Datasets
Models
Downloads: 1
Diff of
/Models/Model_B (1).ipynb
[000000]
..
[6986c7]
Switch to side-by-side view
--- a +++ b/Models/Model_B (1).ipynb @@ -0,0 +1,609 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "provenance": [] + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + }, + "language_info": { + "name": "python" + } + }, + "cells": [ + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "a5Vf7VhQNGDs" + }, + "outputs": [], + "source": [ + "import pandas as pd\n", + "\n", + "df = pd.read_csv('/content/CS279 Data - Sheet1.csv')" + ] + }, + { + "cell_type": "code", + "source": [ + "df = df.dropna()" + ], + "metadata": { + "id": "TkOLhVxqNmNR" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "from sklearn.preprocessing import LabelEncoder\n", + "label_encoder = LabelEncoder()\n", + "df['Shape_Encoded'] = label_encoder.fit_transform(df['Shape'])\n", + "df['Color_Encoded'] = label_encoder.fit_transform(df['Color'])\n", + "df['Diagnosis'] = label_encoder.fit_transform(df['Infected'])" + ], + "metadata": { + "id": "3iLH8iynNppc" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "X = df[['Area']]\n", + "y = df[['Diagnosis']]" + ], + "metadata": { + "id": "9MrbV8gdOgAR" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "from sklearn.model_selection import train_test_split\n", + "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)" + ], + "metadata": { + "id": "yKmSraTfO300" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "from sklearn.linear_model import LogisticRegression\n", + "log_reg_model = LogisticRegression(random_state=42)\n", + "log_reg_model.fit(X_train, y_train)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 136 + }, + "id": "pRAanHQZO--R", + "outputId": "b7e6c4ae-8364-4cb7-f2c7-0495bc22058c" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stderr", + "text": [ + "/usr/local/lib/python3.10/dist-packages/sklearn/utils/validation.py:1339: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n", + " y = column_or_1d(y, warn=True)\n" + ] + }, + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "LogisticRegression(random_state=42)" + ], + "text/html": [ + "<style>#sk-container-id-2 {\n", + " /* Definition of color scheme common for light and dark mode */\n", + " --sklearn-color-text: black;\n", + " --sklearn-color-line: gray;\n", + " /* Definition of color scheme for unfitted estimators */\n", + " --sklearn-color-unfitted-level-0: #fff5e6;\n", + " --sklearn-color-unfitted-level-1: #f6e4d2;\n", + " --sklearn-color-unfitted-level-2: #ffe0b3;\n", + " --sklearn-color-unfitted-level-3: chocolate;\n", + " /* Definition of color scheme for fitted estimators */\n", + " --sklearn-color-fitted-level-0: #f0f8ff;\n", + " --sklearn-color-fitted-level-1: #d4ebff;\n", + " --sklearn-color-fitted-level-2: #b3dbfd;\n", + " --sklearn-color-fitted-level-3: cornflowerblue;\n", + "\n", + " /* Specific color for light theme */\n", + " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n", + " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n", + " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n", + " --sklearn-color-icon: #696969;\n", + "\n", + " @media (prefers-color-scheme: dark) {\n", + " /* Redefinition of color scheme for dark theme */\n", + " --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n", + " --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n", + " --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n", + " --sklearn-color-icon: #878787;\n", + " }\n", + "}\n", + "\n", + "#sk-container-id-2 {\n", + " color: var(--sklearn-color-text);\n", + "}\n", + "\n", + "#sk-container-id-2 pre {\n", + " padding: 0;\n", + "}\n", + "\n", + "#sk-container-id-2 input.sk-hidden--visually {\n", + " border: 0;\n", + " clip: rect(1px 1px 1px 1px);\n", + " clip: rect(1px, 1px, 1px, 1px);\n", + " height: 1px;\n", + " margin: -1px;\n", + " overflow: hidden;\n", + " padding: 0;\n", + " position: absolute;\n", + " width: 1px;\n", + "}\n", + "\n", + "#sk-container-id-2 div.sk-dashed-wrapped {\n", + " border: 1px dashed var(--sklearn-color-line);\n", + " margin: 0 0.4em 0.5em 0.4em;\n", + " box-sizing: border-box;\n", + " padding-bottom: 0.4em;\n", + " background-color: var(--sklearn-color-background);\n", + "}\n", + "\n", + "#sk-container-id-2 div.sk-container {\n", + " /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n", + " but bootstrap.min.css set `[hidden] { display: none !important; }`\n", + " so we also need the `!important` here to be able to override the\n", + " default hidden behavior on the sphinx rendered scikit-learn.org.