From cbdb9b00dc8cb135bef577fdd0199665fd0a76fe Mon Sep 17 00:00:00 2001
From: "Shekwoyeyilo2.gado@live.uwe.ac.uk" <sarah.y.gado@gmail.com>
Date: Wed, 12 Mar 2025 22:14:53 +0000
Subject: [PATCH] model parameters
---
models.ipynb | 47 ++++++++++++++---------------------------------
1 file changed, 14 insertions(+), 33 deletions(-)
diff --git a/models.ipynb b/models.ipynb
index 796d363..55980ec 100644
--- a/models.ipynb
+++ b/models.ipynb
@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
@@ -24,7 +24,7 @@
},
{
"cell_type": "code",
- "execution_count": 2,
+ "execution_count": 11,
"metadata": {},
"outputs": [
{
@@ -155,7 +155,7 @@
"9 ['BehavioralProblems', 'DifficultyCompletingTa... "
]
},
- "execution_count": 2,
+ "execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
@@ -167,7 +167,7 @@
},
{
"cell_type": "code",
- "execution_count": 3,
+ "execution_count": 12,
"metadata": {},
"outputs": [
{
@@ -181,7 +181,7 @@
" 'MMSE']"
]
},
- "execution_count": 3,
+ "execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
@@ -195,7 +195,7 @@
},
{
"cell_type": "code",
- "execution_count": 4,
+ "execution_count": 13,
"metadata": {},
"outputs": [
{
@@ -581,7 +581,7 @@
"[2149 rows x 35 columns]"
]
},
- "execution_count": 4,
+ "execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
@@ -593,7 +593,7 @@
},
{
"cell_type": "code",
- "execution_count": 5,
+ "execution_count": 14,
"metadata": {},
"outputs": [
{
@@ -772,7 +772,7 @@
"[2149 rows x 7 columns]"
]
},
- "execution_count": 5,
+ "execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
@@ -785,7 +785,7 @@
},
{
"cell_type": "code",
- "execution_count": 6,
+ "execution_count": 15,
"metadata": {},
"outputs": [
{
@@ -840,7 +840,7 @@
},
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
@@ -867,7 +867,7 @@
},
{
"cell_type": "code",
- "execution_count": 8,
+ "execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
@@ -904,7 +904,7 @@
},
{
"cell_type": "code",
- "execution_count": 9,
+ "execution_count": null,
"metadata": {},
"outputs": [
{
@@ -915,29 +915,10 @@
"Best parameters for DecisionTree: {'criterion': 'entropy', 'max_depth': 10, 'min_samples_leaf': 4, 'min_samples_split': 2}\n",
"\n",
"Running RandomizedSearchCV for RandomForest...\n",
- "Best parameters for RandomForest: {'criterion': 'gini', 'max_depth': 30, 'min_samples_leaf': 4, 'min_samples_split': 9, 'n_estimators': 112}\n",
+ "Best parameters for RandomForest: {'criterion': 'gini', 'max_depth': 50, 'min_samples_leaf': 2, 'min_samples_split': 8, 'n_estimators': 102}\n",
"\n",
"Running RandomizedSearchCV for svc...\n"
]
- },
- {
- "ename": "KeyboardInterrupt",
- "evalue": "",
- "output_type": "error",
- "traceback": [
- "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
- "\u001b[1;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
- "Cell \u001b[1;32mIn[9], line 5\u001b[0m\n\u001b[0;32m 3\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mRunning RandomizedSearchCV for \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mname\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m...\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m 4\u001b[0m random_search \u001b[38;5;241m=\u001b[39m RandomizedSearchCV(model, param_distributions\u001b[38;5;241m=\u001b[39mparam_grids[name], cv \u001b[38;5;241m=\u001b[39mkf, n_iter \u001b[38;5;241m=\u001b[39m\u001b[38;5;241m100\u001b[39m, random_state\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m42\u001b[39m, n_jobs\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m)\n\u001b[1;32m----> 5\u001b[0m random_search\u001b[38;5;241m.\u001b[39mfit(X_train_scaled, y_train)\n\u001b[0;32m 6\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mBest parameters for \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mname\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mrandom_search\u001b[38;5;241m.\u001b[39mbest_params_\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n",
