balkian/sitc
1
0
Fork 0
mirror of https://github.com/gsi-upm/sitc synced 2025-12-15 09:38:16 +00:00
Code Issues Releases Wiki Activity

Remove outputs and metadata

Browse Source
This commit is contained in:
J. Fernando Sánchez
2019-02-28 15:30:33 +01:00
parent a1be167cc0
commit c1d3ca38ea
25 changed files with 989 additions and 14268 deletions
Download Patch File Download Diff File Expand all files Collapse all files

100
ml2/3_5_Exercise_1.ipynb
View File

@@ -46,10 +46,8 @@
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
},
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
@@ -82,9 +80,7 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [],
"source": []
},
@@ -105,9 +101,7 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"metadata": {},
"outputs": [],
"source": []
},
@@ -121,9 +115,7 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"metadata": {},
"outputs": [],
"source": []
},
@@ -137,9 +129,7 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"metadata": {},
"outputs": [],
"source": []
},
@@ -153,17 +143,13 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": true
},
"metadata": {},
"source": [
"How many passsengers have survived? List them grouped by Sex and Pclass.\n",
"\n",
@@ -173,17 +159,13 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": false
},
"metadata": {},
"source": [
"Visualise df_1 as an histogram."
]
@@ -191,17 +173,13 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": true
},
"metadata": {},
"source": [
"# Feature Engineering"
]
@@ -232,9 +210,7 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [],
"source": [
"df['FamilySize'] = df['SibSp'] + df['Parch']\n",
@@ -258,9 +234,7 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [],
"source": [
"df['Alone'] = (df.FamilySize == 0)\n",
@@ -284,9 +258,7 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [],
"source": [
"#Taken from http://www.analyticsvidhya.com/blog/2014/09/data-munging-python-using-pandas-baby-steps-python/\n",
@@ -307,9 +279,7 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [],
"source": [
"df['Salutation'].unique()"
@@ -318,9 +288,7 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [],
"source": [
"df.groupby(['Salutation']).size()"
@@ -336,9 +304,7 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [],
"source": [
"def group_salutation(old_salutation):\n",
@@ -362,9 +328,7 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [],
"source": [
"# Distribution\n",
@@ -375,9 +339,7 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [],
"source": [
"df.boxplot(column='Age', by = 'Salutation', sym='k.')"
@@ -393,9 +355,7 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [],
"source": [
"# Specific features for Children and Female since there are more survivors\n",
@@ -413,9 +373,7 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"metadata": {},
"outputs": [],
"source": [
"# Group ages to simplify machine learning algorithms. 0: 0-5, 1: 6-10, 2: 11-15, 3: 16-59 and 4: 60-80\n",
@@ -437,10 +395,8 @@
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": false
},
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def substrings_in_string(big_string, substrings):\n",
@@ -475,9 +431,7 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"metadata": {},
"outputs": [],
"source": [
"df['FarePerPerson']= df['Fare'] / (df['FamilySize'] + 1)"
@@ -500,9 +454,7 @@
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"metadata": {},
"outputs": [],
"source": [
"df['AgeClass']=df['Age']*df['Pclass']"