diff --git a/entrega.ipynb b/entrega.ipynb index 4e6a7b9..d465678 100644 --- a/entrega.ipynb +++ b/entrega.ipynb @@ -16,7 +16,7 @@ }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 144, "metadata": {}, "outputs": [], "source": [ @@ -45,6 +45,7 @@ "from sklearn.gaussian_process.kernels import RBF\n", "from sklearn.metrics import RocCurveDisplay\n", "import warnings\n", + "import random\n", "warnings.filterwarnings('ignore')" ] }, @@ -57,7 +58,7 @@ }, { "cell_type": "code", - "execution_count": 2, + "execution_count": 145, "metadata": {}, "outputs": [ { @@ -82,7 +83,7 @@ }, { "cell_type": "code", - "execution_count": 3, + "execution_count": 146, "metadata": {}, "outputs": [], "source": [ @@ -102,7 +103,7 @@ }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 147, "metadata": {}, "outputs": [ { @@ -948,7 +949,7 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 148, "metadata": {}, "outputs": [ { @@ -1064,7 +1065,7 @@ }, { "cell_type": "code", - "execution_count": 6, + "execution_count": 149, "metadata": {}, "outputs": [ { @@ -1261,7 +1262,7 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 150, "metadata": {}, "outputs": [ { @@ -1685,7 +1686,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 151, "metadata": {}, "outputs": [ { @@ -2104,7 +2105,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 152, "metadata": {}, "outputs": [ { @@ -2179,7 +2180,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 153, "metadata": {}, "outputs": [ { @@ -2473,7 +2474,7 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 154, "metadata": { "scrolled": true }, @@ -2659,7 +2660,7 @@ }, { "cell_type": "code", - "execution_count": 12, + "execution_count": 155, "metadata": {}, "outputs": [ { @@ -2668,7 +2669,7 @@ "" ] }, - "execution_count": 12, + "execution_count": 155, "metadata": {}, "output_type": "execute_result" }, @@ -2689,7 +2690,7 @@ }, { "cell_type": "code", - "execution_count": 13, + "execution_count": 156, "metadata": {}, "outputs": [], "source": [ @@ -2698,7 +2699,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 157, "metadata": { "scrolled": true }, @@ -2730,7 +2731,7 @@ "dtype: int64" ] }, - "execution_count": 14, + "execution_count": 157, "metadata": {}, "output_type": "execute_result" } @@ -2748,7 +2749,7 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 158, "metadata": { "scrolled": false }, @@ -2794,7 +2795,7 @@ }, { "cell_type": "code", - "execution_count": 16, + "execution_count": 159, "metadata": {}, "outputs": [], "source": [ @@ -2817,7 +2818,7 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 160, "metadata": { "scrolled": false }, @@ -3444,7 +3445,7 @@ "[20 rows x 21 columns]" ] }, - "execution_count": 17, + "execution_count": 160, "metadata": {}, "output_type": "execute_result" } @@ -3462,7 +3463,7 @@ }, { "cell_type": "code", - "execution_count": 18, + "execution_count": 161, "metadata": { "scrolled": true }, @@ -3473,7 +3474,7 @@ "" ] }, - "execution_count": 18, + "execution_count": 161, "metadata": {}, "output_type": "execute_result" }, @@ -3503,7 +3504,7 @@ }, { "cell_type": "code", - "execution_count": 19, + "execution_count": 162, "metadata": { "scrolled": true }, @@ -3536,7 +3537,7 @@ }, { "cell_type": "code", - "execution_count": 20, + "execution_count": 163, "metadata": { "scrolled": true }, @@ -3544,10 +3545,10 @@ { "data": { "text/plain": [ - "" + "" ] }, - "execution_count": 20, + "execution_count": 163, "metadata": {}, "output_type": "execute_result" }, @@ -3587,7 +3588,7 @@ }, { "cell_type": "code", - "execution_count": 21, + "execution_count": 164, "metadata": { "scrolled": false }, @@ -3668,7 +3669,7 @@ }, { "cell_type": "code", - "execution_count": 22, + "execution_count": 165, "metadata": { "scrolled": true }, @@ -3702,7 +3703,7 @@ }, { "cell_type": "code", - "execution_count": 23, + "execution_count": 166, "metadata": { "scrolled": true }, @@ -3736,7 +3737,7 @@ }, { "cell_type": "code", - "execution_count": 24, + "execution_count": 167, "metadata": {}, "outputs": [ { @@ -3768,7 +3769,7 @@ }, { "cell_type": "code", - "execution_count": 25, + "execution_count": 168, "metadata": {}, "outputs": [ { @@ -3800,7 +3801,7 @@ }, { "cell_type": "code", - "execution_count": 26, + "execution_count": 169, "metadata": { "scrolled": true }, @@ -3819,7 +3820,7 @@ }, { "cell_type": "code", - "execution_count": 27, + "execution_count": 170, "metadata": { "scrolled": true }, @@ -4019,7 +4020,7 @@ "[5 rows x 21 columns]" ] }, - "execution_count": 27, + "execution_count": 170, "metadata": {}, "output_type": "execute_result" } @@ -4038,7 +4039,7 @@ }, { "cell_type": "code", - "execution_count": 28, + "execution_count": 171, "metadata": {}, "outputs": [ { @@ -4111,7 +4112,7 @@ "4 2022-12-21 22200468 2022" ] }, - "execution_count": 28, + "execution_count": 171, "metadata": {}, "output_type": "execute_result" } @@ -4130,7 +4131,7 @@ }, { "cell_type": "code", - "execution_count": 29, + "execution_count": 172, "metadata": {}, "outputs": [ { @@ -4321,7 +4322,7 @@ "[5 rows x 23 columns]" ] }, - "execution_count": 29, + "execution_count": 172, "metadata": {}, "output_type": "execute_result" } @@ -4340,7 +4341,7 @@ }, { "cell_type": "code", - "execution_count": 30, + "execution_count": 173, "metadata": {}, "outputs": [ { @@ -4573,7 +4574,7 @@ "[5 rows x 22 columns]" ] }, - "execution_count": 30, + "execution_count": 173, "metadata": {}, "output_type": "execute_result" } @@ -4592,7 +4593,7 @@ }, { "cell_type": "code", - "execution_count": 31, + "execution_count": 174, "metadata": { "scrolled": false }, @@ -4603,7 +4604,7 @@ "" ] }, - "execution_count": 31, + "execution_count": 174, "metadata": {}, "output_type": "execute_result" }, @@ -4633,7 +4634,7 @@ }, { "cell_type": "code", - "execution_count": 32, + "execution_count": 175, "metadata": {}, "outputs": [ { @@ -4642,7 +4643,7 @@ "" ] }, - "execution_count": 32, + "execution_count": 175, "metadata": {}, "output_type": "execute_result" }, @@ -4671,7 +4672,7 @@ }, { "cell_type": "code", - "execution_count": 33, + "execution_count": 176, "metadata": { "scrolled": true }, @@ -4682,7 +4683,7 @@ "" ] }, - "execution_count": 33, + "execution_count": 176, "metadata": {}, "output_type": "execute_result" }, @@ -4710,7 +4711,7 @@ }, { "cell_type": "code", - "execution_count": 34, + "execution_count": 177, "metadata": {}, "outputs": [], "source": [ @@ -4724,7 +4725,7 @@ }, { "cell_type": "code", - "execution_count": 35, + "execution_count": 178, "metadata": { "scrolled": true }, @@ -4931,7 +4932,7 @@ "[5 rows x 21 columns]" ] }, - "execution_count": 35, + "execution_count": 178, "metadata": {}, "output_type": "execute_result" } @@ -4949,7 +4950,7 @@ }, { "cell_type": "code", - "execution_count": 36, + "execution_count": 179, "metadata": {}, "outputs": [ { @@ -4979,7 +4980,7 @@ }, { "cell_type": "code", - "execution_count": 37, + "execution_count": 180, "metadata": { "scrolled": true }, @@ -5177,7 +5178,7 @@ "4 47.0 0 " ] }, - "execution_count": 37, + "execution_count": 180, "metadata": {}, "output_type": "execute_result" } @@ -5196,7 +5197,7 @@ }, { "cell_type": "code", - "execution_count": 38, + "execution_count": 181, "metadata": {}, "outputs": [], "source": [ @@ -5212,7 +5213,7 @@ }, { "cell_type": "code", - "execution_count": 39, + "execution_count": 182, "metadata": {}, "outputs": [ { @@ -5221,7 +5222,7 @@ "(542, 20)" ] }, - "execution_count": 39, + "execution_count": 182, "metadata": {}, "output_type": "execute_result" } @@ -5239,7 +5240,7 @@ }, { "cell_type": "code", - "execution_count": 40, + "execution_count": 183, "metadata": { "scrolled": false }, @@ -5266,7 +5267,7 @@ }, { "cell_type": "code", - "execution_count": 41, + "execution_count": 184, "metadata": {}, "outputs": [], "source": [ @@ -5283,7 +5284,7 @@ }, { "cell_type": "code", - "execution_count": 