balkian/sitc
1
0
Fork 0
mirror of https://github.com/gsi-upm/sitc synced 2025-01-06 19:21:29 +00:00
Code Issues Releases Wiki Activity

Compare commits

base: balkian:bf21e3ceabaad7f1dba55ca6ec550ee5b28a34ce
Branches Tags
balkian:master
balkian:dveni-patch-2
balkian:dveni-patch-1
...
compare: balkian:f0278aea336a6b81159db0f53a5a705e358c5a34
Branches Tags
balkian:master
balkian:dveni-patch-2
balkian:dveni-patch-1

8 Commits
bf21e3ceab ... f0278aea33

Author SHA1 Message Date
cif
f0278aea33 Updated 2022-03-07 14:19:44 +01:00
cif
7bf0fb6479 Updated 2022-03-07 14:17:02 +01:00
cif
4d87b07ed9 Updated visualization 2022-03-07 14:16:14 +01:00
cif
7d71ba5f7a Updated references 2022-03-07 13:03:48 +01:00
cif
1124c9129c Fixed URL 2022-03-07 13:01:21 +01:00
cif
df6449b55f Updated to last version of seaborn 2022-03-07 12:57:17 +01:00
cif
d99eeb733a Updated median with only numeric values 2022-03-07 12:44:14 +01:00
cif
a43fb4c78c Updated references 2022-03-07 12:28:10 +01:00
10 changed files with 212 additions and 444 deletions
Show Stats Expand all files Collapse all files

4
ml2/3_0_0_Intro_ML_2.ipynb
View File

@ -92,7 +92,7 @@
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
@ -106,7 +106,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.1"
"version": "3.8.12"
},
"latex_envs": {
"LaTeX_envs_menu_present": true,

10
ml2/3_2_Pandas.ipynb
View File

@ -433,10 +433,10 @@
"metadata": {},
"source": [
"* [Pandas](http://pandas.pydata.org/)\n",
"* [Learning Pandas, Michael Heydt, Packt Publishing, 2015](http://proquest.safaribooksonline.com/book/programming/python/9781783985128)\n",
"* [Pandas. Introduction to Data Structures](http://pandas.pydata.org/pandas-docs/stable/dsintro.html#dsintro)\n",
"* [Learning Pandas, Michael Heydt, Packt Publishing, 2017](https://learning.oreilly.com/library/view/learning-pandas/9781787123137/)\n",
"* [Pandas. Introduction to Data Structures](https://pandas.pydata.org/pandas-docs/stable/user_guide/dsintro.html)\n",
"* [Introducing Pandas Objects](https://www.oreilly.com/learning/introducing-pandas-objects)\n",
"* [Boolean Operators in Pandas](http://pandas.pydata.org/pandas-docs/stable/indexing.html#boolean-operators)"
"* [Boolean Operators in Pandas](https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#boolean-operators)"
]
},
{
@ -458,7 +458,7 @@
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
@ -472,7 +472,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.1"
"version": "3.8.12"
},
"latex_envs": {
"LaTeX_envs_menu_present": true,

