
+ " <td>-0.166280</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " A B C D\n",
+ "0 1.460591 -1.167721 -0.838375 -1.239544\n",
+ "1 1.670965 2.563498 -0.103847 -1.104923\n",
+ "2 -1.515473 0.327335 0.329841 -1.149319\n",
+ "3 0.421181 1.607888 -0.011656 -0.166280\n",
+ "4 1.967833 0.506429 1.675263 0.763151\n",
+ "5 -1.781919 -1.503685 0.366258 -1.276055\n",
+ "6 -0.222054 1.231713 -0.358001 -0.407226\n",
+ "7 0.717591 -0.060166 0.008006 -0.513181\n",
+ "3 0.421181 1.607888 -0.011656 -0.166280"
+ ]
+ },
+ "execution_count": 537,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df.append(s, ignore_index=False).reindex()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Grouping"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 538,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>A</th>\n",
+ " <th>B</th>\n",
+ " <th>C</th>\n",
+ " <th>D</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>foo</td>\n",
+ " <td>one</td>\n",
+ " <td>0.776501</td>\n",
+ " <td>1.452913</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>bar</td>\n",
+ " <td>one</td>\n",
+ " <td>-0.731479</td>\n",
+ " <td>-0.924116</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>foo</td>\n",
+ " <td>two</td>\n",
+ " <td>-0.204101</td>\n",
+ " <td>0.044840</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>bar</td>\n",
+ " <td>three</td>\n",
+ " <td>-0.343739</td>\n",
+ " <td>-0.683006</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>foo</td>\n",
+ " <td>two</td>\n",
+ " <td>-1.519019</td>\n",
+ " <td>0.103475</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>bar</td>\n",
+ " <td>two</td>\n",
+ " <td>1.271579</td>\n",
+ " <td>-2.176090</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6</th>\n",
+ " <td>foo</td>\n",
+ " <td>one</td>\n",
+ " <td>-0.741659</td>\n",
+ " <td>-0.561117</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7</th>\n",
+ " <td>foo</td>\n",
+ " <td>three</td>\n",
+ " <td>-0.174572</td>\n",
+ " <td>1.281778</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " A B C D\n",
+ "0 foo one 0.776501 1.452913\n",
+ "1 bar one -0.731479 -0.924116\n",
+ "2 foo two -0.204101 0.044840\n",
+ "3 bar three -0.343739 -0.683006\n",
+ "4 foo two -1.519019 0.103475\n",
+ "5 bar two 1.271579 -2.176090\n",
+ "6 foo one -0.741659 -0.561117\n",
+ "7 foo three -0.174572 1.281778"
+ ]
+ },
+ "execution_count": 538,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Create \n",
+ "df = pd.DataFrame({'A' : ['foo', 'bar', 'foo', 'bar',\n",
+ " 'foo', 'bar', 'foo', 'foo'],\n",
+ " 'B' : ['one', 'one', 'two', 'three',\n",
+ " 'two', 'two', 'one', 'three'],\n",
+ " 'C' : np.random.randn(8),\n",
+ " 'D' : np.random.randn(8)})\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 539,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>C</th>\n",
+ " <th>D</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>A</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>bar</th>\n",
+ " <td>0.196361</td>\n",
+ " <td>-3.783212</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>foo</th>\n",
+ " <td>-1.862851</td>\n",
+ " <td>2.321889</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " C D\n",
+ "A \n",
+ "bar 0.196361 -3.783212\n",
+ "foo -1.862851 2.321889"
+ ]
+ },
+ "execution_count": 539,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df.groupby('A').sum()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 540,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th>C</th>\n",
+ " <th>D</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>A</th>\n",
+ " <th>B</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th rowspan=\"3\" valign=\"top\">bar</th>\n",
+ " <th>one</th>\n",
+ " <td>-0.731479</td>\n",
+ " <td>-0.924116</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>three</th>\n",
+ " <td>-0.343739</td>\n",
+ " <td>-0.683006</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>two</th>\n",
+ " <td>1.271579</td>\n",
+ " <td>-2.176090</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"3\" valign=\"top\">foo</th>\n",
+ " <th>one</th>\n",
+ " <td>0.034842</td>\n",
+ " <td>0.891796</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>three</th>\n",
+ " <td>-0.174572</td>\n",
+ " <td>1.281778</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>two</th>\n",
+ " <td>-1.723120</td>\n",
+ " <td>0.148315</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " C D\n",
+ "A B \n",
+ "bar one -0.731479 -0.924116\n",
+ " three -0.343739 -0.683006\n",
+ " two 1.271579 -2.176090\n",
+ "foo one 0.034842 0.891796\n",
+ " three -0.174572 1.281778\n",
+ " two -1.723120 0.148315"
+ ]
+ },
+ "execution_count": 540,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df.groupby(['A','B']).sum()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Reshaping using pivot_table"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 541,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>A</th>\n",
+ " <th>B</th>\n",
+ " <th>C</th>\n",
+ " <th>D</th>\n",
+ " <th>E</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>one</td>\n",
