Ejemplo distribuciones

scripts/tema12/04-mtcars.Rmd

@@ -62,3 +62,95 @@ linewidth = 2.0, color = "red")
 plt.show()
 ```
 
+### Medidas de dispersión
+ - Rango de `mpg`, five nums, cuartiles
+```{python}
+from ggplot import mtcars
+
+rang = max(mtcars["mpg"]) - min(mtcars["mpg"])
+print(rang)
+
+five_nums = [mtcars["mpg"].quantile(0),
+            mtcars["mpg"].quantile(0.25),
+            mtcars["mpg"].quantile(0.5),
+            mtcars["mpg"].quantile(0.75),
+            mtcars["mpg"].quantile(1.0)
+]
+print(five_nums)
+
+print(mtcars["mpg"].describe())
+
+print(mtcars["mpg"].quantile(0.75) - mtcars["mpg"].quantile(0.25))
+
+import matplotlib.pyplot as plt
+plt.clf()
+mtcars.boxplot(column = "mpg", return_type = "axes", figsize = (10,10))
+
+plt.text(x=0.8, y = mtcars["mpg"].quantile(0.25), s = "1r cuartil")
+plt.text(x=0.8, y = mtcars["mpg"].quantile(0.5), s = "Mediana")
+plt.text(x=0.8, y = mtcars["mpg"].quantile(0.75), s = "3r cuartil")
+
+plt.text(x=0.9, y = mtcars["mpg"].quantile(0), s = "Min")
+plt.text(x=0.9, y = mtcars["mpg"].quantile(1), s = "Max")
+
+plt.text(x = 0.7, y = mtcars["mpg"].quantile(0.5), s = "RIC", rotation = 90, size = 25)
+plt.show()
+```
+
+- Varianza y desviación típica
+
+```{python}
+from ggplot import mtcars
+
+print(mtcars["mpg"].var())
+print(mtcars["mpg"].std())
+
+mad = abs(mtcars["mpg"]-mtcars["mpg"].median())
+k = 1.4826
+print(mad.median()*k)
+```
+
+- El sesgo y la curtosis
+
+```{python}
+from ggplot import mtcars
+
+print(mtcars["mpg"].skew())
+print(mtcars["mpg"].kurt())
+```
+
+
+```{python}
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+
+norm = np.random.normal(size=100000)
+skew = np.concatenate((np.random.normal(size=35000)+2, 
+                      np.random.exponential(size=65000)),
+                      axis = 0)
+unif = np.random.uniform(-2,2,size = 100000)
+peak = np.concatenate((np.random.exponential(size=50000),
+                      np.random.exponential(size=50000)*(-1)),
+                      axis = 0)
+
+
+data = pd.DataFrame({
+  "normal": norm,
+  "skew": skew,
+  "unif": unif,
+  "peak": peak
+})
+
+plt.clf()
+data.plot(kind="density", figsize = (10,10), xlim = (-5,5))
+plt.show()
+
+print("Normal, Sesgo = %f, Curtosis = %f"%(data["normal"].skew(), data["normal"].kurt()))
+print("Normal+Exp, Sesgo = %f, Curtosis = %f"%(data["skew"].skew(), data["skew"].kurt()))
+print("Uniforme, Sesgo = %f, Curtosis = %f"%(data["unif"].skew(), data["unif"].kurt()))
+print("Suma de Exp, Sesgo = %f, Curtosis = %f"%(data["peak"].skew(), data["peak"].kurt()))
+```
+
+
+

teoria/Tema10.Rmd

@@ -1,5 +1,5 @@
 ---
-title: "Tema 10 - Introducción a la regresión lineal"
+title: Tema 10 - Introducción a la regresión lineal
 author: "Juan Gabriel Gomila & María Santos"
 output: 
   ioslides_presentation: