diff --git a/analysis.ipynb b/analysis.ipynb
index be53ecbec08df1ef8a20a2a88ae14a786d0e1563..c6c1a1c81d2d069964e6baf5a9b269e3358bbd90 100644
--- a/analysis.ipynb
+++ b/analysis.ipynb
@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 105,
+ "execution_count": 208,
"metadata": {},
"outputs": [],
"source": [
@@ -41,7 +41,7 @@
},
{
"cell_type": "code",
- "execution_count": 106,
+ "execution_count": 209,
"metadata": {},
"outputs": [
{
@@ -1054,7 +1054,7 @@
"[99 rows x 39 columns]"
]
},
- "execution_count": 106,
+ "execution_count": 209,
"metadata": {},
"output_type": "execute_result"
}
@@ -1069,6 +1069,7 @@
"# Drop column and set index\n",
"data_df.set_index(\"Stadtteil\", inplace=True)\n",
"\n",
+ "data2_df = data_df\n",
"data_df"
]
},
@@ -1081,7 +1082,7 @@
},
{
"cell_type": "code",
- "execution_count": 107,
+ "execution_count": 210,
"metadata": {},
"outputs": [],
"source": [
@@ -1115,7 +1116,7 @@
},
{
"cell_type": "code",
- "execution_count": 108,
+ "execution_count": 211,
"metadata": {},
"outputs": [
{
@@ -1415,7 +1416,7 @@
"max 4.000000 7.208333 0.277313 "
]
},
- "execution_count": 108,
+ "execution_count": 211,
"metadata": {},
"output_type": "execute_result"
}
@@ -1426,7 +1427,7 @@
},
{
"cell_type": "code",
- "execution_count": 109,
+ "execution_count": 212,
"metadata": {},
"outputs": [
{
@@ -1498,7 +1499,7 @@
},
{
"cell_type": "code",
- "execution_count": 110,
+ "execution_count": 213,
"metadata": {},
"outputs": [
{
@@ -1579,7 +1580,7 @@
},
{
"cell_type": "code",
- "execution_count": 111,
+ "execution_count": 214,
"metadata": {},
"outputs": [
{
@@ -1654,7 +1655,7 @@
},
{
"cell_type": "code",
- "execution_count": 112,
+ "execution_count": 215,
"metadata": {},
"outputs": [
{
@@ -1992,7 +1993,7 @@
},
{
"cell_type": "code",
- "execution_count": 113,
+ "execution_count": 216,
"metadata": {},
"outputs": [
{
@@ -2011,7 +2012,7 @@
"Text(0.5, 1.0, 'Density Plot of Art_Score ')"
]
},
- "execution_count": 113,
+ "execution_count": 216,
"metadata": {},
"output_type": "execute_result"
},
@@ -2036,7 +2037,7 @@
},
{
"cell_type": "code",
- "execution_count": 114,
+ "execution_count": 217,
"metadata": {},
"outputs": [
{
@@ -2070,7 +2071,7 @@
},
{
"cell_type": "code",
- "execution_count": 115,
+ "execution_count": 218,
"metadata": {},
"outputs": [
{
@@ -2104,7 +2105,7 @@
},
{
"cell_type": "code",
- "execution_count": 116,
+ "execution_count": 219,
"metadata": {},
"outputs": [
{
@@ -2152,7 +2153,7 @@
},
{
"cell_type": "code",
- "execution_count": 117,
+ "execution_count": 220,
"metadata": {},
"outputs": [
{
@@ -2226,7 +2227,7 @@
},
{
"cell_type": "code",
- "execution_count": 118,
+ "execution_count": 221,
"metadata": {},
"outputs": [
{
@@ -2244,7 +2245,13 @@
"/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
" if is_sparse(pd_dtype):\n",
"/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
- " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
"/var/folders/lj/q1ndb2493275c2y0vzyplnk00000gn/T/ipykernel_25655/2287162676.py:19: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
@@ -2292,7 +2299,7 @@
},
{
"cell_type": "code",
- "execution_count": 119,
+ "execution_count": 222,
"metadata": {},
"outputs": [
{
@@ -2333,7 +2340,7 @@
},
{
"cell_type": "code",
- "execution_count": 120,
+ "execution_count": 223,
"metadata": {},
"outputs": [
{
@@ -2428,12 +2435,12 @@
" <td>4</td>\n",
" <td>2.565476</td>\n",
" <td>0.000000</td>\n",
- " <td>2</td>\n",
+ " <td>1</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
- " <td>1</td>\n",
" <td>0</td>\n",
- " <td>1</td>\n",
+ " <td>4</td>\n",
+ " <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>HafenCity</th>\n",
@@ -2456,10 +2463,10 @@
" <td>0.005758</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
- " <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
- " <td>1</td>\n",
+ " <td>4</td>\n",
+ " <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Neustadt</th>\n",
@@ -2480,12 +2487,12 @@
" <td>4</td>\n",
" <td>2.702381</td>\n",
" <td>0.001174</td>\n",
