lars/FYSSTK-Project2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Run ruff

Browse Source
This commit is contained in:
Lars Bogner
2025-11-05 08:43:18 +01:00
parent 6466f07935
commit e6f4a7369f
11 changed files with 314 additions and 128 deletions
Download Patch File Download Diff File Expand all files Collapse all files
notebooks/11_regression-usecase.ipynb
+45 -13
View File
@@ -24,27 +24,50 @@
"data = load_breast_cancer()\n",
"\n",
"\n",
"feature_names = [n for n in data.feature_names if 'radius' in n or 'area' in n]\n",
"feature_names = [n for n in data.feature_names if \"radius\" in n or \"area\" in n]\n",
"\n",
"X = data.data[:, [data.feature_names.tolist().index(n) for n in feature_names]]\n",
"X = StandardScaler().fit_transform(X)\n",
"y = data.data[:, [data.feature_names.tolist().index(n) for n in data.feature_names if n not in feature_names]]\n",
"y = data.data[\n",
" :,\n",
" [\n",
" data.feature_names.tolist().index(n)\n",
" for n in data.feature_names\n",
" if n not in feature_names\n",
" ],\n",
"]\n",
"y = StandardScaler().fit_transform(y)\n",
"feature_dim = X.shape[1]\n",
"target_dim = y.shape[1]\n",
"\n",
"def get_regression_model(n_hidden_layers: int, n_neurons: int, activation: type=LeakyReLU, regularization_strength: float = 1e-3) -> list[Layer]:\n",
"\n",
"def get_regression_model(\n",
" n_hidden_layers: int,\n",
" n_neurons: int,\n",
" activation: type = LeakyReLU,\n",
" regularization_strength: float = 1e-3,\n",
") -> list[Layer]:\n",
" layers = []\n",
" layers.append(Layer(feature_dim, n_neurons, activation_function=activation()))\n",
" for _ in range(n_hidden_layers - 1):\n",
" layers.append(Layer(n_neurons, n_neurons, activation_function=activation()))\n",
" layers.append(Layer(n_neurons, target_dim, activation_function=Linear()))\n",
" for layer in layers:\n",
" layer.regularization = Regularization(regularization_strength, 'l2')\n",
" layer.regularization = Regularization(regularization_strength, \"l2\")\n",
" return layers\n",
"\n",
"\n",
"def get_model():\n",
" return FFNN(get_regression_model(n_hidden_layers=2, n_neurons=32, activation=LeakyReLU, regularization_strength=1e-3), AdamScheduler(epochs=10000, learning_rate=1e-2), MSELoss())"
" return FFNN(\n",
" get_regression_model(\n",
" n_hidden_layers=2,\n",
" n_neurons=32,\n",
" activation=LeakyReLU,\n",
" regularization_strength=1e-3,\n",
" ),\n",
" AdamScheduler(epochs=10000, learning_rate=1e-2),\n",
" MSELoss(),\n",
" )"
]
},
{
@@ -57,8 +80,12 @@
"crossvalidation_groups = 5\n",
"group_length = X.shape[0] // crossvalidation_groups\n",
"predictions = np.zeros_like(y)\n",
"for g in range(crossvalidation_groups + 1): # One final smaller group to catch the rest\n",
" indices = [i for i in range(X.shape[0]) if i < g*group_length or i > (g+1)*group_length]\n",
"for g in range(crossvalidation_groups + 1): # One final smaller group to catch the rest\n",
" indices = [\n",
" i\n",
" for i in range(X.shape[0])\n",
" if i < g * group_length or i > (g + 1) * group_length\n",
" ]\n",
" prediction_indices = [i for i in range(X.shape[0]) if i not in indices]\n",
" X_train = X[indices]\n",
" X_pred = X[prediction_indices]\n",
@@ -66,8 +93,7 @@
"\n",
" model = get_model()\n",
" model.fit(X_train, y_train)\n",
" predictions[prediction_indices] = model.predict(X_pred)\n",
"\n"
" predictions[prediction_indices] = model.predict(X_pred)"
]
},
{
@@ -122,15 +148,21 @@
"outputs": [],
"source": [
"combined_data = np.zeros_like(data.data)\n",
"combined_data[:,:6] = X\n",
"combined_data[:, :6] = X\n",
"combined_data[:, 6:] = predictions\n",
"\n",
"combined_df = pd.DataFrame(combined_data, columns=[*feature_names, *[n for n in data.feature_names if n not in feature_names]])\n",
"combined_df['target'] = data.target\n",
"combined_df = pd.DataFrame(\n",
" combined_data,\n",
" columns=[\n",
" *feature_names,\n",
" *[n for n in data.feature_names if n not in feature_names],\n",
" ],\n",
")\n",
"combined_df[\"target\"] = data.target\n",
"combined_df.to_csv(\"breast_cancer_regression_results.csv\", index=False)\n",
"\n",
"original_df = pd.DataFrame(data.data, columns=data.feature_names)\n",
"original_df['target'] = data.target\n",
"original_df[\"target\"] = data.target\n",
"original_df.to_csv(\"breast_cancer_original_data.csv\", index=False)"
]
},