\n", + " See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n", + " display: inline-block !important;\n", + " position: relative;\n", + "}\n", + "\n", + "#sk-container-id-2 div.sk-text-repr-fallback {\n", + " display: none;\n", + "}\n", + "\n", + "div.sk-parallel-item,\n", + "div.sk-serial,\n", + "div.sk-item {\n", + " /* draw centered vertical line to link estimators */\n", + " background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n", + " background-size: 2px 100%;\n", + " background-repeat: no-repeat;\n", + " background-position: center center;\n", + "}\n", + "\n", + "/* Parallel-specific style estimator block */\n", + "\n", + "#sk-container-id-2 div.sk-parallel-item::after {\n", + " content: \"\";\n", + " width: 100%;\n", + " border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n", + " flex-grow: 1;\n", + "}\n", + "\n", + "#sk-container-id-2 div.sk-parallel {\n", + " display: flex;\n", + " align-items: stretch;\n", + " justify-content: center;\n", + " background-color: var(--sklearn-color-background);\n", + " position: relative;\n", + "}\n", + "\n", + "#sk-container-id-2 div.sk-parallel-item {\n", + " display: flex;\n", + " flex-direction: column;\n", + "}\n", + "\n", + "#sk-container-id-2 div.sk-parallel-item:first-child::after {\n", + " align-self: flex-end;\n", + " width: 50%;\n", + "}\n", + "\n", + "#sk-container-id-2 div.sk-parallel-item:last-child::after {\n", + " align-self: flex-start;\n", + " width: 50%;\n", + "}\n", + "\n", + "#sk-container-id-2 div.sk-parallel-item:only-child::after {\n", + " width: 0;\n", + "}\n", + "\n", + "/* Serial-specific style estimator block */\n", + "\n", + "#sk-container-id-2 div.sk-serial {\n", + " display: flex;\n", + " flex-direction: column;\n", + " align-items: center;\n", + " background-color: var(--sklearn-color-background);\n", + " padding-right: 1em;\n", + " padding-left: 1em;\n", + "}\n", + "\n", + "\n", + "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n", + "clickable and can be expanded/collapsed.\n", + "- Pipeline and ColumnTransformer use this feature and define the default style\n", + "- Estimators will overwrite some part of the style using the `sk-estimator` class\n", + "*/\n", + "\n", + "/* Pipeline and ColumnTransformer style (default) */\n", + "\n", + "#sk-container-id-2 div.sk-toggleable {\n", + " /* Default theme specific background. It is overwritten whether we have a\n", + " specific estimator or a Pipeline/ColumnTransformer */\n", + " background-color: var(--sklearn-color-background);\n", + "}\n", + "\n", + "/* Toggleable label */\n", + "#sk-container-id-2 label.sk-toggleable__label {\n", + " cursor: pointer;\n", + " display: block;\n", + " width: 100%;\n", + " margin-bottom: 0;\n", + " padding: 0.5em;\n", + " box-sizing: border-box;\n", + " text-align: center;\n", + "}\n", + "\n", + "#sk-container-id-2 label.sk-toggleable__label-arrow:before {\n", + " /* Arrow on the left of the label */\n", + " content: \"▸\";\n", + " float: left;\n", + " margin-right: 0.25em;\n", + " color: var(--sklearn-color-icon);\n", + "}\n", + "\n", + "#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {\n", + " color: var(--sklearn-color-text);\n", + "}\n", + "\n", + "/* Toggleable content - dropdown */\n", + "\n", + "#sk-container-id-2 div.sk-toggleable__content {\n", + " max-height: 0;\n", + " max-width: 0;\n", + " overflow: hidden;\n", + " text-align: left;\n", + " /* unfitted */\n", + " background-color: var(--sklearn-color-unfitted-level-0);\n", + "}\n", + "\n", + "#sk-container-id-2 div.sk-toggleable__content.fitted {\n", + " /* fitted */\n", + " background-color: var(--sklearn-color-fitted-level-0);\n", + "}\n", + "\n", + "#sk-container-id-2 div.sk-toggleable__content pre {\n", + " margin: 0.2em;\n", + " border-radius: 0.25em;\n", + " color: var(--sklearn-color-text);\n", + " /* unfitted */\n", + " background-color: var(--sklearn-color-unfitted-level-0);\n", + "}\n", + "\n", + "#sk-container-id-2 div.sk-toggleable__content.fitted pre {\n", + " /* unfitted */\n", + " background-color: var(--sklearn-color-fitted-level-0);\n", + "}\n", + "\n", + "#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n", + " /* Expand drop-down */\n", + " max-height: 200px;\n", + " max-width: 