Curso Completo de ML

Author: joanby

.RData

@@ -102,3 +102,5 @@ venv.bak/
 
 # mypy
 .mypy_cache/
+.Rproj.user
+.DS_Store

.Rhistory

@@ -0,0 +1,11 @@
+Country,Age,Salary,Purchased
+France,44,72000,No
+Spain,27,48000,Yes
+Germany,30,54000,No
+Spain,38,61000,No
+Germany,40,,Yes
+France,35,58000,Yes
+Spain,,52000,No
+France,48,79000,Yes
+Germany,50,83000,No
+France,37,67000,Yes

.gitignore

@@ -0,0 +1,12 @@
+# Plantilla para el Pre Procesado de Datos - Datos Categóricos
+# Importar el dataset
+dataset = read.csv('Data.csv')
+
+
+# Codificar las variables categóricas
+dataset$Country = factor(dataset$Country,
+                         levels = c("France", "Spain", "Germany"),
+                         labels = c(1, 2, 3))
+dataset$Purchased = factor(dataset$Purchased,
+                           levels = c("No", "Yes"),
+                           labels = c(0,1))

additional materials/transparencias/Part 0 - Welcome to Machine Learning A-Z/Section 1 - Welcome to Machine Learning A-Z !/ML_Overview_ES.key

@@ -0,0 +1,28 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Thu Feb 28 13:19:06 2019
+
+@author: juangabriel
+"""
+
+# Plantilla de Pre Procesado - Datos Categóricos
+
+# Cómo importar las librerías
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+
+# Importar el data set
+dataset = pd.read_csv('Data.csv')
+X = dataset.iloc[:, :-1].values
+y = dataset.iloc[:, 3].values
+
+# Codificar datos categóricos
+from sklearn.preprocessing import LabelEncoder, OneHotEncoder
+labelencoder_X = LabelEncoder()
+X[:, 0] = labelencoder_X.fit_transform(X[:, 0])
+onehotencoder = OneHotEncoder(categorical_features=[0])
+X = onehotencoder.fit_transform(X).toarray()
+labelencoder_y = LabelEncoder()
+y = labelencoder_y.fit_transform(y)

additional materials/transparencias/Part 10 - Model Selection & Boosting/Section 48 - Model Selection/Step1_Regularization_Intuition.key

@@ -0,0 +1,16 @@
+# Plantilla para el Pre Procesado de Datos
+# Importar el dataset
+dataset = read.csv('Data.csv')
+#dataset = dataset[, 2:3]
+
+# Dividir los datos en conjunto de entrenamiento y conjunto de test
+# install.packages("caTools")
+library(caTools)
+set.seed(123)
+split = sample.split(dataset$Purchased, SplitRatio = 0.8)
+training_set = subset(dataset, split == TRUE)
+testing_set = subset(dataset, split == FALSE)
+
+# Escalado de valores
+# training_set[,2:3] = scale(training_set[,2:3])
+# testing_set[,2:3] = scale(testing_set[,2:3])

additional materials/transparencias/Part 10 - Model Selection & Boosting/Section 48 - Model Selection/Step2_k_Fold_Cross_Validation_Intuition.key

@@ -0,0 +1,31 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Wed Feb 27 19:43:11 2019
+
+@author: juangabriel
+"""
+
+# Plantilla de Pre Procesado
+
+# Cómo importar las librerías
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+
+# Importar el data set
+dataset = pd.read_csv('Data.csv')
+X = dataset.iloc[:, :-1].values
+y = dataset.iloc[:, 3].values
+
+
+# Dividir el data set en conjunto de entrenamiento y conjunto de testing
+from sklearn.model_selection import train_test_split
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)
+
+
+# Escalado de variables
+"""from sklearn.preprocessing import StandardScaler
+sc_X = StandardScaler()
+X_train = sc_X.fit_transform(X_train)
+X_test = sc_X.transform(X_test)"""

additional materials/transparencias/Part 10 - Model Selection & Boosting/Section 48 - Model Selection/Step3_Grid_Search_Intuition.key

@@ -0,0 +1,12 @@
+# Plantilla para el Pre Procesado de Datos - Datos faltantes
+# Importar el dataset
+dataset = read.csv('Data.csv')
+
+
+# Tratamiento de los valores NA
+dataset$Age = ifelse(is.na(dataset$Age),
+                     ave(dataset$Age, FUN = function(x) mean(x, na.rm = TRUE)),
+                     dataset$Age)
+dataset$Salary = ifelse(is.na(dataset$Salary),
+                        ave(dataset$Salary, FUN = function(x) mean(x, na.rm = TRUE)),
+                        dataset$Salary)

additional materials/transparencias/Part 10 - Model Selection & Boosting/Section 49 - XGBoost/XGBoost_Intuition.key

@@ -0,0 +1,25 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Thu Feb 28 13:19:21 2019
+
+@author: juangabriel
+"""
+
+# Plantilla de Pre Procesado - Datos faltantes
+
+# Cómo importar las librerías
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+
+# Importar el data set
+dataset = pd.read_csv('Data.csv')
+X = dataset.iloc[:, :-1].values
+y = dataset.iloc[:, 3].values
+
+# Tratamiento de los NAs
+from sklearn.preprocessing import Imputer
+imputer = Imputer(missing_values = "NaN", strategy = "mean", axis = 0) 
+imputer = imputer.fit(X[:, 1:3])
+X[:, 1:3] = imputer.transform(X[:,1:3])