28
ml2/3_3_Data_Munging_with_Pandas.ipynb
View File

@ -404,7 +404,7 @@
"outputs": [],
"source": [
"#Mean Age and SibSp of passengers grouped by passenger class and sex\n",
"df.groupby(['Pclass', 'Sex'])['Age','SibSp'].mean()"
"df.groupby(['Pclass', 'Sex'])[['Age','SibSp']].mean()"
]
},
{
@ -414,7 +414,7 @@
"outputs": [],
"source": [
"#Show mean Age and SibSp for passengers older than 25 grouped by Passenger Class and Sex\n",
"df[df.Age > 25].groupby(['Pclass', 'Sex'])['Age','SibSp'].mean()"
"df[df.Age > 25].groupby(['Pclass', 'Sex'])[['Age','SibSp']].mean()"
]
},
{
@ -424,7 +424,7 @@
"outputs": [],
"source": [
"# Mean age, SibSp , Survived of passengers older than 25 which survived, grouped by Passenger Class and Sex \n",
"df[(df.Age > 25 & (df.Survived == 1))].groupby(['Pclass', 'Sex'])['Age','SibSp','Survived'].mean()"
"df[(df.Age > 25 & (df.Survived == 1))].groupby(['Pclass', 'Sex'])[['Age','SibSp','Survived']].mean()"
]
},
{
@ -436,7 +436,7 @@
"# We can also decide which function apply in each column\n",
"\n",
"#Show mean Age, mean SibSp, and number of passengers older than 25 that survived, grouped by Passenger Class and Sex\n",
"df[(df.Age > 25 & (df.Survived == 1))].groupby(['Pclass', 'Sex'])['Age','SibSp','Survived'].agg({'Age': np.mean, \n",
"df[(df.Age > 25 & (df.Survived == 1))].groupby(['Pclass', 'Sex'])[['Age','SibSp','Survived']].agg({'Age': np.mean, \n",
" 'SibSp': np.mean, 'Survived': np.sum})"
]
},
@ -600,8 +600,8 @@
"metadata": {},
"outputs": [],
"source": [
"# Fill missing values with the median\n",
"df_filled = df.fillna(df.median())\n",
"# Fill missing values with the median, we avoid empty (None) values with numeric_only\n",
"df_filled = df.fillna(df.median(numeric_only=True))\n",
"df_filled[-5:]"
]
},
@ -685,7 +685,7 @@
"metadata": {},
"outputs": [],
"source": [
"# But we are working on a copy \n",
"# But we are working on a copy, so we get a warning\n",
"df.iloc[889]['Sex'] = np.nan"
]
},
@ -695,7 +695,7 @@
"metadata": {},
"outputs": [],
"source": [
"# If we want to change, we should not chain selections\n",
"# If we want to change it, we should not chain selections\n",
"# The selection can be done with the column name\n",
"df.loc[889, 'Sex']"
]
@ -932,11 +932,11 @@
"metadata": {},
"source": [
"* [Pandas](http://pandas.pydata.org/)\n",
"* [Learning Pandas, Michael Heydt, Packt Publishing, 2015](http://proquest.safaribooksonline.com/book/programming/python/9781783985128)\n",
"* [Useful Pandas Snippets](https://gist.github.com/bsweger/e5817488d161f37dcbd2)\n",
"* [Pandas. Introduction to Data Structures](http://pandas.pydata.org/pandas-docs/stable/dsintro.html#dsintro)\n",
"* [Learning Pandas, Michael Heydt, Packt Publishing, 2017](https://learning.oreilly.com/library/view/learning-pandas/9781787123137/)\n",
"* [Pandas. Introduction to Data Structures](https://pandas.pydata.org/pandas-docs/stable/user_guide/dsintro.html)\n",
"* [Introducing Pandas Objects](https://www.oreilly.com/learning/introducing-pandas-objects)\n",
"* [Boolean Operators in Pandas](http://pandas.pydata.org/pandas-docs/stable/indexing.html#boolean-operators)"
"* [Boolean Operators in Pandas](https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#boolean-operators)\n",
"* [Useful Pandas Snippets](https://gist.github.com/bsweger/e5817488d161f37dcbd2)"
]
},
{
@ -958,7 +958,7 @@
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
@ -972,7 +972,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.1"
"version": "3.8.12"
},
"latex_envs": {
"LaTeX_envs_menu_present": true,

