Caso 6. Comparación modelos de regresión. Datos Precios autos. Programamción Python
Kevin Govanni Rodriguez Parra
2022-10-17
1 Objetivo
Comparar modelos de supervisados a través de la aplicación de algoritmos de predicción de precios de automóviles determinando el estadístico del error cuadrático medio (rmse).
2 Descripción
Se cargan los datos previamente preparados de la dirección https://raw.githubusercontent.com/rpizarrog/Analisis-Inteligente-de-datos/main/datos/CarPrice_Assignment_Numericas_Preparado.csv
Se crean datos de entrenamiento al 80%
Se crean datos de validación al 20%
Se crea el modelo regresión múltiple con datos de entrenamiento
Con este modelo se responde a preguntas tales como:
¿cuáles son variables que están por encima del 90% de confianza como predictores?,
¿Cuál es el valor de R Square Adjusted o que tanto representan las variables dependientes al precio del vehículo?
Se generan predicciones con datos de validación
Se determina el estadístico RMSE para efectos de comparación
Se crea el modelo árboles de regresión con los datos de entrenamiento
Se identifica la importancia de las variables sobre el precio
Se visualiza el árbol de regresión y sus reglas de asociación
Se hacen predicciones con datos de validación
Se determinar el estadístico RMSE para efectos de comparación
Se construye el modelo bosques aleatorios con datos de entrenamiento y con 20 árboles simulados
Se identifica la importancia de las variables sobre el precio
Se generan predicciones con datos de validación
Se determina el estadístico RMSE para efectos de comparación
Al final del caso, se describe una interpretación personal
3 Desarrollo
3.1 Cargar librerías
# Tratamiento de datos
import numpy as np
import pandas as pd
# Gráficos
import matplotlib.pyplot as plt
# Preprocesado y moYdelado
from sklearn.model_selection import train_test_split
# Estadisticos y lineal múltiple
import statsmodels.api as sm # Estadísticas R Adjused
import seaborn as sns # Gráficos
from sklearn import linear_model
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import PolynomialFeatures # Polinomial
# Arbol de regresion
from sklearn.tree import DecisionTreeRegressor
from sklearn.tree import plot_tree
from sklearn.tree import export_graphviz
from sklearn.tree import export_text
from sklearn.model_selection import GridSearchCV
# Random Forest
from sklearn.ensemble import RandomForestRegressor
# Metricas
from sklearn import metrics
from sklearn.metrics import mean_squared_error, r2_score3.2 Cargar datos
datos = pd.read_csv("https://raw.githubusercontent.com/rpizarrog/Analisis-Inteligente-de-datos/main/datos/CarPrice_Assignment_Numericas_Preparado.csv")
datos## Unnamed: 0 symboling wheelbase ... citympg highwaympg price
## 0 1 3 88.6 ... 21 27 13495.0
## 1 2 3 88.6 ... 21 27 16500.0
## 2 3 1 94.5 ... 19 26 16500.0
## 3 4 2 99.8 ... 24 30 13950.0
## 4 5 2 99.4 ... 18 22 17450.0
## .. ... ... ... ... ... ... ...
## 200 201 -1 109.1 ... 23 28 16845.0
## 201 202 -1 109.1 ... 19 25 19045.0
## 202 203 -1 109.1 ... 18 23 21485.0
## 203 204 -1 109.1 ... 26 27 22470.0
## 204 205 -1 109.1 ... 19 25 22625.0
##
## [205 rows x 16 columns]3.3 Exploración de datos
print("Observaciones y variables: ", datos.shape)## Observaciones y variables: (205, 16)print("Columnas y tipo de dato")
# datos.columns## Columnas y tipo de datodatos.dtypes## Unnamed: 0 int64
## symboling int64
## wheelbase float64
## carlength float64
## carwidth float64
## carheight float64
## curbweight int64
## enginesize int64
## boreratio float64
## stroke float64
## compressionratio float64
## horsepower int64
## peakrpm int64
## citympg int64
## highwaympg int64
## price float64
## dtype: object3.4 Diccionario de datos
| Col | Nombre | Descripción |
|---|---|---|
| 1 | Symboling | Its assigned insurance risk rating, A value of +3 indicates that the auto is risky, -3 that it is probably pretty safe.(Categorical) |
| 2 | wheelbase | Weelbase of car (Numeric). Distancia de ejes en pulgadas. |
| 3 | carlength | Length of car (Numeric). Longitud |
| 4 | carwidth | Width of car (Numeric). Amplitud |
| 5 | carheight | height of car (Numeric). Altura |
| 6 | curbweight | The weight of a car without occupants or baggage. (Numeric). Peso del auto |
| 7 | enginesize | Size of car (Numeric). Tamaño del carro en … |
| 8 | boreratio | Boreratio of car (Numeric). Eficiencia de motor |
| 9 | stroke | Stroke or volume inside the engine (Numeric). Pistones, tiempos, combustión |
| 10 | compressionratio | compression ratio of car (Numeric). Comprensión o medición de presión en motor |
| 11 | horsepower | Horsepower (Numeric). Poder del carro |
| 12 | peakrpm | car peak rpm (Numeric). Picos de revoluciones por minuto |
| 13 | citympg | Mileage in city (Numeric). Consumo de gasolina |
| 14 | highwaympg | Mileage on highway (Numeric). Consumo de gasolina |
| 16 | price (Dependent variable) |
Price of car (Numeric). Precio del carro en dólares |
~Fuente: https://archive.ics.uci.edu/ml/datasets/Automobile~
3.5 Limpiar datos
Dejar solo las variables necesarias:
‘symboling’, ‘wheelbase’, ‘carlength’, ‘carwidth’, ‘carheight’, ‘curbweight’, ‘enginesize’, ‘boreratio’, ‘stroke’, ‘compressionratio’, ‘horsepower’, ‘peakrpm’, ‘citympg’, ‘highwaympg’, ‘price’
datos = datos[['symboling', 'wheelbase', 'carlength', 'carwidth', 'carheight', 'curbweight', 'enginesize', 'boreratio', 'stroke', 'compressionratio', 'horsepower', 'peakrpm', 'citympg', 'highwaympg', 'price']]