- " <td>2</td>\n",
+ " <td>1</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
- " <td>1</td>\n",
" <td>0</td>\n",
- " <td>1</td>\n",
+ " <td>4</td>\n",
+ " <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>St. Pauli</th>\n",
@@ -2506,12 +2513,12 @@
" <td>2</td>\n",
" <td>1.851190</td>\n",
" <td>0.009631</td>\n",
- " <td>2</td>\n",
+ " <td>1</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
- " <td>1</td>\n",
" <td>0</td>\n",
- " <td>1</td>\n",
+ " <td>4</td>\n",
+ " <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>St. Georg</th>\n",
@@ -2532,12 +2539,12 @@
" <td>4</td>\n",
" <td>2.523810</td>\n",
" <td>0.008493</td>\n",
- " <td>2</td>\n",
+ " <td>1</td>\n",
" <td>0</td>\n",
" <td>2</td>\n",
- " <td>1</td>\n",
" <td>0</td>\n",
- " <td>1</td>\n",
+ " <td>4</td>\n",
+ " <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
@@ -2586,10 +2593,10 @@
" <td>0.104116</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
+ " <td>3</td>\n",
+ " <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Neugraben-Fischbek</th>\n",
@@ -2610,12 +2617,12 @@
" <td>0</td>\n",
" <td>1.857143</td>\n",
" <td>0.130211</td>\n",
+ " <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
+ " <td>3</td>\n",
" <td>1</td>\n",
- " <td>2</td>\n",
- " <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Francop</th>\n",
@@ -2636,12 +2643,12 @@
" <td>0</td>\n",
" <td>0.000000</td>\n",
" <td>0.114626</td>\n",
- " <td>0</td>\n",
+ " <td>2</td>\n",
+ " <td>1</td>\n",
" <td>1</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
+ " <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Neuenfelde</th>\n",
@@ -2664,10 +2671,10 @@
" <td>0.162791</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
+ " <td>3</td>\n",
+ " <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>Cranz</th>\n",
@@ -2688,12 +2695,12 @@
" <td>0</td>\n",
" <td>0.000000</td>\n",
" <td>0.200686</td>\n",
- " <td>0</td>\n",
+ " <td>2</td>\n",
+ " <td>1</td>\n",
" <td>1</td>\n",
- " <td>0</td>\n",
- " <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
+ " <td>1</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
@@ -2857,36 +2864,36 @@
"\n",
" KMeans_5 KMeans_2 Spectral_5 Spectral_2 Agglo_5 \\\n",
"Stadtteil \n",
- "Hamburg-Altstadt 2 0 2 1 0 \n",
- "HafenCity 1 0 0 1 0 \n",
- "Neustadt 2 0 2 1 0 \n",
- "St. Pauli 2 0 2 1 0 \n",
- "St. Georg 2 0 2 1 0 \n",
+ "Hamburg-Altstadt 1 0 2 0 4 \n",
+ "HafenCity 1 0 1 0 4 \n",
+ "Neustadt 1 0 2 0 4 \n",
+ "St. Pauli 1 0 2 0 4 \n",
+ "St. Georg 1 0 2 0 4 \n",
"... ... ... ... ... ... \n",
- "Hausbruch 0 1 0 0 1 \n",
- "Neugraben-Fischbek 1 1 0 1 2 \n",
- "Francop 0 1 0 0 1 \n",
- "Neuenfelde 0 1 0 0 1 \n",
- "Cranz 0 1 0 0 1 \n",
+ "Hausbruch 0 1 1 0 3 \n",
+ "Neugraben-Fischbek 0 1 1 0 3 \n",
+ "Francop 2 1 1 1 0 \n",
+ "Neuenfelde 0 1 1 0 3 \n",
+ "Cranz 2 1 1 1 0 \n",
"\n",
" Agglo_2 \n",
"Stadtteil \n",
- "Hamburg-Altstadt 1 \n",
- "HafenCity 1 \n",
- "Neustadt 1 \n",
- "St. Pauli 1 \n",
- "St. Georg 1 \n",
+ "Hamburg-Altstadt 0 \n",
+ "HafenCity 0 \n",
+ "Neustadt 0 \n",
+ "St. Pauli 0 \n",
+ "St. Georg 0 \n",
"... ... \n",
- "Hausbruch 0 \n",
- "Neugraben-Fischbek 0 \n",
- "Francop 0 \n",
- "Neuenfelde 0 \n",
- "Cranz 0 \n",
+ "Hausbruch 1 \n",
+ "Neugraben-Fischbek 1 \n",
+ "Francop 1 \n",
+ "Neuenfelde 1 \n",
+ "Cranz 1 \n",
"\n",
"[99 rows x 23 columns]"
]
},
- "execution_count": 120,
+ "execution_count": 223,
"metadata": {},
"output_type": "execute_result"
}
@@ -2897,7 +2904,7 @@
},
{
"cell_type": "code",
- "execution_count": 121,
+ "execution_count": 224,
"metadata": {},
"outputs": [],
"source": [
@@ -2929,7 +2936,7 @@
},
{
"cell_type": "code",
- "execution_count": 122,
+ "execution_count": 225,
"metadata": {},
"outputs": [
{
@@ -2946,7 +2953,7 @@
" dtype='object')"
]
},
- "execution_count": 122,
+ "execution_count": 225,
"metadata": {},
"output_type": "execute_result"
}
@@ -2972,7 +2979,7 @@
},
{
"cell_type": "code",
- "execution_count": 123,
+ "execution_count": 226,
"metadata": {},
"outputs": [