28
ml2/3_4_Visualisation_Pandas.ipynb
View File

@ -367,7 +367,7 @@
"outputs": [],
"source": [
"# Now we visualise age and survived to see if there is some relationship\n",
"sns.FacetGrid(df, hue=\"Survived\", size=5).map(sns.kdeplot, \"Age\").add_legend()"
"sns.FacetGrid(df, hue=\"Survived\", height=5).map(sns.kdeplot, \"Age\").add_legend()"
]
},
{
@ -567,7 +567,7 @@
"outputs": [],
"source": [
"# Plot with seaborn\n",
"sns.countplot('Sex', data=df)"
"sns.countplot(x='Sex', data=df)"
]
},
{
@ -683,16 +683,6 @@
"df.groupby('Pclass').size()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Distribution\n",
"sns.countplot('Pclass', data=df)"
]
},
{
"cell_type": "markdown",
"metadata": {},
@ -725,7 +715,7 @@
"metadata": {},
"outputs": [],
"source": [
"sns.factorplot('Pclass',data=df,hue='Sex',kind='count')"
"sns.catplot(x='Pclass',data=df,hue='Sex',kind='count')"
]
},
{
@ -906,7 +896,7 @@
"outputs": [],
"source": [
"# Distribution\n",
"sns.countplot('Embarked', data=df)"
"sns.countplot(x='Embarked', data=df)"
]
},
{
@ -997,7 +987,7 @@
"outputs": [],
"source": [
"# Distribution\n",
"sns.countplot('SibSp', data=df)"
"sns.countplot(x='SibSp', data=df)"
]
},
{
@ -1180,7 +1170,7 @@
"outputs": [],
"source": [
"# Distribution\n",
"sns.countplot('Parch', data=df)"
"sns.countplot(x='Parch', data=df)"
]
},
{
@ -1233,7 +1223,7 @@
"metadata": {},
"outputs": [],
"source": [
"df.groupby(['Pclass', 'Sex', 'Parch'])['Parch', 'SibSp', 'Survived'].agg({'Parch': np.size, 'SibSp': np.mean, 'Survived': np.mean})"
"df.groupby(['Pclass', 'Sex', 'Parch'])[['Parch', 'SibSp', 'Survived']].agg({'Parch': np.size, 'SibSp': np.mean, 'Survived': np.mean})"
]
},
{
@ -1576,7 +1566,7 @@
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
@ -1590,7 +1580,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.1"
"version": "3.8.12"
},
"latex_envs": {
"LaTeX_envs_menu_present": true,