- "File \u001b[1;32mc:\\Users\\sarah\\anaconda3\\Lib\\site-packages\\sklearn\\base.py:1474\u001b[0m, in \u001b[0;36m_fit_context.<locals>.decorator.<locals>.wrapper\u001b[1;34m(estimator, *args, **kwargs)\u001b[0m\n\u001b[0;32m 1467\u001b[0m estimator\u001b[38;5;241m.\u001b[39m_validate_params()\n\u001b[0;32m 1469\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m config_context(\n\u001b[0;32m 1470\u001b[0m skip_parameter_validation\u001b[38;5;241m=\u001b[39m(\n\u001b[0;32m 1471\u001b[0m prefer_skip_nested_validation \u001b[38;5;129;01mor\u001b[39;00m global_skip_validation\n\u001b[0;32m 1472\u001b[0m )\n\u001b[0;32m 1473\u001b[0m ):\n\u001b[1;32m-> 1474\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m fit_method(estimator, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
- "File \u001b[1;32mc:\\Users\\sarah\\anaconda3\\Lib\\site-packages\\sklearn\\model_selection\\_search.py:970\u001b[0m, in \u001b[0;36mBaseSearchCV.fit\u001b[1;34m(self, X, y, **params)\u001b[0m\n\u001b[0;32m 964\u001b[0m results \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_format_results(\n\u001b[0;32m 965\u001b[0m all_candidate_params, n_splits, all_out, all_more_results\n\u001b[0;32m 966\u001b[0m )\n\u001b[0;32m 968\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m results\n\u001b[1;32m--> 970\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_run_search(evaluate_candidates)\n\u001b[0;32m 972\u001b[0m \u001b[38;5;66;03m# multimetric is determined here because in the case of a callable\u001b[39;00m\n\u001b[0;32m 973\u001b[0m \u001b[38;5;66;03m# self.scoring the return type is only known after calling\u001b[39;00m\n\u001b[0;32m 974\u001b[0m first_test_score \u001b[38;5;241m=\u001b[39m all_out[\u001b[38;5;241m0\u001b[39m][\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtest_scores\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n",
- "File \u001b[1;32mc:\\Users\\sarah\\anaconda3\\Lib\\site-packages\\sklearn\\model_selection\\_search.py:1914\u001b[0m, in \u001b[0;36mRandomizedSearchCV._run_search\u001b[1;34m(self, evaluate_candidates)\u001b[0m\n\u001b[0;32m 1912\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_run_search\u001b[39m(\u001b[38;5;28mself\u001b[39m, evaluate_candidates):\n\u001b[0;32m 1913\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Search n_iter candidates from param_distributions\"\"\"\u001b[39;00m\n\u001b[1;32m-> 1914\u001b[0m evaluate_candidates(\n\u001b[0;32m 1915\u001b[0m ParameterSampler(\n\u001b[0;32m 1916\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mparam_distributions, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mn_iter, random_state\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mrandom_state\n\u001b[0;32m 1917\u001b[0m )\n\u001b[0;32m 1918\u001b[0m )\n",