{
@@ -3069,7 +3076,7 @@
},
{
"cell_type": "code",
- "execution_count": 124,
+ "execution_count": 227,
"metadata": {},
"outputs": [
{
@@ -3118,31 +3125,9 @@
},
{
"cell_type": "code",
- "execution_count": 125,
+ "execution_count": 228,
"metadata": {},
"outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Test Data Evaluation:\n",
- "R² Score: -0.003523284549393324\n",
- "Mean Absolute Error (MAE): 0.9425595238095239\n",
- "Mean Squared Error (MSE): 1.3866904053287983\n",
- "Root Mean Squared Error (RMSE): 1.1775781949954738\n",
- " Coefficient\n",
- "Anteil Kinder und Jugendlicher unter 18 Jahren ... 0.052760\n",
- "Anteil älterer Einwohner: innen über 64 Jahren ... 0.008694\n",
- "Einwohner: innen je km² 0.310062\n",
- "Gesamtbetrag Einkünfte Median - [€] 0.124880\n",
- "Anteil der Sozial-wohnungen an allen Wohnungen 0.026643\n",
- "Durch-schnittliche Wohnfläche je Einwohner:in i... 0.027564\n",
- "Durch-schnittliche Anzahl der Personen je Haushalt 0.080884\n",
- "organic_restaurants_count 0.000000\n",
- "vegan_restaurants_count 0.243526\n",
- "distance_rathaus 0.124988\n"
- ]
- },
{
"name": "stderr",
"output_type": "stream",
@@ -3176,7 +3161,35 @@
"/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
" if is_sparse(pd_dtype):\n",
"/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
- " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n"
+ ]
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Test Data Evaluation:\n",
+ "R² Score: -0.4464530491116274\n",
+ "Mean Absolute Error (MAE): 1.0651785714285713\n",
+ "Mean Squared Error (MSE): 1.9987404336734695\n",
+ "Root Mean Squared Error (RMSE): 1.413768168291205\n",
+ " Coefficient\n",
+ "Anteil Kinder und Jugendlicher unter 18 Jahren ... 0.091625\n",
+ "Anteil älterer Einwohner: innen über 64 Jahren ... 0.066265\n",
+ "Einwohner: innen je km² 0.310324\n",
+ "Gesamtbetrag Einkünfte Median - [€] 0.023681\n",
+ "Anteil der Sozial-wohnungen an allen Wohnungen 0.030918\n",
+ "Durch-schnittliche Wohnfläche je Einwohner:in i... 0.126750\n",
+ "Durch-schnittliche Anzahl der Personen je Haushalt 0.041658\n",
+ "organic_restaurants_count 0.000007\n",
+ "vegan_restaurants_count 0.243526\n",
+ "distance_rathaus 0.065245\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
"/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
" if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
"/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
@@ -3247,7 +3260,7 @@
},
{
"cell_type": "code",
- "execution_count": 126,
+ "execution_count": 229,
"metadata": {},
"outputs": [
{
@@ -3350,7 +3363,7 @@
},
{
"cell_type": "code",
- "execution_count": 127,
+ "execution_count": 230,
"metadata": {},
"outputs": [
{
@@ -3457,7 +3470,7 @@
},
{
"cell_type": "code",
- "execution_count": 128,
+ "execution_count": 231,
"metadata": {},
"outputs": [
{
@@ -3474,7 +3487,7 @@
" dtype='object')"
]
},
- "execution_count": 128,
+ "execution_count": 231,
"metadata": {},
"output_type": "execute_result"
}
@@ -3490,7 +3503,7 @@
},
{
"cell_type": "code",
- "execution_count": 129,
+ "execution_count": 232,
"metadata": {},
"outputs": [
{
@@ -3894,7 +3907,13 @@
"/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
" if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
"/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/neural_network/_multilayer_perceptron.py:1623: 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",
+ " y = column_or_1d(y, warn=True)\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
"/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/neural_network/_multilayer_perceptron.py:686: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (10) reached and the optimization hasn't converged yet.\n",
" warnings.warn(\n",
"/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
@@ -8890,7 +8909,7 @@
},
{
"cell_type": "code",
- "execution_count": 130,
+ "execution_count": 233,
"metadata": {},
"outputs": [
{
@@ -8984,7 +9003,7 @@
"max 36.786614 6.065197 6.065197"
]
},