339
ml2/3_5_Exercise_1.ipynb
View File

@ -46,7 +46,7 @@
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@ -72,7 +72,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"Assign the variable *df* a Dataframe with the Titanic Dataset from the URL https://raw.githubusercontent.com/gsi-upm/sitc/master/ml2/data-titanic/train.csv\"\n",
"Assign the variable *df* a Dataframe with the Titanic Dataset from the URL https://raw.githubusercontent.com/gsi-upm/sitc/master/ml2/data-titanic/train.csv.\n",
"\n",
"Print *df*."
]
@ -209,312 +209,9 @@
},
{
"cell_type": "code",
"execution_count": 20,
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>PassengerId</th>\n",
" <th>Survived</th>\n",
" <th>Pclass</th>\n",
" <th>Name</th>\n",
" <th>Sex</th>\n",
" <th>Age</th>\n",
" <th>SibSp</th>\n",
" <th>Parch</th>\n",
" <th>Ticket</th>\n",
" <th>Fare</th>\n",
" <th>Cabin</th>\n",
" <th>Embarked</th>\n",
" <th>FamilySize</th>\n",
" <th>AgeGroup</th>\n",
" <th>Deck</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>Braund, Mr. Owen Harris</td>\n",
" <td>male</td>\n",
" <td>22.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>A/5 21171</td>\n",
" <td>7.2500</td>\n",
" <td>NaN</td>\n",
" <td>S</td>\n",
" <td>1</td>\n",
" <td>3.0</td>\n",
" <td>X</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
" <td>female</td>\n",
" <td>38.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>PC 17599</td>\n",
" <td>71.2833</td>\n",
" <td>C85</td>\n",
" <td>C</td>\n",
" <td>1</td>\n",
" <td>3.0</td>\n",
" <td>C</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>1</td>\n",
" <td>3</td>\n",
" <td>Heikkinen, Miss. Laina</td>\n",
" <td>female</td>\n",
" <td>26.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>STON/O2. 3101282</td>\n",
" <td>7.9250</td>\n",
" <td>NaN</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>3.0</td>\n",
" <td>X</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
" <td>female</td>\n",
" <td>35.0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>113803</td>\n",
" <td>53.1000</td>\n",
" <td>C123</td>\n",
" <td>S</td>\n",
" <td>1</td>\n",
" <td>3.0</td>\n",
" <td>C</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>Allen, Mr. William Henry</td>\n",
" <td>male</td>\n",
" <td>35.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>373450</td>\n",
" <td>8.0500</td>\n",
" <td>NaN</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>3.0</td>\n",
" <td>X</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>886</th>\n",
" <td>887</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
" <td>Montvila, Rev. Juozas</td>\n",
" <td>male</td>\n",
" <td>27.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>211536</td>\n",
" <td>13.0000</td>\n",
" <td>NaN</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>3.0</td>\n",
" <td>X</td>\n",
" </tr>\n",
" <tr>\n",
" <th>887</th>\n",
" <td>888</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>Graham, Miss. Margaret Edith</td>\n",
" <td>female</td>\n",
" <td>19.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>112053</td>\n",
" <td>30.0000</td>\n",
" <td>B42</td>\n",
" <td>S</td>\n",
" <td>0</td>\n",
" <td>3.0</td>\n",
" <td>B</td>\n",
" </tr>\n",
" <tr>\n",
" <th>888</th>\n",
" <td>889</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>Johnston, Miss. Catherine Helen \"Carrie\"</td>\n",
" <td>female</td>\n",
" <td>NaN</td>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>W./C. 6607</td>\n",
" <td>23.4500</td>\n",
" <td>NaN</td>\n",
" <td>S</td>\n",
" <td>3</td>\n",
" <td>NaN</td>\n",
" <td>X</td>\n",
" </tr>\n",
" <tr>\n",
" <th>889</th>\n",
" <td>890</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>Behr, Mr. Karl Howell</td>\n",
" <td>male</td>\n",
" <td>26.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>111369</td>\n",
" <td>30.0000</td>\n",
" <td>C148</td>\n",
" <td>C</td>\n",
