Permalink
Show file tree
Hide file tree
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Showing
16 changed files
with
8,395 additions
and
31 deletions.
There are no files selected for viewing
Large diffs are not rendered by default.
Oops, something went wrong.
Large diffs are not rendered by default.
Oops, something went wrong.
Large diffs are not rendered by default.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,202 @@ | ||
{ | ||
"cells": [ | ||
{ | ||
"cell_type": "markdown", | ||
"metadata": {}, | ||
"source": [ | ||
"# Notebook showing confusion matrix evaluation of a trained logistic regression model\n", | ||
"#### by Salih MSA" | ||
] | ||
}, | ||
{ | ||
"cell_type": "markdown", | ||
"metadata": {}, | ||
"source": [ | ||
"## Importing" | ||
] | ||
}, | ||
{ | ||
"cell_type": "markdown", | ||
"metadata": {}, | ||
"source": [ | ||
"### Importing libraries" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": 14, | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"import numpy as np\n", | ||
"import pandas as pd\n", | ||
"\n", | ||
"import statistics # mean, median, etc.\n", | ||
"\n", | ||
"# Data visualisation functionality\n", | ||
"import matplotlib.pyplot as plt\n", | ||
"%matplotlib inline\n", | ||
"import seaborn as sns\n", | ||
"\n", | ||
"from sklearn.model_selection import train_test_split # method to split dataset into 4\n", | ||
"from sklearn.linear_model import LogisticRegression # linear regression algorithm\n", | ||
"from sklearn.metrics import mean_squared_error, mean_absolute_error # accuracy testing method\n", | ||
"from sklearn.metrics import confusion_matrix\n", | ||
"import seaborn as sns" | ||
] | ||
}, | ||
{ | ||
"cell_type": "markdown", | ||
"metadata": {}, | ||
"source": [ | ||
"### Importing data" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": 3, | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"cols = [\"test a\", \"test b\", \"accepted\"]\n", | ||
"data = pd.read_csv(\"../Week3/admission.data\", names=cols) # import dataset with custom headers, store" | ||
] | ||
}, | ||
{ | ||
"cell_type": "markdown", | ||
"metadata": {}, | ||
"source": [ | ||
"## Learning itself" | ||
] | ||
}, | ||
{ | ||
"cell_type": "markdown", | ||
"metadata": {}, | ||
"source": [ | ||
"### Splitting dataset" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": 4, | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"x = data.iloc[:, -3:-1].values # values we want to classify\n", | ||
"y = data.iloc[:, -1].values # acceptances for each row\n", | ||
"x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=.25, random_state=0) # split dataset into train, test" | ||
] | ||
}, | ||
{ | ||
"cell_type": "markdown", | ||
"metadata": {}, | ||
"source": [ | ||
"### Train model" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": 5, | ||
"metadata": {}, | ||
"outputs": [ | ||
{ | ||
"data": { | ||
"text/plain": [ | ||
"LogisticRegression()" | ||
] | ||
}, | ||
"execution_count": 5, | ||
"metadata": {}, | ||
"output_type": "execute_result" | ||
} | ||
], | ||
"source": [ | ||
"model = LogisticRegression()\n", | ||
"model.fit(x_train, y_train)" | ||
] | ||
}, | ||
{ | ||
"cell_type": "markdown", | ||
"metadata": {}, | ||
"source": [ | ||
"## Testing (using confusion matrix) (focus of notebook)" | ||
] | ||
}, | ||
{ | ||
"cell_type": "markdown", | ||
"metadata": {}, | ||
"source": [ | ||
"### Generate matrix" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": 9, | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"y_test_pred = model.predict(x_test)\n", | ||
"cm = confusion_matrix(y_test, y_test_pred) # shows true positive, true negative, false positive, false negatives for test dataset\n", | ||
" # in array form" | ||
] | ||
}, | ||
{ | ||
"cell_type": "markdown", | ||
"metadata": {}, | ||
"source": [ | ||
"### Visualise matrix" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": 15, | ||
"metadata": {}, | ||
"outputs": [ | ||
{ | ||
"ename": "TypeError", | ||
"evalue": "plot_confusion_matrix() missing 2 required positional arguments: 'X' and 'y_true'", | ||
"output_type": "error", | ||
"traceback": [ | ||
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", | ||
"\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)", | ||
"\u001b[0;32m<ipython-input-15-f03823523525>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0mlabels\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m\"T+\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\"T-\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\"F+\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\"F-\"\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mplot_confusion_matrix\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcm\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", | ||
"\u001b[0;32m~/.local/lib/python3.8/site-packages/sklearn/utils/validation.py\u001b[0m in \u001b[0;36minner_f\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 61\u001b[0m \u001b[0mextra_args\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m-\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mall_args\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 62\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mextra_args\u001b[0m \u001b[0;34m<=\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 63\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\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 64\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 65\u001b[0m \u001b[0;31m# extra_args > 0\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", | ||
"\u001b[0;31mTypeError\u001b[0m: plot_confusion_matrix() missing 2 required positional arguments: 'X' and 'y_true'" | ||
] | ||
} | ||
], | ||
"source": [ | ||
"labels = [\"T+\",\"T-\",\"F+\",\"F-\"]\n", | ||
"plot_confusion_matrix(cm)" | ||
] | ||
}, | ||
{ | ||
"cell_type": "code", | ||
"execution_count": null, | ||
"metadata": {}, | ||
"outputs": [], | ||
"source": [] | ||
} | ||
], | ||
"metadata": { | ||
"kernelspec": { | ||
"display_name": "Python 3", | ||
"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": "3.8.10" | ||
} | ||
}, | ||
"nbformat": 4, | ||
"nbformat_minor": 4 | ||
} |
Oops, something went wrong.