- "execution_count": 130,
+ "execution_count": 233,
"metadata": {},
"output_type": "execute_result"
}
@@ -8996,6 +9015,159 @@
"loo_mlp_results.describe()"
]
},
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### MLP with all Variables"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 234,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Index(['Anzahl der Einwohner: innen',\n",
+ " 'Anzahl der Kinder und Jugendlichen unter 18 Jahren',\n",
+ " 'Anteil Kinder und Jugendlicher unter 18 Jahren an der Gesamt-bevölkerung',\n",
+ " 'Anzahl älterer Einwohner: innen über 64 Jahren',\n",
+ " 'Anteil älterer Einwohner: innen über 64 Jahren an der Gesamt-bevölkerung',\n",
+ " 'Anzahl der Haushalte',\n",
+ " 'Durch-schnittliche Anzahl der Personen je Haushalt', 'Fläche in km²',\n",
+ " 'Einwohner: innen je km²', 'Anzahl der Wohngebäude',\n",
+ " 'Anzahl der Wohnungen', 'Durch-schnittliche Wohnungs-größe in m²',\n",
+ " 'Durch-schnittliche Wohnfläche je Einwohner:in in m²',\n",
+ " 'Anzahl der Sozial-wohnungen',\n",
+ " 'Anteil der Sozial-wohnungen an allen Wohnungen',\n",
+ " 'Anzahl der Wohnungen in Ein- und Zweifamilien-häusern',\n",
+ " 'Anteil der Wohnungen in Ein- und Zweifamilien-häusern an allen Wohnungen',\n",
+ " 'Anzahl der Einpersonen-haushalte',\n",
+ " 'Anteil der Haushalte, in denen nur eine Person lebt, an allen Haushalten',\n",
+ " 'Gesamtbetrag der Einkünfte - [Steuerpflichtig]',\n",
+ " 'Gesamtbetrag der Einkünfte - [1000€]',\n",
+ " 'Festgesetzte Einkommenssteuer/ Jahreslohnsteuer - [1000€]',\n",
+ " 'Gesamtbetrag Einkünfte Mittelwert - [€]',\n",
+ " 'Gesamtbetrag Einkünfte Median - [€]', 'organic_restaurants_count',\n",
+ " 'vegan_restaurants_count', 'distance_rathaus'],\n",
+ " dtype='object')"
+ ]
+ },
+ "execution_count": 234,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "y2 = data2_df[[\"art_score\"]]\n",
+ "X2 = data2_df.drop(['art_score','market_count', 'farms_count','greencrocers_count', 'supermarkets_count', \n",
+ "'biosupermarkets_count','all_restaurants_count', ], axis=1)\n",
+ "X2= X2.dropna(axis='columns')\n",
+ "X2.columns"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 235,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Test Data Evaluation:\n",
+ "R² Score: 0.15069178934954564\n",
+ "Mean Absolute Error (MAE): 0.7749609684397321\n",
+ "Mean Squared Error (MSE): 1.1735926460388846\n",
+ "Root Mean Squared Error (RMSE): 1.0833248109587839\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/neural_network/_multilayer_perceptron.py:1623: 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",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/neural_network/_multilayer_perceptron.py:686: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (10) reached and the optimization hasn't converged yet.\n",
+ " warnings.warn(\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n"
+ ]
+ }
+ ],
+ "source": [
+ "## ------------------- Pipeline ------------------------ ##\n",
+ "\n",
+ "# train test split\n",
+ "X_train, X_test, y_train, y_test = train_test_split(X2, y2, test_size=0.2, random_state=42)\n",
+ "\n",
+ "# Pipeline - combine models \n",
+ "pipeline = Pipeline([('scaler', StandardScaler()), ('MLP', MLPRegressor(hidden_layer_sizes=(100,), activation='relu', solver='adam', max_iter=10, random_state=42))])\n",
+ "\n",
+ "pipeline.fit(X_train, y_train)\n",
+ "\n",
+ "y_pred_test = pipeline.predict(X_test)\n",
+ "\n",
+ "r2_score_test = pipeline.score(X_test, y_test)\n",
+ "mse_test = mean_squared_error(y_test, y_pred_test)\n",
+ "mae_test = mean_absolute_error(y_test, y_pred_test)\n",
+ "rmse_test = np.sqrt(mse_test)\n",
+ "\n",
+ "print(\"Test Data Evaluation:\")\n",
+ "print(\"R² Score:\", r2_score_test)\n",
+ "print(\"Mean Absolute Error (MAE):\", mae_test)\n",
+ "print(\"Mean Squared Error (MSE):\", mse_test)\n",
+ "print(\"Root Mean Squared Error (RMSE):\", rmse_test)"
+ ]
+ },
{
"cell_type": "markdown",
"metadata": {},
@@ -9005,7 +9177,7 @@
},
{