" <td>0</td>\n",
" <td>3.0</td>\n",
" <td>C</td>\n",
" </tr>\n",
" <tr>\n",
" <th>890</th>\n",
" <td>891</td>\n",
" <td>0</td>\n",
" <td>3</td>\n",
" <td>Dooley, Mr. Patrick</td>\n",
" <td>male</td>\n",
" <td>32.0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>370376</td>\n",
" <td>7.7500</td>\n",
" <td>NaN</td>\n",
" <td>Q</td>\n",
" <td>0</td>\n",
" <td>3.0</td>\n",
" <td>X</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>891 rows × 15 columns</p>\n",
"</div>"
],
"text/plain": [
" PassengerId Survived Pclass \\\n",
"0 1 0 3 \n",
"1 2 1 1 \n",
"2 3 1 3 \n",
"3 4 1 1 \n",
"4 5 0 3 \n",
".. ... ... ... \n",
"886 887 0 2 \n",
"887 888 1 1 \n",
"888 889 0 3 \n",
"889 890 1 1 \n",
"890 891 0 3 \n",
"\n",
" Name Sex Age SibSp \\\n",
"0 Braund, Mr. Owen Harris male 22.0 1 \n",
"1 Cumings, Mrs. John Bradley (Florence Briggs Th... female 38.0 1 \n",
"2 Heikkinen, Miss. Laina female 26.0 0 \n",
"3 Futrelle, Mrs. Jacques Heath (Lily May Peel) female 35.0 1 \n",
"4 Allen, Mr. William Henry male 35.0 0 \n",
".. ... ... ... ... \n",
"886 Montvila, Rev. Juozas male 27.0 0 \n",
"887 Graham, Miss. Margaret Edith female 19.0 0 \n",
"888 Johnston, Miss. Catherine Helen \"Carrie\" female NaN 1 \n",
"889 Behr, Mr. Karl Howell male 26.0 0 \n",
"890 Dooley, Mr. Patrick male 32.0 0 \n",
"\n",
" Parch Ticket Fare Cabin Embarked FamilySize AgeGroup \\\n",
"0 0 A/5 21171 7.2500 NaN S 1 3.0 \n",
"1 0 PC 17599 71.2833 C85 C 1 3.0 \n",
"2 0 STON/O2. 3101282 7.9250 NaN S 0 3.0 \n",
"3 0 113803 53.1000 C123 S 1 3.0 \n",
"4 0 373450 8.0500 NaN S 0 3.0 \n",
".. ... ... ... ... ... ... ... \n",
"886 0 211536 13.0000 NaN S 0 3.0 \n",
"887 0 112053 30.0000 B42 S 0 3.0 \n",
"888 2 W./C. 6607 23.4500 NaN S 3 NaN \n",
"889 0 111369 30.0000 C148 C 0 3.0 \n",
"890 0 370376 7.7500 NaN Q 0 3.0 \n",
"\n",
" Deck \n",
"0 X \n",
"1 C \n",
"2 X \n",
"3 C \n",
"4 X \n",
".. ... \n",
"886 X \n",
"887 B \n",
"888 X \n",
"889 C \n",
"890 X \n",
"\n",
"[891 rows x 15 columns]"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"outputs": [],
"source": [
"df['FamilySize'] = df['SibSp'] + df['Parch']\n",
"df"
@ -606,23 +303,9 @@
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
},
"outputs": [
{
"ename": "NameError",
"evalue": "name 'df' is not defined",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-2-515fd9f54fd1>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 13\u001b[0m \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 14\u001b[0m \u001b[0;32mreturn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Others'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 15\u001b[0;31m \u001b[0mdf\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'Salutation'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'Salutation'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mgroup_salutation\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 16\u001b[0m \u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgroupby\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'Salutation'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msize\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mNameError\u001b[0m: name 'df' is not defined"
]
}
],
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def group_salutation(old_salutation):\n",
" if old_salutation == 'Mr':\n",
@ -689,7 +372,7 @@
},
{
"cell_type": "code",
"execution_count": 12,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@ -712,7 +395,7 @@
},
{
"cell_type": "code",
"execution_count": 14,
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
@ -805,7 +488,7 @@
"window_display": false
},
"kernelspec": {
"display_name": "Python 3",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
@ -819,7 +502,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.8"
"version": "3.8.12"
},
"latex_envs": {
"LaTeX_envs_menu_present": true,

