Skip to content

Commit

Permalink
updated kernelspec with script (#1251)
Browse files Browse the repository at this point in the history
  • Loading branch information
@manuelhelmerichs
manuelhelmerichs committed Jul 24, 2024
1 parent aa2b3e8 commit 1a7b49f
Show file tree
Hide file tree
Showing 19 changed files with 7,024 additions and 6,987 deletions.
762 changes: 381 additions & 381 deletions exercises/evaluation/ex_eval_1_py.ipynb
View file

Large diffs are not rendered by default.

326 changes: 163 additions & 163 deletions exercises/evaluation/ex_eval_2_py.ipynb
View file
Original file line number Diff line number Diff line change
@@ -1,165 +1,165 @@
{
"cells": [
{
"cell_type": "markdown",
"id": "53329df4",
"metadata": {},
"source": [
"***\n",
"**Introduction to Machine Learning** <br>\n",
"__[https://slds-lmu.github.io/i2ml/](https://slds-lmu.github.io/i2ml/)__\n",
"***"
]
"cells": [
{
"cell_type": "markdown",
"id": "53329df4",
"metadata": {},
"source": [
"***\n",
"**Introduction to Machine Learning** <br>\n",
"__[https://slds-lmu.github.io/i2ml/](https://slds-lmu.github.io/i2ml/)__\n",
"***"
]
},
{
"cell_type": "markdown",
"id": "56e690c1",
"metadata": {},
"source": [
"# Exercise sheet 6: Evaluation 2"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "2848e780",
"metadata": {},
"outputs": [],
"source": [
"#| label: import\n",
"# Consider the following libraries for this exercise sheet:\n",
"\n",
"# general\n",
"import numpy as np\n",
"import pandas as pd\n",
"\n",
"# sklearn\n",
"from sklearn.linear_model import LogisticRegression\n",
"from sklearn.preprocessing import LabelEncoder\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.model_selection import RepeatedKFold\n",
"from sklearn.model_selection import RepeatedStratifiedKFold"
]
},
{
"cell_type": "markdown",
"id": "bb7dd93d",
"metadata": {},
"source": [
"## Exercise 2: Resampling strategies"
]
},
{
"cell_type": "markdown",
"id": "5ca487b7",
"metadata": {},
"source": [
"> a) Why would we apply resampling rather than a single holdout split?\n",
"\n",
"> **\\# Enter your answer here:**"
]
},
{
"cell_type": "markdown",
"id": "086f9397",
"metadata": {},
"source": [
"> b) Classify the `german_credit` data into solvent and insolvent debtors using logistic regression. Compute the\n",
"training error w.r.t. MCE."
]
},
{
"cell_type": "markdown",
"id": "a2c7a878",
"metadata": {},
"source": [
"<div class=\"alert alert-block alert-info\">\n",
" <b>Hint:</b> Read the already preprocessed file <a href=\"https://github.com/slds-lmu/lecture_i2ml/blob/master/exercises/data/german_credit_for_py.csv\"><code>german_credit_for_py.csv</code></a>.<br>\n",
"</div>"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "582a28c4",
"metadata": {},
"outputs": [],
"source": [
"# Enter your code here:"
]
},
{
"cell_type": "markdown",
"id": "d7767419",
"metadata": {},
"source": [
"> c) In order to evaluate your learner, compare test MCE using\n",
">> (i) three times ten-fold cross validation (3x10-CV) <br>\n",
">> (ii) 10x3-CV <br>\n",
">> (iii) 3x10-CV with stratification for the feature `foreign_worker` to ensure equal representation in all folds <br>\n",
">> (iv) a single holdout split with $90\\%$ training data"
]
},
{
"cell_type": "markdown",
"id": "0a9c9f8e",
"metadata": {},
"source": [
"<div class=\"alert alert-block alert-info\">\n",
" <b>Hint:</b> you will need <code>RepeatedKFold</code>, <code>RepeatedStratifiedKFold</code>, and <code>train_test_split</code>. <br>\n",
"</div>"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "2091102d",
"metadata": {},
"outputs": [],
"source": [
"# Enter your code here:"
]
},
{
"cell_type": "markdown",