"cell_type": "code",
- "execution_count": 131,
+ "execution_count": 236,
"metadata": {},
"outputs": [
{
@@ -9019,7 +9191,7 @@
" dtype='object')"
]
},
- "execution_count": 131,
+ "execution_count": 236,
"metadata": {},
"output_type": "execute_result"
}
@@ -9049,7 +9221,7 @@
},
{
"cell_type": "code",
- "execution_count": 132,
+ "execution_count": 237,
"metadata": {},
"outputs": [
{
@@ -9256,7 +9428,7 @@
},
{
"cell_type": "code",
- "execution_count": 133,
+ "execution_count": 238,
"metadata": {},
"outputs": [
{
@@ -9329,7 +9501,7 @@
},
{
"cell_type": "code",
- "execution_count": 134,
+ "execution_count": 239,
"metadata": {},
"outputs": [
{
@@ -9406,7 +9578,7 @@
},
{
"cell_type": "code",
- "execution_count": 135,
+ "execution_count": 240,
"metadata": {},
"outputs": [
{
@@ -9415,15 +9587,15 @@
"text": [
" precision recall f1-score support\n",
"\n",
- " 0 0.42 0.18 0.25 45\n",
- " 1 0.45 0.23 0.30 40\n",
- " 2 0.12 0.22 0.15 9\n",
- " 3 0.00 0.00 0.00 4\n",
+ " 0 0.59 0.22 0.32 45\n",
+ " 1 0.35 0.23 0.27 40\n",
+ " 2 0.05 0.11 0.06 9\n",
+ " 3 0.11 0.50 0.18 4\n",
" 4 0.00 0.00 0.00 1\n",
"\n",
- " accuracy 0.19 99\n",
- " macro avg 0.20 0.12 0.14 99\n",
- "weighted avg 0.38 0.19 0.25 99\n",
+ " accuracy 0.22 99\n",
+ " macro avg 0.22 0.21 0.17 99\n",
+ "weighted avg 0.42 0.22 0.27 99\n",
"\n"
]
},
@@ -9465,7 +9637,7 @@
},
{
"cell_type": "code",
- "execution_count": 136,
+ "execution_count": 241,
"metadata": {},
"outputs": [
{
@@ -9491,7 +9663,7 @@
},
{
"cell_type": "code",
- "execution_count": 137,
+ "execution_count": 242,
"metadata": {},
"outputs": [
{
@@ -9708,7 +9880,7 @@
},
{
"cell_type": "code",
- "execution_count": 138,
+ "execution_count": 243,
"metadata": {},
"outputs": [
{
@@ -9762,7 +9934,7 @@
},
{
"cell_type": "code",
- "execution_count": 139,
+ "execution_count": 244,
"metadata": {},
"outputs": [
{
@@ -9776,7 +9948,7 @@
" dtype='object')"
]
},
- "execution_count": 139,
+ "execution_count": 244,
"metadata": {},
"output_type": "execute_result"
}
@@ -9808,7 +9980,7 @@
},
{
"cell_type": "code",
- "execution_count": 140,
+ "execution_count": 245,
"metadata": {},
"outputs": [
{
@@ -9816,7 +9988,7 @@
"output_type": "stream",
"text": [
"Training Set Accuracy: 1.0\n",
- "Test Set Accuracy: 0.45\n",
+ "Test Set Accuracy: 0.5\n",
"\n",
"Training Set Classification Report:\n",
" precision recall f1-score support\n",
@@ -9835,15 +10007,14 @@
"Test Set Classification Report:\n",
" precision recall f1-score support\n",
"\n",
- " 0 0.70 0.78 0.74 9\n",
- " 1 0.33 0.29 0.31 7\n",
+ " 0 0.78 0.78 0.78 9\n",
+ " 1 0.38 0.43 0.40 7\n",
" 2 0.00 0.00 0.00 4\n",
- " 3 0.00 0.00 0.00 0\n",
" 4 0.00 0.00 0.00 0\n",
"\n",
- " accuracy 0.45 20\n",
- " macro avg 0.21 0.21 0.21 20\n",
- "weighted avg 0.43 0.45 0.44 20\n",
+ " accuracy 0.50 20\n",
+ " macro avg 0.29 0.30 0.29 20\n",
+ "weighted avg 0.48 0.50 0.49 20\n",
"\n",
"\n",
"Model Parameters: {'memory': None, 'steps': [('scaler', StandardScaler()), ('DTC', DecisionTreeClassifier())], 'verbose': False, 'scaler': StandardScaler(), 'DTC': DecisionTreeClassifier(), 'scaler__copy': True, 'scaler__with_mean': True, 'scaler__with_std': True, 'DTC__ccp_alpha': 0.0, 'DTC__class_weight': None, 'DTC__criterion': 'gini', 'DTC__max_depth': None, 'DTC__max_features': None, 'DTC__max_leaf_nodes': None, 'DTC__min_impurity_decrease': 0.0, 'DTC__min_samples_leaf': 1, 'DTC__min_samples_split': 2, 'DTC__min_weight_fraction_leaf': 0.0, 'DTC__random_state': None, 'DTC__splitter': 'best'}\n"
@@ -10013,7 +10184,7 @@
},
{
"cell_type": "code",
- "execution_count": 141,
+ "execution_count": 246,
"metadata": {},
"outputs": [
{
@@ -10027,7 +10198,7 @@
" dtype='object')"
]
},
- "execution_count": 141,
+ "execution_count": 246,
"metadata": {},
"output_type": "execute_result"
}
@@ -10059,9 +10230,41 @@
},
{
"cell_type": "code",
- "execution_count": 142,
+ "execution_count": 247,
"metadata": {},
"outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Training Set Accuracy: 1.0\n",
+ "Test Set Accuracy: 0.85\n",