datos.describe()## symboling wheelbase carlength ... citympg highwaympg price
## count 205.000000 205.000000 205.000000 ... 205.000000 205.000000 205.000000
## mean 0.834146 98.756585 174.049268 ... 25.219512 30.751220 13276.710571
## std 1.245307 6.021776 12.337289 ... 6.542142 6.886443 7988.852332
## min -2.000000 86.600000 141.100000 ... 13.000000 16.000000 5118.000000
## 25% 0.000000 94.500000 166.300000 ... 19.000000 25.000000 7788.000000
## 50% 1.000000 97.000000 173.200000 ... 24.000000 30.000000 10295.000000
## 75% 2.000000 102.400000 183.100000 ... 30.000000 34.000000 16503.000000
## max 3.000000 120.900000 208.100000 ... 49.000000 54.000000 45400.000000
##
## [8 rows x 15 columns]datos## symboling wheelbase carlength ... citympg highwaympg price
## 0 3 88.6 168.8 ... 21 27 13495.0
## 1 3 88.6 168.8 ... 21 27 16500.0
## 2 1 94.5 171.2 ... 19 26 16500.0
## 3 2 99.8 176.6 ... 24 30 13950.0
## 4 2 99.4 176.6 ... 18 22 17450.0
## .. ... ... ... ... ... ... ...
## 200 -1 109.1 188.8 ... 23 28 16845.0
## 201 -1 109.1 188.8 ... 19 25 19045.0
## 202 -1 109.1 188.8 ... 18 23 21485.0
## 203 -1 109.1 188.8 ... 26 27 22470.0
## 204 -1 109.1 188.8 ... 19 25 22625.0
##
## [205 rows x 15 columns]3.5.1 Datos de entrenamiento y validación
Datos de entrenamiento al 80% de los datos y 20% los datos de validación. Semilla 1307
X_entrena, X_valida, Y_entrena, Y_valida = train_test_split(datos.drop(columns = "price"), datos['price'],train_size = 0.80, random_state = 1307)3.5.1.1 Datos de entrenamiento
X_entrena## symboling wheelbase carlength ... peakrpm citympg highwaympg
## 109 0 114.2 198.9 ... 5000 19 24
## 121 1 93.7 167.3 ... 5500 31 38
## 9 0 99.5 178.2 ... 5500 16 22
## 35 0 96.5 163.4 ... 6000 30 34
## 25 1 93.7 157.3 ... 5500 31 38
## .. ... ... ... ... ... ... ...
## 59 1 98.8 177.8 ... 4800 26 32
## 134 3 99.1 186.6 ... 5250 21 28
## 178 3 102.9 183.5 ... 5200 20 24
## 81 3 96.3 173.0 ... 5000 25 32
## 122 1 93.7 167.3 ... 5500 31 38
##
## [164 rows x 14 columns]3.5.1.2 Datos de validación
X_valida## symboling wheelbase carlength ... peakrpm citympg highwaympg
## 12 0 101.2 176.8 ... 4250 21 28
## 65 0 104.9 175.0 ... 5000 19 27
## 167 2 98.4 176.2 ... 4800 24 30
## 5 2 99.8 177.3 ... 5500 19 25
## 34 1 93.7 150.0 ... 6000 30 34
## 199 -1 104.3 188.8 ... 5100 17 22
## 201 -1 109.1 188.8 ... 5300 19 25
## 44 1 94.5 155.9 ... 5400 38 43
## 41 0 96.5 175.4 ... 5800 24 28
## 148 0 96.9 173.6 ... 4800 23 29
## 179 3 102.9 183.5 ... 5200 19 24
## 184 2 97.3 171.7 ... 4800 37 46
## 182 2 97.3 171.7 ... 4800 37 46
## 106 1 99.2 178.5 ... 5200 19 25
## 153 0 95.7 169.7 ... 4800 31 37
## 102 0 100.4 184.6 ... 5200 17 22
## 130 0 96.1 181.5 ... 5100 23 31
## 161 0 95.7 166.3 ... 4800 28 34
## 156 0 95.7 166.3 ... 4800 30 37
## 197 -1 104.3 188.8 ... 5400 24 28
## 13 0 101.2 176.8 ... 4250 21 28
## 61 1 98.8 177.8 ... 4800 26 32
## 149 0 96.9 173.6 ... 4800 23 23
## 124 3 95.9 173.2 ... 5000 19 24
## 98 2 95.1 162.4 ... 5200 31 37
## 16 0 103.5 193.8 ... 5400 16 22
## 60 0 98.8 177.8 ... 4800 26 32
## 139 2 93.7 157.9 ... 4400 26 31
## 2 1 94.5 171.2 ... 5000 19 26
## 142 0 97.2 172.0 ... 4400 28 33
## 7 1 105.8 192.7 ... 5500 19 25
## 55 3 95.3 169.0 ... 6000 17 23
## 172 2 98.4 176.2 ... 4800 24 30
## 73 0 120.9 208.1 ... 4500 14 16
## 32 1 93.7 150.0 ... 5500 38 42
## 158 0 95.7 166.3 ... 4500 34 36
## 15 0 103.5 189.0 ... 5400 16 22
## 49 0 102.0 191.7 ... 5000 13 17
## 19 1 94.5 155.9 ... 5400 38 43
## 93 1 94.5 170.2 ... 5200 31 37
## 112 0 107.9 186.7 ... 4150 28 33
##
## [41 rows x 14 columns]3.6 Modelos Supervisados
3.6.1 Modelo de regresión lineal múltiple. (RM)
Se construye el modelo de regresión lineal múltiple (rm)
modelo_rm = LinearRegression()
modelo_rm.fit(X_entrena,Y_entrena)## LinearRegression()3.6.1.1 Coeficientes
Solo se muestran los coeficientes de: \(\beta_1, \beta_2, ...\beta_n\)
modelo_rm.coef_## array([ 3.17186534e+02, 1.32383009e+02, -1.03370273e+02, 6.44126965e+02,
## 1.13974626e+02, 1.43640873e+00, 1.32654173e+02, -2.07214251e+03,
## -3.90223816e+03, 3.72881265e+02, 2.86621423e+01, 2.33860775e+00,
## -2.79207643e+02, 1.65303498e+02])- En modelos lineales múltiples el estadístico Adjusted R-squared: 0.8347 significa que las variables independientes explican aproximadamente el 83.47% de la variable dependiente precio.