42, + "execution_count": 185, "metadata": {}, "outputs": [], "source": [ @@ -5300,7 +5301,7 @@ }, { "cell_type": "code", - "execution_count": 43, + "execution_count": 186, "metadata": { "scrolled": true }, @@ -5456,7 +5457,7 @@ }, { "cell_type": "code", - "execution_count": 44, + "execution_count": 187, "metadata": {}, "outputs": [], "source": [ @@ -5475,7 +5476,7 @@ }, { "cell_type": "code", - "execution_count": 45, + "execution_count": 188, "metadata": {}, "outputs": [], "source": [ @@ -5490,7 +5491,7 @@ }, { "cell_type": "code", - "execution_count": 46, + "execution_count": 189, "metadata": { "scrolled": true }, @@ -5621,7 +5622,7 @@ "234 0.592593 0.552632 " ] }, - "execution_count": 46, + "execution_count": 189, "metadata": {}, "output_type": "execute_result" } @@ -5639,7 +5640,7 @@ }, { "cell_type": "code", - "execution_count": 47, + "execution_count": 190, "metadata": {}, "outputs": [], "source": [ @@ -5660,7 +5661,7 @@ }, { "cell_type": "code", - "execution_count": 48, + "execution_count": 191, "metadata": {}, "outputs": [ { @@ -5707,7 +5708,7 @@ }, { "cell_type": "code", - "execution_count": 49, + "execution_count": 192, "metadata": {}, "outputs": [ { @@ -5738,7 +5739,7 @@ }, { "cell_type": "code", - "execution_count": 50, + "execution_count": 193, "metadata": {}, "outputs": [ { @@ -5747,7 +5748,7 @@ "0.7361963190184049" ] }, - "execution_count": 50, + "execution_count": 193, "metadata": {}, "output_type": "execute_result" } @@ -5767,14 +5768,14 @@ }, { "cell_type": "code", - "execution_count": 51, + "execution_count": 194, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "Accuracy: 0.7730061349693251\n" + "Accuracy: 0.7914110429447853\n" ] } ], @@ -5798,7 +5799,7 @@ }, { "cell_type": "code", - "execution_count": 52, + "execution_count": 195, "metadata": { "scrolled": true }, @@ -5809,13 +5810,13 @@ "" ] }, - "execution_count": 52, + "execution_count": 195, "metadata": {}, "output_type": "execute_result" }, { "data": { - "image/png": "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\n", + "image/png": "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\n", "text/plain": [ "
" ] @@ -5838,7 +5839,7 @@ }, { "cell_type": "code", - "execution_count": 53, + "execution_count": 196, "metadata": {}, "outputs": [ { @@ -5847,12 +5848,12 @@ "text": [ " precision recall f1-score support\n", "\n", - " 0 0.69 0.72 0.70 61\n", - " 1 0.83 0.80 0.82 102\n", + " 0 0.71 0.74 0.73 61\n", + " 1 0.84 0.82 0.83 102\n", "\n", - " accuracy 0.77 163\n", - " macro avg 0.76 0.76 0.76 163\n", - "weighted avg 0.78 0.77 0.77 163\n", + " accuracy 0.79 163\n", + " macro avg 0.78 0.78 0.78 163\n", + "weighted avg 0.79 0.79 0.79 163\n", "\n" ] } @@ -5870,7 +5871,7 @@ }, { "cell_type": "code", - "execution_count": 54, + "execution_count": 197, "metadata": { "scrolled": true }, @@ -5905,7 +5906,7 @@ }, { "cell_type": "code", - "execution_count": 55, + "execution_count": 198, "metadata": {}, "outputs": [ { @@ -5937,7 +5938,7 @@ }, { "cell_type": "code", - "execution_count": 56, + "execution_count": 199, "metadata": { "scrolled": false }, @@ -5969,7 +5970,7 @@ }, { "cell_type": "code", - "execution_count": 57, + "execution_count": 200, "metadata": { "scrolled": true }, @@ -6159,7 +6160,7 @@ }, { "cell_type": "code", - "execution_count": 58, + "execution_count": 201, "metadata": {}, "outputs": [], "source": [ @@ -6175,7 +6176,7 @@ }, { "cell_type": "code", - "execution_count": 59, + "execution_count": 202, "metadata": {}, "outputs": [ { @@ -6199,7 +6200,7 @@ }, { "cell_type": "code", - "execution_count": 60, + "execution_count": 203, "metadata": {}, "outputs": [ { @@ -6231,7 +6232,7 @@ }, { "cell_type": "code", - "execution_count": 61, + "execution_count": 204, "metadata": {}, "outputs": [], "source": [ @@ -6247,7 +6248,7 @@ }, { "cell_type": "code", - "execution_count": 62, + "execution_count": 205, "metadata": {}, "outputs": [ { @@ -6271,16 +6272,16 @@ }, { "cell_type": "code", - "execution_count": 63, + "execution_count": 206, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "" + "" ] }, - "execution_count": 63, + "execution_count": 206, "metadata": {}, "output_type": "execute_result" } @@ -6302,7 +6303,7 @@ }, { "cell_type": "code", - "execution_count": 64, + "execution_count": 207, "metadata": { "scrolled": true }, @@ -6336,7 +6337,7 @@ }, { "cell_type": "code", - "execution_count": 65, + "execution_count": 208, "metadata": {}, "outputs": [], "source": [ @@ -6359,28 +6360,28 @@ }, { "cell_type": "code", - "execution_count": 66, + "execution_count": 209, "metadata": { - "scrolled": true + "scrolled": false }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "Dummy | score = 0.558 | time = 0.000s/0.001s\n", - "KNN(3) | score = 0.742 | time = 0.001s/0.006s\n", - "RBF SVM | score = 0.755 | time = 0.003s/0.002s\n", - "Decision Tree | score = 0.730 | time = 0.002s/0.001s\n", - "Random Forest | score = 0.712 | time = 0.012s/0.002s\n", - "Neural Net | score = 0.810 | time = 0.198s/0.002s\n", + "Dummy | score = 0.479 | time = 0.000s/0.000s\n", + "KNN(3) | score = 0.742 | time = 0.001s/0.005s\n", + "RBF SVM | score = 0.755 | time = 0.004s/0.002s\n", + "Decision Tree | score = 0.724 | time = 0.002s/0.001s\n", + "Random Forest | score = 0.736 | time = 0.012s/0.002s\n", + "Neural Net | score = 0.810 | time = 0.183s/0.001s\n", "AdaBoost | score = 0.779 | time = 0.072s/0.007s\n", "Naive Bayes | score = 0.804 | time = 0.001s/0.001s\n", - "QDA | score = 0.816 | time = 0.010s/0.001s\n", + "QDA | score = 0.816 | time = 0.001s/0.001s\n", "Linear SVC | score = 0.804 | time = 0.003s/0.001s\n", "Linear SVM | score = 0.804 | time = 0.003s/0.002s\n", - "Gaussian Proc | score = 0.798 | time = 1.853s/0.004s\n", - "LogisticRegr | score = 0.816 | time = 0.006s/0.005s\n" + "Gaussian Proc | score = 0.798 | time = 1.518s/0.004s\n", + "LogisticRegr | score = 0.816 | time = 0.004s/0.006s\n" ] } ], @@ -6399,6 +6400,123 @@ " score_time = time()-start\n", " print(\"{:<15}| score = {:.3f} | time = {:,.3f}s/{:,.3f}s\".format(name, score, train_time, score_time))" ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Creamos un dataframe con valores random entre 0 y 1 para poder hacer la predicción de nuestro modelo con más precisión" + ] + }, + { + "cell_type": "code", + "execution_count": 210, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
FG_PCT_home_normFT_PCT_home_normFG3_PCT_home_normAST_home_normREB_home_normFG_PCT_away_normFT_PCT_away_normFG3_PCT_away_normAST_away_normREB_away_norm
00.9511820.9990250.3537080.743790.5504160.6416510.1383850.7912210.5354370.404599
\n", + "
" + ], + "text/plain": [ + " FG_PCT_home_norm FT_PCT_home_norm FG3_PCT_home_norm AST_home_norm \\\n", + "0 0.951182 0.999025 0.353708 0.74379 \n", + "\n", + " REB_home_norm FG_PCT_away_norm FT_PCT_away_norm FG3_PCT_away_norm \\\n", + "0 0.550416 0.641651 0.138385 0.791221 \n", + "\n", + " AST_away_norm REB_away_norm \n", + "0 0.535437 0.404599 " + ] + }, + "execution_count": 210, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "prediccion= pd.DataFrame() \n", + "\n", + "for i in variables_elegidas_norm: \n", + " prediccion[i]= [random.uniform(0,1)] \n", + "\n", + "prediccion" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "Nuestro modelo entrenado con mayor accuracy es la regresión logistica, asi que usamos el dataframe que acabamos de crear para hacer la predicción del equipo que gana y vemos el resultado" + ] + }, + { + "cell_type": "code", + "execution_count": 211, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "El resultado ha sido 1. Gana el equipo visitante\n" + ] + } + ], + "source": [ + "if logreg.predict(prediccion) == '0':\n", + " print(\"El resultado ha sido 0. Gana el equipo local\")\n", + "else:\n", + " print(\"El resultado ha sido 1. Gana el equipo visitante\")" + ] } ], "metadata": {