6
ml2/3_6_Machine_Learning.ipynb
View File

@ -78,7 +78,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"* [Python Machine Learning](http://proquest.safaribooksonline.com/book/programming/python/9781783555130), Sebastian Raschka, Packt Publishing, 2015."
"* [Python Machine Learning](https://learning.oreilly.com/library/view/python-machine-learning/9781789955750/), Sebastian Raschka and Vahid Mirjalili, Packt Publishing, 2019."
]
},
{
@ -100,7 +100,7 @@
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
@ -114,7 +114,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.1"
"version": "3.8.12"
},
"latex_envs": {
"LaTeX_envs_menu_present": true,

12
ml2/3_7_SVM.ipynb
View File

@ -535,13 +535,13 @@
"source": [
"# This step will take some time\n",
"# Cross-validationt\n",
"cv = KFold(n_splits=5, shuffle=False, random_state=33)\n",
"cv = KFold(n_splits=5, shuffle=True, random_state=33)\n",
"# StratifiedKFold has is a variation of k-fold which returns stratified folds:\n",
"# each set contains approximately the same percentage of samples of each target class as the complete set.\n",
"#cv = StratifiedKFold(y, n_folds=3, shuffle=False, random_state=33)\n",
"#cv = StratifiedKFold(y, n_folds=3, shuffle=True, random_state=33)\n",
"scores = cross_val_score(model, X, y, cv=cv)\n",
"print(\"Scores in every iteration\", scores)\n",
"print(\"Accuracy: %0.2f (+/- %0.2f)\" % (scores.mean(), scores.std() * 2))\n"
"print(\"Accuracy: %0.2f (+/- %0.2f)\" % (scores.mean(), scores.std() * 2))"
]
},
{
@ -644,7 +644,7 @@
"source": [
"* [Titanic Machine Learning from Disaster](https://www.kaggle.com/c/titanic/forums/t/5105/ipython-notebook-tutorial-for-titanic-machine-learning-from-disaster)\n",
"* [API SVC scikit-learn](http://scikit-learn.org/stable/modules/generated/sklearn.svm.SVC.html)\n",
"* [Better evaluation of classification models](http://blog.kaggle.com/2015/10/23/scikit-learn-video-9-better-evaluation-of-classification-models/)"
"* [How to choose the right metric for evaluating an ML model](https://www.kaggle.com/vipulgandhi/how-to-choose-right-metric-for-evaluating-ml-model)"
]
},
{
@ -666,7 +666,7 @@
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
@ -680,7 +680,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.1"
"version": "3.8.12"
},
"latex_envs": {
"LaTeX_envs_menu_present": true,

6
ml2/3_8_Exercise_2.ipynb
View File

@ -39,7 +39,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"In this exercise we are going to put in practice what we have learnt in the notebooks of the session. \n",
"In this exercise, we are going to put in practice what we have learnt in the notebooks of the session. \n",
"\n",
"In the previous notebook we have been applying the SVM machine learning algorithm.\n",
"\n",
@ -67,7 +67,7 @@
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
@ -81,7 +81,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.1"
"version": "3.8.12"
},
"latex_envs": {
"LaTeX_envs_menu_present": true,

221
ml2/plot_learning_curve.py
View File

@ -1,21 +1,21 @@
"""
Taken from http://scikit-learn.org/stable/auto_examples/model_selection/plot_learning_curve.html
========================
Plotting Learning Curves
========================
In the first column, first row the learning curve of a naive Bayes classifier
is shown for the digits dataset. Note that the training score and the
cross-validation score are both not very good at the end. However, the shape
of the curve can be found in more complex datasets very often: the training
score is very high at the beginning and decreases and the cross-validation
score is very low at the beginning and increases. In the second column, first
row we see the learning curve of an SVM with RBF kernel. We can see clearly
that the training score is still around the maximum and the validation score
could be increased with more training samples. The plots in the second row
show the times required by the models to train with various sizes of training
dataset. The plots in the third row show how much time was required to train
the models for each training sizes.
On the left side the learning curve of a naive Bayes classifier is shown for
the digits dataset. Note that the training score and the cross-validation score
are both not very good at the end. However, the shape of the curve can be found
in more complex datasets very often: the training score is very high at the
beginning and decreases and the cross-validation score is very low at the
beginning and increases. On the right side we see the learning curve of an SVM
with RBF kernel. We can see clearly that the training score is still around
the maximum and the validation score could be increased with more training
samples.
"""
#print(__doc__)
import numpy as np
import matplotlib.pyplot as plt
@ -23,86 +23,181 @@ from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
from sklearn.datasets import load_digits
from sklearn.model_selection import learning_curve
from sklearn.model_selection import ShuffleSplit
def plot_learning_curve(estimator, title, X, y, ylim=None, cv=None,
n_jobs=1, train_sizes=np.linspace(.1, 1.0, 5)):
def plot_learning_curve(
estimator,
title,
X,
y,
axes=None,
ylim=None,
cv=None,
n_jobs=None,
train_sizes=np.linspace(0.1, 1.0, 5),
):
"""
Generate a simple plot of the test and traning learning curve.
Generate 3 plots: the test and training learning curve, the training
samples vs fit times curve, the fit times vs score curve.
Parameters
----------
estimator : object type that implements the "fit" and "predict" methods
An object of that type which is cloned for each validation.
estimator : estimator instance
An estimator instance implementing `fit` and `predict` methods which
will be cloned for each validation.
title : string
title : str
Title for the chart.
X : array-like, shape (n_samples, n_features)
Training vector, where n_samples is the number of samples and
n_features is the number of features.
X : array-like of shape (n_samples, n_features)
Training vector, where ``n_samples`` is the number of samples and
``n_features`` is the number of features.
y : array-like, shape (n_samples) or (n_samples, n_features), optional
Target relative to X for classification or regression;
y : array-like of shape (n_samples) or (n_samples, n_features)
Target relative to ``X`` for classification or regression;
None for unsupervised learning.
ylim : tuple, shape (ymin, ymax), optional
Defines minimum and maximum yvalues plotted.
axes : array-like of shape (3,), default=None
Axes to use for plotting the curves.
cv : integer, cross-validation generator, optional
If an integer is passed, it is the number of folds (defaults to 3).
Specific cross-validation objects can be passed, see
sklearn.model_selection module for the list of possible objects
ylim : tuple of shape (2,), default=None
Defines minimum and maximum y-values plotted, e.g. (ymin, ymax).
n_jobs : integer, optional
Number of jobs to run in parallel (default 1).
cv : int, cross-validation generator or an iterable, default=None
Determines the cross-validation splitting strategy.
Possible inputs for cv are:
- None, to use the default 5-fold cross-validation,
- integer, to specify the number of folds.
- :term:`CV splitter`,
- An iterable yielding (train, test) splits as arrays of indices.
For integer/None inputs, if ``y`` is binary or multiclass,
:class:`StratifiedKFold` used. If the estimator is not a classifier
or if ``y`` is neither binary nor multiclass, :class:`KFold` is used.
Refer :ref:`User Guide <cross_validation>` for the various
cross-validators that can be used here.
n_jobs : int or None, default=None
Number of jobs to run in parallel.
``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
``-1`` means using all processors. See :term:`Glossary <n_jobs>`
for more details.
train_sizes : array-like of shape (n_ticks,)
Relative or absolute numbers of training examples that will be used to