print(modelo_rm.score(X_entrena, Y_entrena))## 0.86914485446726693.6.1.2 Predicciones del modelo rm
predicciones_rm = modelo_rm.predict(X_valida)
print(predicciones_rm[:-1])## [16626.26023764 15839.87709934 13468.89237861 15760.3524183
## 8704.34670222 15763.85156511 18969.81484685 6241.33875894
## 9892.03503603 10276.63266463 22919.99328956 11192.71102931
## 11188.40180312 23687.97143591 5691.39036531 22785.4695227
## 10073.2670804 6689.99280404 6591.39017885 15835.24716701
## 16705.26271786 9906.21949034 9961.64216746 15239.70264707
## 6804.71130653 27080.00069376 9830.09750074 8570.88999407
## 18580.59324031 8394.0002033 18869.01798138 8367.27261818
## 14207.70480256 41876.84759442 5932.13261809 9696.32662776
## 26944.53898237 49802.38703319 6241.33875894 5647.58429948]3.6.1.3 Tabla comparativa
comparaciones = pd.DataFrame(X_valida)
comparaciones = comparaciones.assign(Precio_Real = Y_valida)
comparaciones = comparaciones.assign(Precio_Prediccion = predicciones_rm.flatten().tolist())
print(comparaciones)## symboling wheelbase ... Precio_Real Precio_Prediccion
## 12 0 101.2 ... 20970.0 16626.260238
## 65 0 104.9 ... 18280.0 15839.877099
## 167 2 98.4 ... 8449.0 13468.892379
## 5 2 99.8 ... 15250.0 15760.352418
## 34 1 93.7 ... 7129.0 8704.346702
## 199 -1 104.3 ... 18950.0 15763.851565
## 201 -1 109.1 ... 19045.0 18969.814847
## 44 1 94.5 ... 8916.5 6241.338759
## 41 0 96.5 ... 12945.0 9892.035036
## 148 0 96.9 ... 8013.0 10276.632665
## 179 3 102.9 ... 15998.0 22919.993290
## 184 2 97.3 ... 7995.0 11192.711029
## 182 2 97.3 ... 7775.0 11188.401803
## 106 1 99.2 ... 18399.0 23687.971436
## 153 0 95.7 ... 6918.0 5691.390365
## 102 0 100.4 ... 14399.0 22785.469523
## 130 0 96.1 ... 9295.0 10073.267080
## 161 0 95.7 ... 8358.0 6689.992804
## 156 0 95.7 ... 6938.0 6591.390179
## 197 -1 104.3 ... 16515.0 15835.247167
## 13 0 101.2 ... 21105.0 16705.262718
## 61 1 98.8 ... 10595.0 9906.219490
## 149 0 96.9 ... 11694.0 9961.642167
## 124 3 95.9 ... 12764.0 15239.702647
## 98 2 95.1 ... 8249.0 6804.711307
## 16 0 103.5 ... 41315.0 27080.000694
## 60 0 98.8 ... 8495.0 9830.097501
## 139 2 93.7 ... 7053.0 8570.889994
## 2 1 94.5 ... 16500.0 18580.593240
## 142 0 97.2 ... 7775.0 8394.000203
## 7 1 105.8 ... 18920.0 18869.017981
## 55 3 95.3 ... 10945.0 8367.272618
## 172 2 98.4 ... 17669.0 14207.704803
## 73 0 120.9 ... 40960.0 41876.847594
## 32 1 93.7 ... 5399.0 5932.132618
## 158 0 95.7 ... 7898.0 9696.326628
## 15 0 103.5 ... 30760.0 26944.538982
## 49 0 102.0 ... 36000.0 49802.387033
## 19 1 94.5 ... 6295.0 6241.338759
## 93 1 94.5 ... 7349.0 5647.584299
## 112 0 107.9 ... 16900.0 18540.628858
##
## [41 rows x 16 columns]3.6.1.4 RMSE modelo de rm
rmse_rm = mean_squared_error(
y_true = Y_valida,
y_pred = predicciones_rm,
squared = False
)
print(f"El error (rmse) de test es: {rmse_rm}")## El error (rmse) de test es: 4231.747475030332o
print('Root Mean Squared Error RMSE:', np.sqrt(metrics.mean_squared_error(Y_valida, predicciones_rm)))## Root Mean Squared Error RMSE: 4231.7474750303323.6.2 Modelo de árbol de regresión (AR)
Se construye el modelo de árbol de regresión (ar)
modelo_ar = DecisionTreeRegressor(
#max_depth = 3,
random_state = 1307
)Entrenar el modelo
modelo_ar.fit(X_entrena, Y_entrena)## DecisionTreeRegressor(random_state=1307)3.6.2.1 Visualización de árbol de regresión
fig, ax = plt.subplots(figsize=(12, 5))
print(f"Profundidad del árbol: {modelo_ar.get_depth()}")## Profundidad del árbol: 14print(f"Número de nodos terminales: {modelo_ar.get_n_leaves()}")## Número de nodos terminales: 153plot = plot_tree(
decision_tree = modelo_ar,
feature_names = datos.drop(columns = "price").columns,
class_names = 'price',
filled = True,
impurity = False,
fontsize = 10,
precision = 2,
ax = ax
)
plot
Reglas de asociación del árbol
texto_modelo = export_text(
decision_tree = modelo_ar,
feature_names = list(datos.drop(columns = "price").columns)
)
print(texto_modelo)## |--- enginesize <= 182.00
## | |--- curbweight <= 2542.00
## | | |--- curbweight <= 2247.00
## | | | |--- curbweight <= 2072.00
## | | | | |--- wheelbase <= 94.10
## | | | | | |--- stroke <= 3.09
## | | | | | | |--- carlength <= 149.00
## | | | | | | | |--- value: [5151.00]
## | | | | | | |--- carlength > 149.00
## | | | | | | | |--- value: [5118.00]
## | | | | | |--- stroke > 3.09
## | | | | | | |--- curbweight <= 1944.50
## | | | | | | | |--- carlength <= 153.65
## | | | | | | | | |--- highwaympg <= 46.00
## | | | | | | | | | |--- carheight <= 51.70
## | | | | | | | | | | |--- value: [6855.00]
## | | | | | | | | | |--- carheight > 51.70
## | | | | | | | | | | |--- value: [6529.00]
## | | | | | | | | |--- highwaympg > 46.00
## | | | | | | | | | |--- value: [6479.00]
## | | | | | | | |--- carlength > 153.65
## | | | | | | | | |--- citympg <= 34.00
## | | | | | | | | | |--- citympg <= 30.50
## | | | | | | | | | | |--- value: [5195.00]
## | | | | | | | | | |--- citympg > 30.50
## | | | | | | | | | | |--- curbweight <= 1902.50
## | | | | | | | | | | | |--- truncated branch of depth 2
## | | | | | | | | | | |--- curbweight > 1902.50
## | | | | | | | | | | | |--- truncated branch of depth 2
## | | | | | | | | |--- citympg > 34.00
## | | | | | | | | | |--- carwidth <= 64.10
## | | | | | | | | | | |--- value: [5572.00]
## | | | | | | | | | |--- carwidth > 64.10
## | | | | | | | | | | |--- value: [5389.00]