100%;\n", + " overflow: auto;\n", + "}\n", + "\n", + "#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n", + " content: \"▾\";\n", + "}\n", + "\n", + "/* Pipeline/ColumnTransformer-specific style */\n", + "\n", + "#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n", + " color: var(--sklearn-color-text);\n", + " background-color: var(--sklearn-color-unfitted-level-2);\n", + "}\n", + "\n", + "#sk-container-id-2 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n", + " background-color: var(--sklearn-color-fitted-level-2);\n", + "}\n", + "\n", + "/* Estimator-specific style */\n", + "\n", + "/* Colorize estimator box */\n", + "#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n", + " /* unfitted */\n", + " background-color: var(--sklearn-color-unfitted-level-2);\n", + "}\n", + "\n", + "#sk-container-id-2 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n", + " /* fitted */\n", + " background-color: var(--sklearn-color-fitted-level-2);\n", + "}\n", + "\n", + "#sk-container-id-2 div.sk-label label.sk-toggleable__label,\n", + "#sk-container-id-2 div.sk-label label {\n", + " /* The background is the default theme color */\n", + " color: var(--sklearn-color-text-on-default-background);\n", + "}\n", + "\n", + "/* On hover, darken the color of the background */\n", + "#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {\n", + " color: var(--sklearn-color-text);\n", + " background-color: var(--sklearn-color-unfitted-level-2);\n", + "}\n", + "\n", + "/* Label box, darken color on hover, fitted */\n", + "#sk-container-id-2 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n", + " color: var(--sklearn-color-text);\n", + " background-color: var(--sklearn-color-fitted-level-2);\n", + "}\n", + "\n", + "/* Estimator label */\n", + "\n", + "#sk-container-id-2 div.sk-label label {\n", + " font-family: monospace;\n", + " font-weight: bold;\n", + " display: inline-block;\n", + " line-height: 1.2em;\n", + "}\n", + "\n", + "#sk-container-id-2 div.sk-label-container {\n", + " text-align: center;\n", + "}\n", + "\n", + "/* Estimator-specific */\n", + "#sk-container-id-2 div.sk-estimator {\n", + " font-family: monospace;\n", + " border: 1px dotted var(--sklearn-color-border-box);\n", + " border-radius: 0.25em;\n", + " box-sizing: border-box;\n", + " margin-bottom: 0.5em;\n", + " /* unfitted */\n", + " background-color: var(--sklearn-color-unfitted-level-0);\n", + "}\n", + "\n", + "#sk-container-id-2 div.sk-estimator.fitted {\n", + " /* fitted */\n", + " background-color: var(--sklearn-color-fitted-level-0);\n", + "}\n", + "\n", + "/* on hover */\n", + "#sk-container-id-2 div.sk-estimator:hover {\n", + " /* unfitted */\n", + " background-color: var(--sklearn-color-unfitted-level-2);\n", + "}\n", + "\n", + "#sk-container-id-2 div.sk-estimator.fitted:hover {\n", + " /* fitted */\n", + " background-color: var(--sklearn-color-fitted-level-2);\n", + "}\n", + "\n", + "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n", + "\n", + "/* Common style for \"i\" and \"?\" */\n", + "\n", + ".sk-estimator-doc-link,\n", + "a:link.sk-estimator-doc-link,\n", + "a:visited.sk-estimator-doc-link {\n", + " float: right;\n", + " font-size: smaller;\n", + " line-height: 1em;\n", + " font-family: monospace;\n", + " background-color: var(--sklearn-color-background);\n", + " border-radius: 1em;\n", + " height: 1em;\n", + " width: 1em;\n", + " text-decoration: none !important;\n", + " margin-left: 1ex;\n", + " /* unfitted */\n", + " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n", + " color: var(--sklearn-color-unfitted-level-1);\n", + "}\n", + "\n", + ".sk-estimator-doc-link.fitted,\n", + "a:link.sk-estimator-doc-link.fitted,\n", + "a:visited.sk-estimator-doc-link.fitted {\n", + " /* fitted */\n", + " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n", + " color: var(--sklearn-color-fitted-level-1);\n", + "}\n", + "\n", + "/* On hover */\n", + "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n", + ".sk-estimator-doc-link:hover,\n", + "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n", + ".sk-estimator-doc-link:hover {\n", + " /* unfitted */\n", + " background-color: var(--sklearn-color-unfitted-level-3);\n", + " color: var(--sklearn-color-background);\n", + " text-decoration: none;\n", + "}\n", + "\n", + "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n", + ".sk-estimator-doc-link.fitted:hover,\n", + "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n", + ".sk-estimator-doc-link.fitted:hover {\n", + " /* fitted */\n", + " background-color: var(--sklearn-color-fitted-level-3);\n", + " color: var(--sklearn-color-background);\n", + " text-decoration: none;\n", + "}\n", + "\n", + "/* Span, style for the box shown on hovering the info icon */\n", + ".sk-estimator-doc-link span {\n", + " display: none;\n", + " z-index: 9999;\n", + " position: relative;\n", + " font-weight: normal;\n", + " right: .2ex;\n", + " padding: .5ex;\n", + " margin: .5ex;\n", + " width: min-content;\n", + " min-width: 20ex;\n", + " max-width: 50ex;\n", + " color: var(--sklearn-color-text);\n", + " box-shadow: 2pt 2pt 4pt #999;\n", + " /* unfitted */\n", + " background: var(--sklearn-color-unfitted-level-0);\n", + " border: .5pt solid var(--sklearn-color-unfitted-level-3);\n", + "}\n", + "\n", + ".sk-estimator-doc-link.fitted span {\n", + " /* fitted */\n", + " background: var(--sklearn-color-fitted-level-0);\n", + " border: var(--sklearn-color-fitted-level-3);\n", + "}\n", + "\n", + ".sk-estimator-doc-link:hover span {\n", + " display: block;\n", + "}\n", + "\n", + "/* \"?\"-specific style due to the `<a>` HTML tag */\n", + "\n", + "#sk-container-id-2 a.estimator_doc_link {\n", + " float: right;\n", + " font-size: 1rem;\n", + " line-height: 1em;\n", + " font-family: monospace;\n", + " background-color: var(--sklearn-color-background);\n", + " border-radius: 1rem;\n", + " height: 1rem;\n", + " width: 1rem;\n", + " text-decoration: none;\n", + " /* unfitted */\n", + " color: var(--sklearn-color-unfitted-level-1);\n", + " border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n", + "}\n", + "\n", + "#sk-container-id-2 a.estimator_doc_link.fitted {\n", + " /* fitted */\n", + " border: var(--sklearn-color-fitted-level-1) 1pt solid;\n", + " color: var(--sklearn-color-fitted-level-1);\n", + "}\n", + "\n", + "/* On hover */\n", + "#sk-container-id-2 a.estimator_doc_link:hover {\n", + " /* unfitted */\n", + " background-color: var(--sklearn-color-unfitted-level-3);\n", + " color: var(--sklearn-color-background);\n", + " text-decoration: none;\n", + "}\n", + "\n", + "#sk-container-id-2 a.estimator_doc_link.fitted:hover {\n", + " /* fitted */\n", + " background-color: var(--sklearn-color-fitted-level-3);\n", + "}\n", + "</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression(random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\"> LogisticRegression<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.linear_model.LogisticRegression.html\">?<span>Documentation for LogisticRegression</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>LogisticRegression(random_state=42)</pre></div> </div></div></div></div>" + ] + }, + "metadata": {}, + "execution_count": 17 + } + ] + }, + { + "cell_type": "code", + "source": [ + "from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score, confusion_matrix\n", + "from sklearn.metrics import roc_auc_score" + ], + "metadata": { + "id": "0J50xt-YPlio" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "y_pred = log_reg_model.predict(X_test)\n", + "accuracy = accuracy_score(y_test, y_pred)\n", + "precision = precision_score(y_test, y_pred)\n", + "recall = recall_score(y_test, y_pred)\n", + "f1 = f1_score(y_test, y_pred)" + ], + "metadata": { + "id": "WgLjC2AfPnZg" + }, + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "source": [ + "y_scores = log_reg_model.predict_proba(X_test)[:, 1]\n", + "\n", + "# Compute the ROC AUC score\n", + "roc_auc = roc_auc_score(y_test, y_scores)\n", + "\n", + "print(f\"ROC AUC Score: {roc_auc:.2f}\")" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "JKbm1CT6PwDa", + "outputId": "fa7ef655-f7df-438c-a022-e6427c0549d7" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "ROC AUC Score: 0.94\n" + ] + } + ] + }, + { + "cell_type": "code", + "source": [ + "print(f'Accuracy: {accuracy * 100:.2f}%')\n", + "print(f'Precision: {precision * 100:.2f}%')\n", + "print(f'Recall: {recall * 100:.2f}%')\n", + "print(f'F1 Score: {f1 * 100:.2f}%')" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "bkUrSfC0Pzul", + "outputId": "29a0e64c-40f3-417e-8300-b841403ccaea" + }, + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Accuracy: 91.67%\n", + "Precision: 66.67%\n", + "Recall: 80.00%\n", + "F1 Score: 72.73%\n" + ] + } + ] + } + ] +} \ No newline at end of file