"id": "9f12230c",
"metadata": {},
"source": [
"> d) Discuss and compare your findings from c) and compare them to the training error from b).\n",
"\n",
"> **\\# Enter your answer here:**"
]
},
{
"cell_type": "markdown",
"id": "7bf9bb5e",
"metadata": {},
"source": [
"> e) Would you consider LOO-CV to be a good alternative?\n",
"\n",
"> **\\# Enter your answer here:**"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python (I2ML)",
"language": "python",
"name": "python-i2ml"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.13"
}
},
{
"cell_type": "markdown",
"id": "56e690c1",
"metadata": {},
"source": [
"# Exercise sheet 6: Evaluation 2"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2848e780",
"metadata": {},
"outputs": [],
"source": [
"#| label: import\n",
"# Consider the following libraries for this exercise sheet:\n",
"\n",
"# general\n",
"import numpy as np\n",
"import pandas as pd\n",
"\n",
"# sklearn\n",
"from sklearn.linear_model import LogisticRegression\n",
"from sklearn.preprocessing import LabelEncoder\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.model_selection import RepeatedKFold\n",
"from sklearn.model_selection import RepeatedStratifiedKFold"
]
},
{
"cell_type": "markdown",
"id": "bb7dd93d",
"metadata": {},
"source": [
"## Exercise 2: Resampling strategies"
]
},
{
"cell_type": "markdown",
"id": "5ca487b7",
"metadata": {},
"source": [
"> a) Why would we apply resampling rather than a single holdout split?\n",
"\n",
"> **\\# Enter your answer here:**"
]
},
{
"cell_type": "markdown",
"id": "086f9397",
"metadata": {},
"source": [
"> b) Classify the `german_credit` data into solvent and insolvent debtors using logistic regression. Compute the\n",
"training error w.r.t. MCE."
]
},
{
"cell_type": "markdown",
"id": "a2c7a878",
"metadata": {},
"source": [
"<div class=\"alert alert-block alert-info\">\n",
" <b>Hint:</b> Read the already preprocessed file <a href=\"https://github.com/slds-lmu/lecture_i2ml/blob/master/exercises/data/german_credit_for_py.csv\"><code>german_credit_for_py.csv</code></a>.<br>\n",
"</div>"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "582a28c4",
"metadata": {},
"outputs": [],
"source": [
"# Enter your code here:"
]
},
{
"cell_type": "markdown",
"id": "d7767419",
"metadata": {},
"source": [
"> c) In order to evaluate your learner, compare test MCE using\n",
">> (i) three times ten-fold cross validation (3x10-CV) <br>\n",
">> (ii) 10x3-CV <br>\n",
">> (iii) 3x10-CV with stratification for the feature `foreign_worker` to ensure equal representation in all folds <br>\n",
">> (iv) a single holdout split with $90\\%$ training data"
]
},
{
"cell_type": "markdown",
"id": "0a9c9f8e",
"metadata": {},
"source": [
"<div class=\"alert alert-block alert-info\">\n",
" <b>Hint:</b> you will need <code>RepeatedKFold</code>, <code>RepeatedStratifiedKFold</code>, and <code>train_test_split</code>. <br>\n",
"</div>"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2091102d",
"metadata": {},
"outputs": [],
"source": [
"# Enter your code here:"
]
},
{
"cell_type": "markdown",
"id": "9f12230c",
"metadata": {},
"source": [
"> d) Discuss and compare your findings from c) and compare them to the training error from b).\n",
"\n",
"> **\\# Enter your answer here:**"
]
},
{
"cell_type": "markdown",
"id": "7bf9bb5e",
"metadata": {},
"source": [
"> e) Would you consider LOO-CV to be a good alternative?\n",
"\n",
"> **\\# Enter your answer here:**"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.12"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
"nbformat": 4,
"nbformat_minor": 5
}
Loading

0 comments on commit 1a7b49f

Please sign in to comment.