## | | | | | | |--- curbweight > 1944.50
## | | | | | | | |--- boreratio <= 3.05
## | | | | | | | | |--- curbweight <= 1978.00
## | | | | | | | | | |--- carlength <= 162.05
## | | | | | | | | | | |--- value: [6229.00]
## | | | | | | | | | |--- carlength > 162.05
## | | | | | | | | | | |--- value: [6695.00]
## | | | | | | | | |--- curbweight > 1978.00
## | | | | | | | | | |--- carheight <= 50.70
## | | | | | | | | | | |--- value: [7150.50]
## | | | | | | | | | |--- carheight > 50.70
## | | | | | | | | | | |--- carwidth <= 64.10
## | | | | | | | | | | | |--- value: [6692.00]
## | | | | | | | | | | |--- carwidth > 64.10
## | | | | | | | | | | | |--- value: [6669.00]
## | | | | | | | |--- boreratio > 3.05
## | | | | | | | | |--- value: [7395.00]
## | | | | |--- wheelbase > 94.10
## | | | | | |--- carlength <= 156.50
## | | | | | | |--- value: [8916.50]
## | | | | | |--- carlength > 156.50
## | | | | | | |--- carwidth <= 63.70
## | | | | | | | |--- curbweight <= 2000.00
## | | | | | | | | |--- highwaympg <= 41.00
## | | | | | | | | | |--- value: [5348.00]
## | | | | | | | | |--- highwaympg > 41.00
## | | | | | | | | | |--- value: [6575.00]
## | | | | | | | |--- curbweight > 2000.00
## | | | | | | | | |--- curbweight <= 2027.50
## | | | | | | | | | |--- value: [6488.00]
## | | | | | | | | |--- curbweight > 2027.50
## | | | | | | | | | |--- value: [6338.00]
## | | | | | | |--- carwidth > 63.70
## | | | | | | | |--- curbweight <= 1903.50
## | | | | | | | | |--- value: [5499.00]
## | | | | | | | |--- curbweight > 1903.50
## | | | | | | | | |--- carheight <= 54.00
## | | | | | | | | | |--- carlength <= 167.90
## | | | | | | | | | | |--- value: [7799.00]
## | | | | | | | | | |--- carlength > 167.90
## | | | | | | | | | | |--- value: [7999.00]
## | | | | | | | | |--- carheight > 54.00
## | | | | | | | | | |--- curbweight <= 1944.50
## | | | | | | | | | | |--- curbweight <= 1928.00
## | | | | | | | | | | | |--- value: [6649.00]
## | | | | | | | | | | |--- curbweight > 1928.00
## | | | | | | | | | | | |--- value: [6849.00]
## | | | | | | | | | |--- curbweight > 1944.50
## | | | | | | | | | | |--- stroke <= 3.44
## | | | | | | | | | | | |--- truncated branch of depth 3
## | | | | | | | | | | |--- stroke > 3.44
## | | | | | | | | | | | |--- value: [7099.00]
## | | | |--- curbweight > 2072.00
## | | | | |--- highwaympg <= 29.50
## | | | | | |--- value: [9980.00]
## | | | | |--- highwaympg > 29.50
## | | | | | |--- citympg <= 29.50
## | | | | | | |--- horsepower <= 71.50
## | | | | | | | |--- wheelbase <= 95.10
## | | | | | | | | |--- curbweight <= 2186.50
## | | | | | | | | | |--- value: [8058.00]
## | | | | | | | | |--- curbweight > 2186.50
## | | | | | | | | | |--- value: [8238.00]
## | | | | | | | |--- wheelbase > 95.10
## | | | | | | | | |--- value: [9258.00]
## | | | | | | |--- horsepower > 71.50
## | | | | | | | |--- carheight <= 50.70
## | | | | | | | | |--- value: [8558.00]
## | | | | | | | |--- carheight > 50.70
## | | | | | | | | |--- wheelbase <= 93.50
## | | | | | | | | | |--- symboling <= 1.50
## | | | | | | | | | | |--- value: [7689.00]
## | | | | | | | | | |--- symboling > 1.50
## | | | | | | | | | | |--- value: [7603.00]
## | | | | | | | | |--- wheelbase > 93.50
## | | | | | | | | | |--- highwaympg <= 33.50
## | | | | | | | | | | |--- carwidth <= 64.50
## | | | | | | | | | | | |--- value: [7957.00]
## | | | | | | | | | | |--- carwidth > 64.50
## | | | | | | | | | | | |--- value: [7895.00]
## | | | | | | | | | |--- highwaympg > 33.50
## | | | | | | | | | | |--- curbweight <= 2210.50
## | | | | | | | | | | | |--- value: [7975.00]
## | | | | | | | | | | |--- curbweight > 2210.50
## | | | | | | | | | | | |--- value: [8195.00]
## | | | | | |--- citympg > 29.50
## | | | | | | |--- highwaympg <= 37.50
## | | | | | | | |--- enginesize <= 103.00
## | | | | | | | | |--- value: [7198.00]
## | | | | | | | |--- enginesize > 103.00
## | | | | | | | | |--- value: [7126.00]
## | | | | | | |--- highwaympg > 37.50
## | | | | | | | |--- wheelbase <= 94.70
## | | | | | | | | |--- value: [7609.00]
## | | | | | | | |--- wheelbase > 94.70
## | | | | | | | | |--- value: [7738.00]
## | | |--- curbweight > 2247.00
## | | | |--- horsepower <= 100.50
## | | | | |--- carwidth <= 65.75
## | | | | | |--- peakrpm <= 5100.00
## | | | | | | |--- carheight <= 53.90
## | | | | | | | |--- carheight <= 50.50
## | | | | | | | | |--- value: [8499.00]
## | | | | | | | |--- carheight > 50.50
## | | | | | | | | |--- curbweight <= 2385.00
## | | | | | | | | | |--- citympg <= 26.50
## | | | | | | | | | | |--- peakrpm <= 4900.00
## | | | | | | | | | | | |--- value: [6785.00]
## | | | | | | | | | | |--- peakrpm > 4900.00
## | | | | | | | | | | | |--- value: [6989.00]
## | | | | | | | | | |--- citympg > 26.50
## | | | | | | | | | | |--- highwaympg <= 39.50
## | | | | | | | | | | | |--- value: [7463.00]
## | | | | | | | | | | |--- highwaympg > 39.50
## | | | | | | | | | | | |--- value: [7788.00]
## | | | | | | | | |--- curbweight > 2385.00
## | | | | | | | | | |--- value: [8189.00]
## | | | | | | |--- carheight > 53.90
## | | | | | | | |--- horsepower <= 65.00
## | | | | | | | | |--- value: [7898.00]
## | | | | | | | |--- horsepower > 65.00
## | | | | | | | | |--- horsepower <= 85.00
## | | | | | | | | | |--- peakrpm <= 4650.00
## | | | | | | | | | | |--- value: [9495.00]
## | | | | | | | | | |--- peakrpm > 4650.00
## | | | | | | | | | | |--- value: [9233.00]
## | | | | | | | | |--- horsepower > 85.00
## | | | | | | | | | |--- value: [8921.00]
## | | | | | |--- peakrpm > 5100.00
## | | | | | | |--- highwaympg <= 30.00
## | | | | | | | |--- value: [11595.00]
## | | | | | | |--- highwaympg > 30.00
## | | | | | | | |--- curbweight <= 2332.00
## | | | | | | | | |--- horsepower <= 98.50
## | | | | | | | | | |--- enginesize <= 109.50
## | | | | | | | | | | |--- value: [8495.00]
## | | | | | | | | | |--- enginesize > 109.50
## | | | | | | | | | | |--- curbweight <= 2303.00
## | | | | | | | | | | | |--- truncated branch of depth 2
## | | | | | | | | | | |--- curbweight > 2303.00
## | | | | | | | | | | | |--- truncated branch of depth 2
## | | | | | | | | |--- horsepower > 98.50
## | | | | | | | | | |--- value: [9995.00]
## | | | | | | | |--- curbweight > 2332.00
## | | | | | | | | |--- carlength <= 172.75
## | | | | | | | | | |--- value: [9960.00]
## | | | | | | | | |--- carlength > 172.75
## | | | | | | | | | |--- carheight <= 53.55
## | | | | | | | | | | |--- value: [10198.00]
## | | | | | | | | | |--- carheight > 53.55
## | | | | | | | | | | |--- value: [10295.00]
## | | | | |--- carwidth > 65.75
## | | | | | |--- curbweight <= 2397.50
## | | | | | | |--- peakrpm <= 5150.00
## | | | | | | | |--- symboling <= 0.00
## | | | | | | | | |--- value: [8948.00]
## | | | | | | | |--- symboling > 0.00
## | | | | | | | | |--- value: [8845.00]
## | | | | | | |--- peakrpm > 5150.00
## | | | | | | | |--- value: [10345.00]
## | | | | | |--- curbweight > 2397.50
## | | | | | | |--- carwidth <= 66.55
## | | | | | | | |--- curbweight <= 2419.50
## | | | | | | | | |--- carheight <= 54.40
## | | | | | | | | | |--- value: [9988.00]
## | | | | | | | | |--- carheight > 54.40
## | | | | | | | | | |--- curbweight <= 2412.00
## | | | | | | | | | | |--- value: [10245.00]
## | | | | | | | | | |--- curbweight > 2412.00
## | | | | | | | | | | |--- value: [10898.00]
## | | | | | | | |--- curbweight > 2419.50
## | | | | | | | | |--- horsepower <= 78.50
## | | | | | | | | | |--- carheight <= 55.20
## | | | | | | | | | | |--- value: [10698.00]
## | | | | | | | | | |--- carheight > 55.20
## | | | | | | | | | | |--- value: [10795.00]
## | | | | | | | | |--- horsepower > 78.50
## | | | | | | | | | |--- peakrpm <= 4500.00
## | | | | | | | | | | |--- value: [11248.00]
## | | | | | | | | | |--- peakrpm > 4500.00
## | | | | | | | | | | |--- value: [11245.00]
## | | | | | | |--- carwidth > 66.55
## | | | | | | | |--- value: [9895.00]
## | | | |--- horsepower > 100.50
## | | | | |--- carlength <= 176.40
## | | | | | |--- citympg <= 20.00
## | | | | | | |--- horsepower <= 118.00
## | | | | | | | |--- curbweight <= 2382.50
## | | | | | | | | |--- value: [11845.00]
## | | | | | | | |--- curbweight > 2382.50
## | | | | | | | | |--- value: [13645.00]
## | | | | | | |--- horsepower > 118.00
## | | | | | | | |--- value: [15645.00]
## | | | | | |--- citympg > 20.00
## | | | | | | |--- carheight <= 53.45
## | | | | | | | |--- symboling <= 1.50
## | | | | | | | | |--- highwaympg <= 29.50
## | | | | | | | | | |--- curbweight <= 2282.50
## | | | | | | | | | | |--- value: [9298.00]
## | | | | | | | | | |--- curbweight > 2282.50
## | | | | | | | | | | |--- value: [9538.00]
## | | | | | | | | |--- highwaympg > 29.50
## | | | | | | | | | |--- value: [9279.00]
## | | | | | | | |--- symboling > 1.50
## | | | | | | | | |--- boreratio <= 3.39
## | | | | | | | | | |--- value: [9959.00]
## | | | | | | | | |--- boreratio > 3.39
## | | | | | | | | | |--- value: [9639.00]
## | | | | | | |--- carheight > 53.45
## | | | | | | | |--- value: [11259.00]
## | | | | |--- carlength > 176.40
## | | | | | |--- highwaympg <= 29.50
## | | | | | | |--- symboling <= 1.00
## | | | | | | | |--- value: [16925.00]
## | | | | | | |--- symboling > 1.00
## | | | | | | | |--- value: [16430.00]
## | | | | | |--- highwaympg > 29.50
## | | | | | | |--- value: [13950.00]
## | |--- curbweight > 2542.00
## | | |--- carwidth <= 68.65
## | | | |--- horsepower <= 118.50
## | | | | |--- carwidth <= 65.85
## | | | | | |--- curbweight <= 2549.50
## | | | | | | |--- value: [14997.50]
## | | | | | |--- curbweight > 2549.50
## | | | | | | |--- enginesize <= 105.50
## | | | | | | | |--- value: [8778.00]
## | | | | | | |--- enginesize > 105.50
## | | | | | | | |--- curbweight <= 2615.00
## | | | | | | | | |--- value: [9989.00]
## | | | | | | | |--- curbweight > 2615.00
## | | | | | | | | |--- highwaympg <= 29.50
## | | | | | | | | | |--- value: [11048.00]
## | | | | | | | | |--- highwaympg > 29.50
## | | | | | | | | | |--- curbweight <= 2696.50
## | | | | | | | | | | |--- value: [11199.00]
## | | | | | | | | | |--- curbweight > 2696.50
## | | | | | | | | | | |--- value: [11549.00]
## | | | | |--- carwidth > 65.85
## | | | | | |--- curbweight <= 2697.50
## | | | | | | |--- carlength <= 181.65
## | | | | | | | |--- compressionratio <= 15.75
## | | | | | | | | |--- value: [13295.00]
## | | | | | | | |--- compressionratio > 15.75
## | | | | | | | | |--- value: [13845.00]
## | | | | | | |--- carlength > 181.65
## | | | | | | | |--- compressionratio <= 9.31
## | | | | | | | | |--- curbweight <= 2629.00
## | | | | | | | | | |--- value: [12290.00]
## | | | | | | | | |--- curbweight > 2629.00
## | | | | | | | | | |--- value: [12170.00]
## | | | | | | | |--- compressionratio > 9.31
## | | | | | | | | |--- value: [11850.00]
## | | | | | |--- curbweight > 2697.50
## | | | | | | |--- carlength <= 181.60
## | | | | | | | |--- peakrpm <= 4850.00
## | | | | | | | | |--- value: [18344.00]
## | | | | | | | |--- peakrpm > 4850.00
## | | | | | | | | |--- value: [17450.00]
## | | | | | | |--- carlength > 181.60
## | | | | | | | |--- curbweight <= 3241.00
## | | | | | | | | |--- stroke <= 3.11
## | | | | | | | | | |--- curbweight <= 2732.50
## | | | | | | | | | | |--- value: [15040.00]
## | | | | | | | | | |--- curbweight > 2732.50
## | | | | | | | | | | |--- highwaympg <= 26.00
## | | | | | | | | | | | |--- value: [15580.00]
## | | | | | | | | | | |--- highwaympg > 26.00
## | | | | | | | | | | | |--- value: [15510.00]
## | | | | | | | | |--- stroke > 3.11
## | | | | | | | | | |--- curbweight <= 3136.00
## | | | | | | | | | | |--- curbweight <= 3054.50
## | | | | | | | | | | | |--- truncated branch of depth 4
## | | | | | | | | | | |--- curbweight > 3054.50
## | | | | | | | | | | | |--- value: [16630.00]
## | | | | | | | | | |--- curbweight > 3136.00
## | | | | | | | | | | |--- curbweight <= 3213.50
## | | | | | | | | | | | |--- value: [13200.00]
## | | | | | | | | | | |--- curbweight > 3213.50
## | | | | | | | | | | | |--- value: [12440.00]
## | | | | | | | |--- curbweight > 3241.00
## | | | | | | | | |--- curbweight <= 3357.50
## | | | | | | | | | |--- enginesize <= 136.00
## | | | | | | | | | | |--- value: [16695.00]
## | | | | | | | | | |--- enginesize > 136.00
## | | | | | | | | | | |--- value: [17950.00]
## | | | | | | | | |--- curbweight > 3357.50
## | | | | | | | | | |--- curbweight <= 3457.50
## | | | | | | | | | | |--- value: [13860.00]
## | | | | | | | | | |--- curbweight > 3457.50
## | | | | | | | | | | |--- value: [17075.00]
## | | | |--- horsepower > 118.50
## | | | | |--- horsepower <= 144.00
## | | | | | |--- enginesize <= 142.50
## | | | | | | |--- value: [18150.00]
## | | | | | |--- enginesize > 142.50
## | | | | | | |--- curbweight <= 2916.50
## | | | | | | | |--- value: [22018.00]
## | | | | | | |--- curbweight > 2916.50
## | | | | | | | |--- value: [24565.00]
## | | | | |--- horsepower > 144.00
## | | | | | |--- horsepower <= 158.00
## | | | | | | |--- boreratio <= 3.35
## | | | | | | | |--- curbweight <= 3141.00
## | | | | | | | | |--- value: [15690.00]
## | | | | | | | |--- curbweight > 3141.00
## | | | | | | | | |--- value: [15750.00]
## | | | | | | |--- boreratio > 3.35
## | | | | | | | |--- curbweight <= 2877.00
## | | | | | | | | |--- stroke <= 3.88
## | | | | | | | | | |--- value: [12629.00]
## | | | | | | | | |--- stroke > 3.88
## | | | | | | | | | |--- value: [12964.00]
## | | | | | | | |--- curbweight > 2877.00
## | | | | | | | | |--- carwidth <= 66.40
## | | | | | | | | | |--- curbweight <= 2923.50
## | | | | | | | | | | |--- value: [14869.00]
## | | | | | | | | | |--- curbweight > 2923.50
## | | | | | | | | | | |--- value: [14489.00]
## | | | | | | | | |--- carwidth > 66.40
## | | | | | | | | | |--- value: [13499.00]
## | | | | | |--- horsepower > 158.00
## | | | | | | |--- horsepower <= 187.50
## | | | | | | | |--- enginesize <= 135.50
## | | | | | | | | |--- carheight <= 54.05
## | | | | | | | | | |--- value: [17859.17]
## | | | | | | | | |--- carheight > 54.05
## | | | | | | | | | |--- curbweight <= 2827.50
## | | | | | | | | | | |--- value: [18150.00]
## | | | | | | | | | |--- curbweight > 2827.50
## | | | | | | | | | | |--- peakrpm <= 5300.00
## | | | | | | | | | | | |--- value: [18420.00]
## | | | | | | | | | | |--- peakrpm > 5300.00
## | | | | | | | | | | | |--- value: [18620.00]
## | | | | | | | |--- enginesize > 135.50
## | | | | | | | | |--- wheelbase <= 97.00
## | | | | | | | | | |--- value: [17199.00]
## | | | | | | | | |--- wheelbase > 97.00
## | | | | | | | | | |--- boreratio <= 3.52
## | | | | | | | | | | |--- value: [16558.00]
## | | | | | | | | | |--- boreratio > 3.52
## | | | | | | | | | | |--- value: [16503.00]
## | | | | | | |--- horsepower > 187.50
## | | | | | | | |--- value: [19699.00]
## | | |--- carwidth > 68.65
## | | | |--- curbweight <= 2982.00
## | | | | |--- horsepower <= 112.00
## | | | | | |--- value: [17710.00]
## | | | | |--- horsepower > 112.00
## | | | | | |--- value: [16845.00]
## | | | |--- curbweight > 2982.00
## | | | | |--- carlength <= 190.75
## | | | | | |--- stroke <= 3.01
## | | | | | | |--- value: [21485.00]
## | | | | | |--- stroke > 3.01
## | | | | | | |--- horsepower <= 110.00
## | | | | | | | |--- value: [22470.00]
## | | | | | | |--- horsepower > 110.00
## | | | | | | | |--- value: [22625.00]
## | | | | |--- carlength > 190.75
## | | | | | |--- value: [23875.00]
## |--- enginesize > 182.00
## | |--- citympg <= 14.50
## | | |--- value: [45400.00]
## | |--- citympg > 14.50
## | | |--- compressionratio <= 9.75
## | | | |--- compressionratio <= 8.05
## | | | | |--- value: [36880.00]
## | | | |--- compressionratio > 8.05
## | | | | |--- curbweight <= 2778.00
## | | | | | |--- value: [33278.00]
## | | | | |--- curbweight > 2778.00
## | | | | | |--- compressionratio <= 8.90
## | | | | | | |--- wheelbase <= 104.80
## | | | | | | | |--- value: [35056.00]
## | | | | | | |--- wheelbase > 104.80
## | | | | | | | |--- carheight <= 54.65
## | | | | | | | | |--- value: [33900.00]
## | | | | | | | |--- carheight > 54.65
## | | | | | | | | |--- value: [34184.00]
## | | | | | |--- compressionratio > 8.90
## | | | | | | |--- value: [37028.00]
## | | |--- compressionratio > 9.75
## | | | |--- carwidth <= 71.00
## | | | | |--- carheight <= 57.60
## | | | | | |--- carheight <= 55.70
## | | | | | | |--- value: [28176.00]
## | | | | | |--- carheight > 55.70
## | | | | | | |--- value: [25552.00]
## | | | | |--- carheight > 57.60
## | | | | | |--- value: [28248.00]
## | | | |--- carwidth > 71.00
## | | | | |--- symboling <= 0.00
## | | | | | |--- value: [31600.00]
## | | | | |--- symboling > 0.00
## | | | | | |--- value: [31400.50]3.6.2.2 Importancia de los predictores
importancia_predictores = pd.DataFrame(