generate the learning curve. If the ``dtype`` is float, it is regarded
as a fraction of the maximum size of the training set (that is
determined by the selected validation method), i.e. it has to be within
(0, 1]. Otherwise it is interpreted as absolute sizes of the training
sets. Note that for classification the number of samples usually have
to be big enough to contain at least one sample from each class.
(default: np.linspace(0.1, 1.0, 5))
"""
plt.figure()
plt.title(title)
if axes is None:
_, axes = plt.subplots(1, 3, figsize=(20, 5))
axes[0].set_title(title)
if ylim is not None:
plt.ylim(*ylim)
plt.xlabel("Training examples")
plt.ylabel("Score")
train_sizes, train_scores, test_scores = learning_curve(
estimator, X, y, cv=cv, n_jobs=n_jobs, train_sizes=train_sizes)
axes[0].set_ylim(*ylim)
axes[0].set_xlabel("Training examples")
axes[0].set_ylabel("Score")
train_sizes, train_scores, test_scores, fit_times, _ = learning_curve(
estimator,
X,
y,
cv=cv,
n_jobs=n_jobs,
train_sizes=train_sizes,
return_times=True,
)
train_scores_mean = np.mean(train_scores, axis=1)
train_scores_std = np.std(train_scores, axis=1)
test_scores_mean = np.mean(test_scores, axis=1)
test_scores_std = np.std(test_scores, axis=1)
plt.grid()
fit_times_mean = np.mean(fit_times, axis=1)
fit_times_std = np.std(fit_times, axis=1)
plt.fill_between(train_sizes, train_scores_mean - train_scores_std,
train_scores_mean + train_scores_std, alpha=0.1,
color="r")
plt.fill_between(train_sizes, test_scores_mean - test_scores_std,
test_scores_mean + test_scores_std, alpha=0.1, color="g")
plt.plot(train_sizes, train_scores_mean, 'o-', color="r",
label="Training score")
plt.plot(train_sizes, test_scores_mean, 'o-', color="g",
label="Cross-validation score")
# Plot learning curve
axes[0].grid()
axes[0].fill_between(
train_sizes,
train_scores_mean - train_scores_std,
train_scores_mean + train_scores_std,
alpha=0.1,
color="r",
)
axes[0].fill_between(
train_sizes,
test_scores_mean - test_scores_std,
test_scores_mean + test_scores_std,
alpha=0.1,
color="g",
)
axes[0].plot(
train_sizes, train_scores_mean, "o-", color="r", label="Training score"
)
axes[0].plot(
train_sizes, test_scores_mean, "o-", color="g", label="Cross-validation score"
)
axes[0].legend(loc="best")
# Plot n_samples vs fit_times
axes[1].grid()
axes[1].plot(train_sizes, fit_times_mean, "o-")
axes[1].fill_between(
train_sizes,
fit_times_mean - fit_times_std,
fit_times_mean + fit_times_std,
alpha=0.1,
)
axes[1].set_xlabel("Training examples")
axes[1].set_ylabel("fit_times")
axes[1].set_title("Scalability of the model")
# Plot fit_time vs score
fit_time_argsort = fit_times_mean.argsort()
fit_time_sorted = fit_times_mean[fit_time_argsort]
test_scores_mean_sorted = test_scores_mean[fit_time_argsort]
test_scores_std_sorted = test_scores_std[fit_time_argsort]
axes[2].grid()
axes[2].plot(fit_time_sorted, test_scores_mean_sorted, "o-")
axes[2].fill_between(
fit_time_sorted,
test_scores_mean_sorted - test_scores_std_sorted,
test_scores_mean_sorted + test_scores_std_sorted,
alpha=0.1,
)
axes[2].set_xlabel("fit_times")
axes[2].set_ylabel("Score")
axes[2].set_title("Performance of the model")
plt.legend(loc="best")
return plt
#digits = load_digits()
#X, y = digits.data, digits.target
fig, axes = plt.subplots(3, 2, figsize=(10, 15))
X, y = load_digits(return_X_y=True)
#title = "Learning Curves (Naive Bayes)"
# Cross validation with 100 iterations to get smoother mean test and train
title = "Learning Curves (Naive Bayes)"
# Cross validation with 50 iterations to get smoother mean test and train
# score curves, each time with 20% data randomly selected as a validation set.
#cv = cross_validation.ShuffleSplit(digits.data.shape[0], n_iter=100,
# test_size=0.2, random_state=0)
cv = ShuffleSplit(n_splits=50, test_size=0.2, random_state=0)
#estimator = GaussianNB()
#plot_learning_curve(estimator, title, X, y, ylim=(0.7, 1.01), cv=cv, n_jobs=4)
estimator = GaussianNB()
plot_learning_curve(
estimator, title, X, y, axes=axes[:, 0], ylim=(0.7, 1.01), cv=cv, n_jobs=4
)
#title = "Learning Curves (SVM, RBF kernel, $\gamma=0.001$)"
title = r"Learning Curves (SVM, RBF kernel, $\gamma=0.001$)"
# SVC is more expensive so we do a lower number of CV iterations:
#cv = cross_validation.ShuffleSplit(digits.data.shape[0], n_iter=10,
# test_size=0.2, random_state=0)
#estimator = SVC(gamma=0.001)
#plot_learning_curve(estimator, title, X, y, (0.7, 1.01), cv=cv, n_jobs=4)
cv = ShuffleSplit(n_splits=5, test_size=0.2, random_state=0)
estimator = SVC(gamma=0.001)
plot_learning_curve(
estimator, title, X, y, axes=axes[:, 1], ylim=(0.7, 1.01), cv=cv, n_jobs=4
)
#plt.show()
plt.show()

2
ml2/plot_svm.py
View File

@ -3,7 +3,7 @@ import matplotlib.pyplot as plt
import numpy as np
from sklearn import svm
#Taken from http://nbviewer.jupyter.org/github/agconti/kaggle-titanic/blob/master/Titanic.ipynb
# Taken from http://nbviewer.jupyter.org/github/agconti/kaggle-titanic/blob/master/Titanic.ipynb
def plot_svm(df):
# set plotting parameters