Upload 3 files

model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c77ee4f3b494b48b05355ea63692c68a94499890f2f8044406b6c45ea785599f
+size 13864

model.json

@@ -0,0 +1 @@
+{"class_name": "Sequential", "config": {"name": "sequential_1", "layers": [{"module": "keras.layers", "class_name": "InputLayer", "config": {"batch_input_shape": [null, 2], "dtype": "float32", "sparse": false, "ragged": false, "name": "dense_2_input"}, "registered_name": null}, {"module": "keras.layers", "class_name": "Dense", "config": {"name": "dense_2", "trainable": true, "dtype": "float32", "batch_input_shape": [null, 2], "units": 16, "activation": "relu", "use_bias": true, "kernel_initializer": {"module": "keras.initializers", "class_name": "GlorotUniform", "config": {"seed": null}, "registered_name": null}, "bias_initializer": {"module": "keras.initializers", "class_name": "Zeros", "config": {}, "registered_name": null}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "registered_name": null, "build_config": {"input_shape": [null, 2]}}, {"module": "keras.layers", "class_name": "Dense", "config": {"name": "dense_3", "trainable": true, "dtype": "float32", "units": 1, "activation": "sigmoid", "use_bias": true, "kernel_initializer": {"module": "keras.initializers", "class_name": "GlorotUniform", "config": {"seed": null}, "registered_name": null}, "bias_initializer": {"module": "keras.initializers", "class_name": "Zeros", "config": {}, "registered_name": null}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "registered_name": null, "build_config": {"input_shape": [null, 16]}}]}, "keras_version": "2.15.0", "backend": "tensorflow"}

titanic_rn_2024_2.py

@@ -0,0 +1,155 @@
+# -*- coding: utf-8 -*-
+"""Titanic_RN.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1bBTik7AiMvb-_MLAf5rTR0STa8nfJp-d
+"""
+
+# importar la libreria
+import pandas as pd
+
+"""Crear el dataframe"""
+
+training = pd.read_csv("titanic-train.csv")
+training.head(5)
+
+"""Verificar el cintenido del dataframe training"""
+
+training.info()
+
+"""Reemplazar los datos del genero a entero
+male==> 0           female==> 1
+"""
+
+training['Gender'] = training['Gender'].apply(lambda toLabel:0 if toLabel=='male' else 1)
+
+training.head(5)
+
+"""Completar los valores Nan correspondiente a la edad ( Age ) con el promedio de edades validos"""
+
+training["Age"].fillna(training["Age"].mean(),inplace=True)
+
+training.head(5)
+
+"""Verrificar los datos del dataset"""
+
+training.info()
+
+"""Indentificar los input data y los target data"""
+
+y_target = training["Survived"].values
+print(y_target)
+
+columns = ["Fare","Pclass","Gender","Age","SibSp"]
+x_input = training[list(columns)].values
+print(x_input)
+
+"""Definir la estructura de la red nuronal para el aprendizaje"""
+
+import keras
+from keras import layers
+from keras import ops
+
+model = keras.Sequential()
+model.add(layers.Dense(16,input_dim=5,activation='relu'))
+model.add(layers.Dense(16, activation="relu", name="layer1"))
+model.add(layers.Dense(1, activation='sigmoid',name="layer2"))
+
+"""Configurar los parametros de la red"""
+
+model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])
+
+"""Realizar el proceso de entrenamiento de la red neuronal"""
+
+model.fit(x_input,y_target,epochs=1000)
+
+"""Evaluar la presicion."""
+
+score = model.evaluate(x_input,y_target)
+print("\n %s: %.2f%%" % (model.metrics_names[1],score[1]*100))
+
+XX = np.array(x_input[[2]])
+print(XX)
+respuesta = model.predict(XX)
+print(respuesta.round()[0][0])
+
+y_simulado = []
+for i in range(len(y_target)):
+  y_simulado.append(model.predict(x_input[[i]]).round())
+print(y_simulado)
+
+import numpy as np
+respuesta = model.predict(np.array([[83.475, 1, 1, 35, 1,]]))
+#respuesta = model.predict(np.array([[ 7.8958, 3.0, 0.0, 29.97086721, 0.0]]))
+#respuesta = model.predict(np.array([[82.2667,1,1,23.000000,1]]))
+print(respuesta.round()[0][0])
+
+precision = 0
+for i in range(len(y_simulado)):
+  if y_target[i]==y_simulado[i].round()[0][0]:
+    precision = precision + 1
+precision = precision/float(len(y_simulado))
+print(precision)
+
+y_simulado_lista = []
+for i in range(len(y_simulado)):
+  y_simulado_lista.append(y_simulado[i].round()[0][0])
+print(y_simulado_lista)
+
+import numpy as np
+from sklearn.metrics import confusion_matrix
+Matriz_de_Confusion = confusion_matrix(y_target, y_simulado_lista)
+Matriz_de_Confusion
+"""sensibilidad"""
+#sensibilidad = (Matriz_de_Confusion[0,0])/np.sum(Matriz_de_Confusion[0,0]+ Matriz_de_Confusion[1,0])
+VP = Matriz_de_Confusion[0,0]
+FN = Matriz_de_Confusion[1,0]
+sensibilidad = VP/(VP+FN)
+sensibilidad
+
+"""especificidad"""
+#especificidad = (Matriz_de_Confusion[1,1])/np.sum(Matriz_de_Confusion[1,1]+ Matriz_de_Confusion[0,1])
+VN = Matriz_de_Confusion[1,1]
+FP = Matriz_de_Confusion[0,1]
+especificidad = VN/(VN+FP)
+especificidad
+
+from sklearn.metrics import confusion_matrix
+from matplotlib import pyplot as plt
+from sklearn.metrics import classification_report
+
+conf_mat = confusion_matrix(y_true=y_target, y_pred=y_simulado_lista)
+print('Matriz de Confusión - DATOS ORIGINALES:\n', conf_mat)
+print('Métricas de Matriz de Confusión - DATOS ORIGINALES:\n',classification_report(y_target,y_simulado_lista))
+labels = ['Class 0', 'Class 1']
+fig = plt.figure()
+ax = fig.add_subplot(111)
+cax = ax.matshow(conf_mat, cmap=plt.cm.Blues)
+fig.colorbar(cax)
+ax.set_xticklabels([''] + labels)
+ax.set_yticklabels([''] + labels)
+plt.xlabel('Predicted')
+plt.ylabel('Expected')
+plt.show()
+
+#Grabando la estructura
+model_json = model.to_json()
+with open("mimodel.json","w") as json_file:
+  json_file.write(model_json)
+
+# Grabando los pesos
+model.save_weights("mimodelo.weights.h5")
+print("modelo guardado")
+
+from keras.models import Model,model_from_json
+json_file = open("model.json",'r')
+loaded_model_json = json_file.read()
+json_file.close()
+loaded_model = model_from_json(loaded_model_json)
+loaded_model.load_weights("mimodelo.weights.h5")
+print("modelo cargado en el disco")
+loaded_model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])
+
+print(loaded_model.predict(np.array([[83.475, 1, 1, 35, 1,]])).round()[0][0])