{'predictor': datos.drop(columns = "price").columns,
'importancia': modelo_ar.feature_importances_}
)
print("Importancia de los predictores en el modelo")## Importancia de los predictores en el modeloimportancia_predictores.sort_values('importancia', ascending=False)## predictor importancia
## 6 enginesize 0.663625
## 5 curbweight 0.230675
## 10 horsepower 0.032163
## 3 carwidth 0.026297
## 12 citympg 0.020558
## 9 compressionratio 0.011517
## 2 carlength 0.008241
## 4 carheight 0.001527
## 13 highwaympg 0.001454
## 11 peakrpm 0.001428
## 8 stroke 0.001043
## 7 boreratio 0.000709
## 1 wheelbase 0.000708
## 0 symboling 0.000055Estos sería los predictores más importantes para el modelo de árbol de regresión enginesize, curbweight, peakrpm, carheight y wheelbase
3.6.2.3 Predicciones del modelo (ar)
predicciones_ar = modelo_ar.predict(X = X_valida)
predicciones_ar## array([22018. , 18150. , 9639. , 16430. , 6229. , 18420. , 22625. ,
## 8916.5, 11259. , 9233. , 16558. , 7898. , 7898. , 16558. ,
## 7898. , 13499. , 13295. , 9258. , 7198. , 15985. , 22018. ,
## 8845. , 11048. , 12629. , 7799. , 36880. , 10245. , 7957. ,
## 15690. , 7895. , 17710. , 11845. , 11549. , 45400. , 5118. ,
## 7463. , 36880. , 45400. , 8916.5, 7999. , 17950. ])3.6.2.4 Tabla comparativa
comparaciones = pd.DataFrame(X_valida)
comparaciones = comparaciones.assign(Precio_Real = Y_valida)
comparaciones = comparaciones.assign(Precio_Prediccion = predicciones_ar.flatten().tolist())
print(comparaciones)## symboling wheelbase ... Precio_Real Precio_Prediccion
## 12 0 101.2 ... 20970.0 22018.0
## 65 0 104.9 ... 18280.0 18150.0
## 167 2 98.4 ... 8449.0 9639.0
## 5 2 99.8 ... 15250.0 16430.0
## 34 1 93.7 ... 7129.0 6229.0
## 199 -1 104.3 ... 18950.0 18420.0
## 201 -1 109.1 ... 19045.0 22625.0
## 44 1 94.5 ... 8916.5 8916.5
## 41 0 96.5 ... 12945.0 11259.0
## 148 0 96.9 ... 8013.0 9233.0
## 179 3 102.9 ... 15998.0 16558.0
## 184 2 97.3 ... 7995.0 7898.0
## 182 2 97.3 ... 7775.0 7898.0
## 106 1 99.2 ... 18399.0 16558.0
## 153 0 95.7 ... 6918.0 7898.0
## 102 0 100.4 ... 14399.0 13499.0
## 130 0 96.1 ... 9295.0 13295.0
## 161 0 95.7 ... 8358.0 9258.0
## 156 0 95.7 ... 6938.0 7198.0
## 197 -1 104.3 ... 16515.0 15985.0
## 13 0 101.2 ... 21105.0 22018.0
## 61 1 98.8 ... 10595.0 8845.0
## 149 0 96.9 ... 11694.0 11048.0
## 124 3 95.9 ... 12764.0 12629.0
## 98 2 95.1 ... 8249.0 7799.0
## 16 0 103.5 ... 41315.0 36880.0
## 60 0 98.8 ... 8495.0 10245.0
## 139 2 93.7 ... 7053.0 7957.0
## 2 1 94.5 ... 16500.0 15690.0
## 142 0 97.2 ... 7775.0 7895.0
## 7 1 105.8 ... 18920.0 17710.0
## 55 3 95.3 ... 10945.0 11845.0
## 172 2 98.4 ... 17669.0 11549.0
## 73 0 120.9 ... 40960.0 45400.0
## 32 1 93.7 ... 5399.0 5118.0
## 158 0 95.7 ... 7898.0 7463.0
## 15 0 103.5 ... 30760.0 36880.0
## 49 0 102.0 ... 36000.0 45400.0
## 19 1 94.5 ... 6295.0 8916.5
## 93 1 94.5 ... 7349.0 7999.0
## 112 0 107.9 ... 16900.0 17950.0
##
## [41 rows x 16 columns]3.6.2.5 RMSE modelo de ar
rmse_ar = mean_squared_error(
y_true = Y_valida,
y_pred = predicciones_ar,
squared = False
)
print(f"El error (rmse) de test es: {rmse_ar}")## El error (rmse) de test es: 2554.2590842575455o
print('Root Mean Squared Error RMSE:', np.sqrt(metrics.mean_squared_error(Y_valida, predicciones_ar)))## Root Mean Squared Error RMSE: 2554.25908425754553.6.2.6 Modelo de bosques aleatorios (RF)
Se construye el modelo de árbol de regresión (ar). Semilla 1307 y 20 árboles de entrenamiento
modelo_rf = RandomForestRegressor(n_estimators = 20, random_state = 1307)
modelo_rf.fit(X_entrena, Y_entrena)## RandomForestRegressor(n_estimators=20, random_state=1307)3.6.2.7 Variables de importancia
# pendiente ... ...3.6.2.8 Predicciones del modelo (rf)
predicciones_rf = modelo_rf.predict(X_valida)
predicciones_rf## array([15658.9 , 14528.1 , 9792.25 , 13554.05 ,
## 7088.775 , 17404.35 , 19165.05 , 6651.375 ,
## 12607.15 , 10483.95 , 17038.70835 , 8804.8 ,
## 8659.8 , 16964.84168333, 8020.85 , 14571.8 ,
## 11591. , 8812.9 , 7527.95 , 14376.5 ,
## 15857.7 , 9996.6 , 13873.44166667, 13523.7 ,
## 7445.40416667, 34456.18335 , 10117.65 , 7830.4 ,
## 13542.35 , 8128.975 , 18734.70835 , 12392.5 ,
## 12919.5 , 39419.5 , 5877.375 , 8016.95 ,
## 35589.25835 , 37070.9 , 6651.375 , 7783.65 ,
## 16407.7 ])3.6.2.9 Tabla comparativa
comparaciones = pd.DataFrame(X_valida)
comparaciones = comparaciones.assign(Precio_Real = Y_valida)
comparaciones = comparaciones.assign(Precio_Prediccion = predicciones_rf.flatten().tolist())
print(comparaciones)## symboling wheelbase ... Precio_Real Precio_Prediccion