+ " <td>X</td>\n",
+ " <td>foo</td>\n",
+ " <td>1.057110</td>\n",
+ " <td>-0.108982</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>one</td>\n",
+ " <td>Y</td>\n",
+ " <td>foo</td>\n",
+ " <td>1.037212</td>\n",
+ " <td>0.477061</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>two</td>\n",
+ " <td>Z</td>\n",
+ " <td>foo</td>\n",
+ " <td>1.375108</td>\n",
+ " <td>0.205573</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>three</td>\n",
+ " <td>X</td>\n",
+ " <td>bar</td>\n",
+ " <td>-0.383392</td>\n",
+ " <td>1.279249</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>one</td>\n",
+ " <td>Y</td>\n",
+ " <td>bar</td>\n",
+ " <td>0.378141</td>\n",
+ " <td>0.166755</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>one</td>\n",
+ " <td>Z</td>\n",
+ " <td>bar</td>\n",
+ " <td>-0.528378</td>\n",
+ " <td>0.405889</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6</th>\n",
+ " <td>two</td>\n",
+ " <td>X</td>\n",
+ " <td>foo</td>\n",
+ " <td>0.406508</td>\n",
+ " <td>0.054299</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7</th>\n",
+ " <td>three</td>\n",
+ " <td>Y</td>\n",
+ " <td>foo</td>\n",
+ " <td>-0.937294</td>\n",
+ " <td>0.251400</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8</th>\n",
+ " <td>one</td>\n",
+ " <td>Z</td>\n",
+ " <td>foo</td>\n",
+ " <td>0.750334</td>\n",
+ " <td>0.880497</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9</th>\n",
+ " <td>one</td>\n",
+ " <td>X</td>\n",
+ " <td>bar</td>\n",
+ " <td>0.827021</td>\n",
+ " <td>-0.148973</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>10</th>\n",
+ " <td>two</td>\n",
+ " <td>Y</td>\n",
+ " <td>bar</td>\n",
+ " <td>-0.143651</td>\n",
+ " <td>-0.729501</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>11</th>\n",
+ " <td>three</td>\n",
+ " <td>Z</td>\n",
+ " <td>bar</td>\n",
+ " <td>-0.205862</td>\n",
+ " <td>1.432239</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " A B C D E\n",
+ "0 one X foo 1.057110 -0.108982\n",
+ "1 one Y foo 1.037212 0.477061\n",
+ "2 two Z foo 1.375108 0.205573\n",
+ "3 three X bar -0.383392 1.279249\n",
+ "4 one Y bar 0.378141 0.166755\n",
+ "5 one Z bar -0.528378 0.405889\n",
+ "6 two X foo 0.406508 0.054299\n",
+ "7 three Y foo -0.937294 0.251400\n",
+ "8 one Z foo 0.750334 0.880497\n",
+ "9 one X bar 0.827021 -0.148973\n",
+ "10 two Y bar -0.143651 -0.729501\n",
+ "11 three Z bar -0.205862 1.432239"
+ ]
+ },
+ "execution_count": 541,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Create a flat table with duplicated entries\n",
+ "df = pd.DataFrame({'A' : ['one', 'one', 'two', 'three'] * 3,\n",
+ " 'B' : ['X', 'Y', 'Z'] * 4,\n",
+ " 'C' : ['foo', 'foo', 'foo', 'bar', 'bar', 'bar'] * 2,\n",
+ " 'D' : np.random.randn(12),\n",
+ " 'E' : np.random.randn(12)})\n",
+ "df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 542,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style>\n",
+ " .dataframe thead tr:only-child th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: left;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>C</th>\n",
+ " <th>bar</th>\n",
+ " <th>foo</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>A</th>\n",
+ " <th>B</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th rowspan=\"3\" valign=\"top\">one</th>\n",
+ " <th>X</th>\n",
+ " <td>0.827021</td>\n",
+ " <td>1.057110</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Y</th>\n",
+ " <td>0.378141</td>\n",
+ " <td>1.037212</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Z</th>\n",
+ " <td>-0.528378</td>\n",
+ " <td>0.750334</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"3\" valign=\"top\">three</th>\n",
+ " <th>X</th>\n",
+ " <td>-0.383392</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Y</th>\n",
+ " <td>NaN</td>\n",
+ " <td>-0.937294</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Z</th>\n",
+ " <td>-0.205862</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"3\" valign=\"top\">two</th>\n",
+ " <th>X</th>\n",
+ " <td>NaN</td>\n",
+ " <td>0.406508</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Y</th>\n",
+ " <td>-0.143651</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Z</th>\n",
+ " <td>NaN</td>\n",
+ " <td>1.375108</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "C bar foo\n",
+ "A B \n",
+ "one X 0.827021 1.057110\n",
+ " Y 0.378141 1.037212\n",
+ " Z -0.528378 0.750334\n",
+ "three X -0.383392 NaN\n",
+ " Y NaN -0.937294\n",
+ " Z -0.205862 NaN\n",
+ "two X NaN 0.406508\n",
+ " Y -0.143651 NaN\n",
+ " Z NaN 1.375108"
+ ]
+ },
+ "execution_count": 542,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "# Create a pivot table using A and B as the index, making C columns, and using D as the values (E is not used)\n",
+ "pd.pivot_table(df, values='D', index=['A', 'B'], columns=['C'])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Further information\n",
+ "- https://pandas.pydata.org/pandas-docs/stable/index.html\n",
+ "- https://stackoverflow.com with pandas tag"
+ ]
+ },
{
"cell_type": "code",
"execution_count": null,
--
GitLab