- "File \u001b[1;32mc:\\Users\\sarah\\anaconda3\\Lib\\site-packages\\sklearn\\model_selection\\_search.py:916\u001b[0m, in \u001b[0;36mBaseSearchCV.fit.<locals>.evaluate_candidates\u001b[1;34m(candidate_params, cv, more_results)\u001b[0m\n\u001b[0;32m 908\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mverbose \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[0;32m 909\u001b[0m \u001b[38;5;28mprint\u001b[39m(\n\u001b[0;32m 910\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFitting \u001b[39m\u001b[38;5;132;01m{0}\u001b[39;00m\u001b[38;5;124m folds for each of \u001b[39m\u001b[38;5;132;01m{1}\u001b[39;00m\u001b[38;5;124m candidates,\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 911\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m totalling \u001b[39m\u001b[38;5;132;01m{2}\u001b[39;00m\u001b[38;5;124m fits\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;241m.\u001b[39mformat(\n\u001b[0;32m 912\u001b[0m n_splits, n_candidates, n_candidates \u001b[38;5;241m*\u001b[39m n_splits\n\u001b[0;32m 913\u001b[0m )\n\u001b[0;32m 914\u001b[0m )\n\u001b[1;32m--> 916\u001b[0m out \u001b[38;5;241m=\u001b[39m parallel(\n\u001b[0;32m 917\u001b[0m delayed(_fit_and_score)(\n\u001b[0;32m 918\u001b[0m clone(base_estimator),\n\u001b[0;32m 919\u001b[0m X,\n\u001b[0;32m 920\u001b[0m y,\n\u001b[0;32m 921\u001b[0m train\u001b[38;5;241m=\u001b[39mtrain,\n\u001b[0;32m 922\u001b[0m test\u001b[38;5;241m=\u001b[39mtest,\n\u001b[0;32m 923\u001b[0m parameters\u001b[38;5;241m=\u001b[39mparameters,\n\u001b[0;32m 924\u001b[0m split_progress\u001b[38;5;241m=\u001b[39m(split_idx, n_splits),\n\u001b[0;32m 925\u001b[0m candidate_progress\u001b[38;5;241m=\u001b[39m(cand_idx, n_candidates),\n\u001b[0;32m 926\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mfit_and_score_kwargs,\n\u001b[0;32m 927\u001b[0m )\n\u001b[0;32m 928\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m (cand_idx, parameters), (split_idx, (train, test)) \u001b[38;5;129;01min\u001b[39;00m product(\n\u001b[0;32m 929\u001b[0m \u001b[38;5;28menumerate\u001b[39m(candidate_params),\n\u001b[0;32m 930\u001b[0m \u001b[38;5;28menumerate\u001b[39m(cv\u001b[38;5;241m.\u001b[39msplit(X, y, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mrouted_params\u001b[38;5;241m.\u001b[39msplitter\u001b[38;5;241m.\u001b[39msplit)),\n\u001b[0;32m 931\u001b[0m )\n\u001b[0;32m 932\u001b[0m )\n\u001b[0;32m 934\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(out) \u001b[38;5;241m<\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[0;32m 935\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[0;32m 936\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mNo fits were performed. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 937\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mWas the CV iterator empty? \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 938\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mWere there no candidates?\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m 939\u001b[0m )\n",
- "File \u001b[1;32mc:\\Users\\sarah\\anaconda3\\Lib\\site-packages\\sklearn\\utils\\parallel.py:67\u001b[0m, in \u001b[0;36mParallel.__call__\u001b[1;34m(self, iterable)\u001b[0m\n\u001b[0;32m 62\u001b[0m config \u001b[38;5;241m=\u001b[39m get_config()\n\u001b[0;32m 63\u001b[0m iterable_with_config \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m 64\u001b[0m (_with_config(delayed_func, config), args, kwargs)\n\u001b[0;32m 65\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m delayed_func, args, kwargs \u001b[38;5;129;01min\u001b[39;00m iterable\n\u001b[0;32m 66\u001b[0m )\n\u001b[1;32m---> 67\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39m\u001b[38;5;21m__call__\u001b[39m(iterable_with_config)\n",