## 12 0 101.2 ... 20970.0 15658.900000
## 65 0 104.9 ... 18280.0 14528.100000
## 167 2 98.4 ... 8449.0 9792.250000
## 5 2 99.8 ... 15250.0 13554.050000
## 34 1 93.7 ... 7129.0 7088.775000
## 199 -1 104.3 ... 18950.0 17404.350000
## 201 -1 109.1 ... 19045.0 19165.050000
## 44 1 94.5 ... 8916.5 6651.375000
## 41 0 96.5 ... 12945.0 12607.150000
## 148 0 96.9 ... 8013.0 10483.950000
## 179 3 102.9 ... 15998.0 17038.708350
## 184 2 97.3 ... 7995.0 8804.800000
## 182 2 97.3 ... 7775.0 8659.800000
## 106 1 99.2 ... 18399.0 16964.841683
## 153 0 95.7 ... 6918.0 8020.850000
## 102 0 100.4 ... 14399.0 14571.800000
## 130 0 96.1 ... 9295.0 11591.000000
## 161 0 95.7 ... 8358.0 8812.900000
## 156 0 95.7 ... 6938.0 7527.950000
## 197 -1 104.3 ... 16515.0 14376.500000
## 13 0 101.2 ... 21105.0 15857.700000
## 61 1 98.8 ... 10595.0 9996.600000
## 149 0 96.9 ... 11694.0 13873.441667
## 124 3 95.9 ... 12764.0 13523.700000
## 98 2 95.1 ... 8249.0 7445.404167
## 16 0 103.5 ... 41315.0 34456.183350
## 60 0 98.8 ... 8495.0 10117.650000
## 139 2 93.7 ... 7053.0 7830.400000
## 2 1 94.5 ... 16500.0 13542.350000
## 142 0 97.2 ... 7775.0 8128.975000
## 7 1 105.8 ... 18920.0 18734.708350
## 55 3 95.3 ... 10945.0 12392.500000
## 172 2 98.4 ... 17669.0 12919.500000
## 73 0 120.9 ... 40960.0 39419.500000
## 32 1 93.7 ... 5399.0 5877.375000
## 158 0 95.7 ... 7898.0 8016.950000
## 15 0 103.5 ... 30760.0 35589.258350
## 49 0 102.0 ... 36000.0 37070.900000
## 19 1 94.5 ... 6295.0 6651.375000
## 93 1 94.5 ... 7349.0 7783.650000
## 112 0 107.9 ... 16900.0 16407.700000
##
## [41 rows x 16 columns]3.6.2.10 RMSE modelo de ar
rmse_rf = mean_squared_error(
y_true = Y_valida,
y_pred = predicciones_rf,
squared = False
)
print(f"El error (rmse) de test es: {rmse_rf}")## El error (rmse) de test es: 2328.478373613539o
print('Root Mean Squared Error RMSE:', np.sqrt(metrics.mean_squared_error(Y_valida, predicciones_rf)))## Root Mean Squared Error RMSE: 2328.4783736135393.7 Evaluación de modelos
Se comparan las predicciones
comparaciones = pd.DataFrame(X_valida)
comparaciones = comparaciones.assign(Precio_Real = Y_valida)
comparaciones = comparaciones.assign(Precio_Prediccion_rm = predicciones_rm.flatten().tolist(), Precio_Prediccion_ar = predicciones_ar.flatten().tolist(), Precio_Prediccion_rf = predicciones_rf.flatten().tolist())
print(comparaciones)## symboling wheelbase ... Precio_Prediccion_ar Precio_Prediccion_rf
## 12 0 101.2 ... 22018.0 15658.900000
## 65 0 104.9 ... 18150.0 14528.100000
## 167 2 98.4 ... 9639.0 9792.250000
## 5 2 99.8 ... 16430.0 13554.050000
## 34 1 93.7 ... 6229.0 7088.775000
## 199 -1 104.3 ... 18420.0 17404.350000
## 201 -1 109.1 ... 22625.0 19165.050000
## 44 1 94.5 ... 8916.5 6651.375000
## 41 0 96.5 ... 11259.0 12607.150000
## 148 0 96.9 ... 9233.0 10483.950000
## 179 3 102.9 ... 16558.0 17038.708350
## 184 2 97.3 ... 7898.0 8804.800000
## 182 2 97.3 ... 7898.0 8659.800000
## 106 1 99.2 ... 16558.0 16964.841683
## 153 0 95.7 ... 7898.0 8020.850000
## 102 0 100.4 ... 13499.0 14571.800000
## 130 0 96.1 ... 13295.0 11591.000000
## 161 0 95.7 ... 9258.0 8812.900000
## 156 0 95.7 ... 7198.0 7527.950000
## 197 -1 104.3 ... 15985.0 14376.500000
## 13 0 101.2 ... 22018.0 15857.700000
## 61 1 98.8 ... 8845.0 9996.600000
## 149 0 96.9 ... 11048.0 13873.441667
## 124 3 95.9 ... 12629.0 13523.700000
## 98 2 95.1 ... 7799.0 7445.404167
## 16 0 103.5 ... 36880.0 34456.183350
## 60 0 98.8 ... 10245.0 10117.650000
## 139 2 93.7 ... 7957.0 7830.400000
## 2 1 94.5 ... 15690.0 13542.350000
## 142 0 97.2 ... 7895.0 8128.975000
## 7 1 105.8 ... 17710.0 18734.708350
## 55 3 95.3 ... 11845.0 12392.500000
## 172 2 98.4 ... 11549.0 12919.500000
## 73 0 120.9 ... 45400.0 39419.500000
## 32 1 93.7 ... 5118.0 5877.375000
## 158 0 95.7 ... 7463.0 8016.950000
## 15 0 103.5 ... 36880.0 35589.258350
## 49 0 102.0 ... 45400.0 37070.900000
## 19 1 94.5 ... 8916.5 6651.375000
## 93 1 94.5 ... 7999.0 7783.650000
## 112 0 107.9 ... 17950.0 16407.700000
##
## [41 rows x 18 columns]Se compara el RMSE.
Se crea un arreglo numpy
rmse = np.array([[rmse_rm, rmse_ar, rmse_rf]])
rmse## array([[4231.74747503, 2554.25908426, 2328.47837361]])Se construye data.frame a partir del rreglo nmpy
rmse = pd.DataFrame(rmse)
rmse.columns = ['Regresion multiple', 'Arbol de regresion', 'Bosque aleatorio']
print("RMSE por modelo\n", rmse)
## RMSE por modelo
## Regresion multiple Arbol de regresion Bosque aleatorio
## 0 4231.747475 2554.259084 2328.4783744 Interpretación
Se cargaron datos numéricos de precios de automóviles basados en algunas variables numéricas.
Se utilizo la semilla 1307.
Importancia de las variables:
La variable de enginesize es la mas significativa en estos modelos y la que va a causar el mayor cambio durante las predicciones. Las variables mas importantes curbweight, y carwidth tambien tienen un gran efecto en todos los modelos.
Teniendo en cuenta que el mejor valor de RMSE en los modelos fue el de arboles aleatorios con un valor de RMSE de: 2328.478374, la diferencia entre el siguiente mejor modelo no es tan grande, en python la diferencia es mas pronunciada. Comparando con los modelos de R, la precisión de los modelos de python fue mas baja, esto como en casos anteriores se debe a que aunque se utiliza un mismo modelo la implementacion y la separacion con el uso de las semillas termina en resultados diferentes.
Las visualizaciones de R son mucho mejores que las de python y creo que dejan mas en claro muchos de los puntos de la actividad al momento de hacer el caso.