+ "\n",
+ "Training Set Classification Report:\n",
+ " precision recall f1-score support\n",
+ "\n",
+ " 0 1.00 1.00 1.00 36\n",
+ " 1 1.00 1.00 1.00 43\n",
+ "\n",
+ " accuracy 1.00 79\n",
+ " macro avg 1.00 1.00 1.00 79\n",
+ "weighted avg 1.00 1.00 1.00 79\n",
+ "\n",
+ "\n",
+ "Test Set Classification Report:\n",
+ " precision recall f1-score support\n",
+ "\n",
+ " 0 0.88 0.78 0.82 9\n",
+ " 1 0.83 0.91 0.87 11\n",
+ "\n",
+ " accuracy 0.85 20\n",
+ " macro avg 0.85 0.84 0.85 20\n",
+ "weighted avg 0.85 0.85 0.85 20\n",
+ "\n",
+ "\n",
+ "Model Parameters: {'memory': None, 'steps': [('scaler', StandardScaler()), ('DTC', DecisionTreeClassifier())], 'verbose': False, 'scaler': StandardScaler(), 'DTC': DecisionTreeClassifier(), 'scaler__copy': True, 'scaler__with_mean': True, 'scaler__with_std': True, 'DTC__ccp_alpha': 0.0, 'DTC__class_weight': None, 'DTC__criterion': 'gini', 'DTC__max_depth': None, 'DTC__max_features': None, 'DTC__max_leaf_nodes': None, 'DTC__min_impurity_decrease': 0.0, 'DTC__min_samples_leaf': 1, 'DTC__min_samples_split': 2, 'DTC__min_weight_fraction_leaf': 0.0, 'DTC__random_state': None, 'DTC__splitter': 'best'}\n"
+ ]
+ },
{
"name": "stderr",
"output_type": "stream",
@@ -10181,38 +10384,6 @@
"/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
" if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n"
]
- },
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Training Set Accuracy: 1.0\n",
- "Test Set Accuracy: 0.85\n",
- "\n",
- "Training Set Classification Report:\n",
- " precision recall f1-score support\n",
- "\n",
- " 0 1.00 1.00 1.00 36\n",
- " 1 1.00 1.00 1.00 43\n",
- "\n",
- " accuracy 1.00 79\n",
- " macro avg 1.00 1.00 1.00 79\n",
- "weighted avg 1.00 1.00 1.00 79\n",
- "\n",
- "\n",
- "Test Set Classification Report:\n",
- " precision recall f1-score support\n",
- "\n",
- " 0 0.88 0.78 0.82 9\n",
- " 1 0.83 0.91 0.87 11\n",
- "\n",
- " accuracy 0.85 20\n",
- " macro avg 0.85 0.84 0.85 20\n",
- "weighted avg 0.85 0.85 0.85 20\n",
- "\n",
- "\n",
- "Model Parameters: {'memory': None, 'steps': [('scaler', StandardScaler()), ('DTC', DecisionTreeClassifier())], 'verbose': False, 'scaler': StandardScaler(), 'DTC': DecisionTreeClassifier(), 'scaler__copy': True, 'scaler__with_mean': True, 'scaler__with_std': True, 'DTC__ccp_alpha': 0.0, 'DTC__class_weight': None, 'DTC__criterion': 'gini', 'DTC__max_depth': None, 'DTC__max_features': None, 'DTC__max_leaf_nodes': None, 'DTC__min_impurity_decrease': 0.0, 'DTC__min_samples_leaf': 1, 'DTC__min_samples_split': 2, 'DTC__min_weight_fraction_leaf': 0.0, 'DTC__random_state': None, 'DTC__splitter': 'best'}\n"
- ]
}
],
"source": [
@@ -10259,7 +10430,7 @@
},
{
"cell_type": "code",
- "execution_count": 143,
+ "execution_count": 248,
"metadata": {},
"outputs": [
{
@@ -10273,7 +10444,7 @@
" dtype='object')"
]
},
- "execution_count": 143,
+ "execution_count": 248,
"metadata": {},
"output_type": "execute_result"
}
@@ -10286,16 +10457,33 @@
" 'Agglo_5', 'Agglo_2', 'market_yes_no'], axis=1)\n",
"\n",
"\n",
- "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\n",
"\n",
"X.columns"
]
},
{
"cell_type": "code",
- "execution_count": 144,
+ "execution_count": 249,
"metadata": {},
"outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n"
+ ]
+ },
{
"name": "stdout",
"output_type": "stream",
@@ -10336,18 +10524,6 @@
"name": "stderr",
"output_type": "stream",
"text": [
- "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
- " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
- "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
- " if is_sparse(pd_dtype):\n",
- "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
- " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
- "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
- " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
- "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
- " if is_sparse(pd_dtype):\n",
- "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
- " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
"/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/neural_network/_multilayer_perceptron.py:686: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (300) reached and the optimization hasn't converged yet.\n",
" warnings.warn(\n",
"/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
@@ -10479,7 +10655,7 @@
},
{
"cell_type": "code",
- "execution_count": 145,
+ "execution_count": 250,
"metadata": {},
"outputs": [],
"source": [
@@ -10495,9 +10671,27 @@
},
{
"cell_type": "code",
- "execution_count": 146,
+ "execution_count": 251,
"metadata": {},
"outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n"
+ ]
+ },
{
"name": "stdout",
"output_type": "stream",
@@ -10534,18 +10728,6 @@
"name": "stderr",
"output_type": "stream",
"text": [
- "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
- " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
- "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
- " if is_sparse(pd_dtype):\n",
- "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
- " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
- "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
- " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
- "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
- " if is_sparse(pd_dtype):\n",
- "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
- " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
"/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/neural_network/_multilayer_perceptron.py:686: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (300) reached and the optimization hasn't converged yet.\n",
" warnings.warn(\n",
"/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
@@ -10671,7 +10853,7 @@
},
{
"cell_type": "code",
- "execution_count": 147,
+ "execution_count": 252,
"metadata": {},
"outputs": [
{
@@ -19051,6 +19233,235 @@
"print(f\"Average Recall: {average_recall}\")\n",
"print(f\"Average F1 Score: {average_f1_score}\")\n"
]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### MLP classifier all variables"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 253,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "Index(['Anzahl der Einwohner: innen',\n",
+ " 'Anzahl der Kinder und Jugendlichen unter 18 Jahren',\n",
+ " 'Anzahl älterer Einwohner: innen über 64 Jahren',\n",
+ " 'Anzahl der Haushalte', 'Fläche in km²', 'Einwohner: innen je km²',\n",
+ " 'Anzahl der Wohngebäude', 'Anzahl der Wohnungen',\n",
+ " 'Durch-schnittliche Wohnungs-größe in m²',\n",
+ " 'Anzahl der Sozial-wohnungen',\n",
+ " 'Anteil der Sozial-wohnungen an allen Wohnungen',\n",
+ " 'Anzahl der Wohnungen in Ein- und Zweifamilien-häusern',\n",
+ " 'Anteil der Wohnungen in Ein- und Zweifamilien-häusern an allen Wohnungen',\n",
+ " 'Anzahl der Einpersonen-haushalte',\n",
+ " 'Anteil der Haushalte, in denen nur eine Person lebt, an allen Haushalten',\n",
+ " 'Gesamtbetrag der Einkünfte - [Steuerpflichtig]',\n",
+ " 'Gesamtbetrag der Einkünfte - [1000€]',\n",
+ " 'Festgesetzte Einkommenssteuer/ Jahreslohnsteuer - [1000€]',\n",
+ " 'Gesamtbetrag Einkünfte Mittelwert - [€]',\n",
+ " 'Gesamtbetrag Einkünfte Median - [€]', 'greencrocers_count',\n",
+ " 'supermarkets_count', 'biosupermarkets_count', 'all_restaurants_count',\n",
+ " 'organic_restaurants_count', 'vegan_restaurants_count',\n",
+ " 'distance_rathaus'],\n",
+ " dtype='object')"
+ ]
+ },
+ "execution_count": 253,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "y3 = data_df[[\"market_yes_no\"]]\n",
+ "\n",
+ "X3 = data2_df.drop(['Anteil Kinder und Jugendlicher unter 18 Jahren an der Gesamt-bevölkerung',\n",
+ " 'Anteil älterer Einwohner: innen über 64 Jahren an der Gesamt-bevölkerung','market_count', 'Durch-schnittliche Wohnfläche je Einwohner:in in m²',\n",
+ " 'Durch-schnittliche Anzahl der Personen je Haushalt', 'art_score', 'farms_count'], axis=1)\n",
+ "X3 = X3.dropna(axis=1)\n",