- "File \u001b[1;32mc:\\Users\\sarah\\anaconda3\\Lib\\site-packages\\joblib\\parallel.py:2007\u001b[0m, in \u001b[0;36mParallel.__call__\u001b[1;34m(self, iterable)\u001b[0m\n\u001b[0;32m 2001\u001b[0m \u001b[38;5;66;03m# The first item from the output is blank, but it makes the interpreter\u001b[39;00m\n\u001b[0;32m 2002\u001b[0m \u001b[38;5;66;03m# progress until it enters the Try/Except block of the generator and\u001b[39;00m\n\u001b[0;32m 2003\u001b[0m \u001b[38;5;66;03m# reaches the first `yield` statement. This starts the asynchronous\u001b[39;00m\n\u001b[0;32m 2004\u001b[0m \u001b[38;5;66;03m# dispatch of the tasks to the workers.\u001b[39;00m\n\u001b[0;32m 2005\u001b[0m \u001b[38;5;28mnext\u001b[39m(output)\n\u001b[1;32m-> 2007\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m output \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mreturn_generator \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mlist\u001b[39m(output)\n",
- "File \u001b[1;32mc:\\Users\\sarah\\anaconda3\\Lib\\site-packages\\joblib\\parallel.py:1650\u001b[0m, in \u001b[0;36mParallel._get_outputs\u001b[1;34m(self, iterator, pre_dispatch)\u001b[0m\n\u001b[0;32m 1647\u001b[0m \u001b[38;5;28;01myield\u001b[39;00m\n\u001b[0;32m 1649\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backend\u001b[38;5;241m.\u001b[39mretrieval_context():\n\u001b[1;32m-> 1650\u001b[0m \u001b[38;5;28;01myield from\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_retrieve()\n\u001b[0;32m 1652\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mGeneratorExit\u001b[39;00m:\n\u001b[0;32m 1653\u001b[0m \u001b[38;5;66;03m# The generator has been garbage collected before being fully\u001b[39;00m\n\u001b[0;32m 1654\u001b[0m \u001b[38;5;66;03m# consumed. This aborts the remaining tasks if possible and warn\u001b[39;00m\n\u001b[0;32m 1655\u001b[0m \u001b[38;5;66;03m# the user if necessary.\u001b[39;00m\n\u001b[0;32m 1656\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_exception \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n",
- "File \u001b[1;32mc:\\Users\\sarah\\anaconda3\\Lib\\site-packages\\joblib\\parallel.py:1762\u001b[0m, in \u001b[0;36mParallel._retrieve\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 1757\u001b[0m \u001b[38;5;66;03m# If the next job is not ready for retrieval yet, we just wait for\u001b[39;00m\n\u001b[0;32m 1758\u001b[0m \u001b[38;5;66;03m# async callbacks to progress.\u001b[39;00m\n\u001b[0;32m 1759\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m ((\u001b[38;5;28mlen\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_jobs) \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m0\u001b[39m) \u001b[38;5;129;01mor\u001b[39;00m\n\u001b[0;32m 1760\u001b[0m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_jobs[\u001b[38;5;241m0\u001b[39m]\u001b[38;5;241m.\u001b[39mget_status(\n\u001b[0;32m 1761\u001b[0m timeout\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtimeout) \u001b[38;5;241m==\u001b[39m TASK_PENDING)):\n\u001b[1;32m-> 1762\u001b[0m time\u001b[38;5;241m.\u001b[39msleep(\u001b[38;5;241m0.01\u001b[39m)\n\u001b[0;32m 1763\u001b[0m \u001b[38;5;28;01mcontinue\u001b[39;00m\n\u001b[0;32m 1765\u001b[0m \u001b[38;5;66;03m# We need to be careful: the job list can be filling up as\u001b[39;00m\n\u001b[0;32m 1766\u001b[0m \u001b[38;5;66;03m# we empty it and Python list are not thread-safe by\u001b[39;00m\n\u001b[0;32m 1767\u001b[0m \u001b[38;5;66;03m# default hence the use of the lock\u001b[39;00m\n",
- "\u001b[1;31mKeyboardInterrupt\u001b[0m: "
- ]
}
],
"source": [
--
GitLab