+ "X3.columns\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 254,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Training Set Accuracy: 1.0\n",
+ "Test Set Accuracy: 0.7\n",
+ "\n",
+ "Training Set Classification Report:\n",
+ " precision recall f1-score support\n",
+ "\n",
+ " 0 1.00 1.00 1.00 36\n",
+ " 1 1.00 1.00 1.00 43\n",
+ "\n",
+ " accuracy 1.00 79\n",
+ " macro avg 1.00 1.00 1.00 79\n",
+ "weighted avg 1.00 1.00 1.00 79\n",
+ "\n",
+ "\n",
+ "Test Set Classification Report:\n",
+ " precision recall f1-score support\n",
+ "\n",
+ " 0 0.71 0.56 0.63 9\n",
+ " 1 0.69 0.82 0.75 11\n",
+ "\n",
+ " accuracy 0.70 20\n",
+ " macro avg 0.70 0.69 0.69 20\n",
+ "weighted avg 0.70 0.70 0.69 20\n",
+ "\n",
+ "\n",
+ "Model Parameters: {'memory': None, 'steps': [('scaler', StandardScaler()), ('MLP', MLPClassifier(max_iter=300, random_state=42))], 'verbose': False, 'scaler': StandardScaler(), 'MLP': MLPClassifier(max_iter=300, random_state=42), 'scaler__copy': True, 'scaler__with_mean': True, 'scaler__with_std': True, 'MLP__activation': 'relu', 'MLP__alpha': 0.0001, 'MLP__batch_size': 'auto', 'MLP__beta_1': 0.9, 'MLP__beta_2': 0.999, 'MLP__early_stopping': False, 'MLP__epsilon': 1e-08, 'MLP__hidden_layer_sizes': (100,), 'MLP__learning_rate': 'constant', 'MLP__learning_rate_init': 0.001, 'MLP__max_fun': 15000, 'MLP__max_iter': 300, 'MLP__momentum': 0.9, 'MLP__n_iter_no_change': 10, 'MLP__nesterovs_momentum': True, 'MLP__power_t': 0.5, 'MLP__random_state': 42, 'MLP__shuffle': True, 'MLP__solver': 'adam', 'MLP__tol': 0.0001, 'MLP__validation_fraction': 0.1, 'MLP__verbose': False, 'MLP__warm_start': False}\n"
+ ]
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/neural_network/_multilayer_perceptron.py:686: ConvergenceWarning: Stochastic Optimizer: Maximum iterations (300) reached and the optimization hasn't converged yet.\n",
+ " warnings.warn(\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:767: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if not hasattr(array, \"sparse\") and array.dtypes.apply(is_sparse).any():\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:605: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype):\n",
+ "/Users/ferdinand/anaconda3/lib/python3.11/site-packages/sklearn/utils/validation.py:614: FutureWarning: is_sparse is deprecated and will be removed in a future version. Check `isinstance(dtype, pd.SparseDtype)` instead.\n",
+ " if is_sparse(pd_dtype) or not is_extension_array_dtype(pd_dtype):\n"
+ ]
+ }
+ ],
+ "source": [
+ "\n",
+ "# Splitting data into training and test sets\n",
+ "X_train, X_test, y_train, y_test = train_test_split(X3, y3, test_size=0.2, random_state=42)\n",
+ "\n",
+ "# Setting up the pipeline with MLPClassifier\n",
+ "pipeline = Pipeline([\n",
+ " ('scaler', StandardScaler()), # Feature scaling is especially important for neural networks\n",
+ " ('MLP', MLPClassifier(hidden_layer_sizes=(100,), activation='relu', solver='adam', max_iter=300, random_state=42))\n",
+ "])\n",
+ "\n",
+ "# Fitting the pipeline to the training data\n",
+ "pipeline.fit(X_train, y_train.values.ravel())\n",
+ "\n",
+ "# Making predictions on both the training and test sets\n",
+ "y_pred_train = pipeline.predict(X_train)\n",
+ "y_pred_test = pipeline.predict(X_test)\n",
+ "\n",
+ "# Calculating and printing accuracy for both sets\n",
+ "accuracy_train = accuracy_score(y_train, y_pred_train)\n",
+ "print(\"Training Set Accuracy:\", accuracy_train)\n",
+ "\n",
+ "accuracy_test = accuracy_score(y_test, y_pred_test)\n",
+ "print(\"Test Set Accuracy:\", accuracy_test)\n",
+ "\n",
+ "# Generating and printing classification reports for both sets\n",
+ "print(\"\\nTraining Set Classification Report:\\n\", classification_report(y_train, y_pred_train))\n",
+ "print(\"\\nTest Set Classification Report:\\n\", classification_report(y_test, y_pred_test))\n",
+ "\n",
+ "# Getting and printing the pipeline's parameters\n",
+ "params = pipeline.get_params()\n",
+ "print(\"\\nModel Parameters:\", params)"
+ ]
}
],
"metadata": {