R + Python con reticulate

Author: joanby

ejercicios/data_frame_plot.png

@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

scripts/tema1/.ipynb_checkpoints/07-io-checkpoint.ipynb

@@ -0,0 +1,100 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Entrada y salida de datos"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Hola, me llamo Juan Gabriel\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"Hola, me llamo Juan Gabriel\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "5\n"
+     ]
+    }
+   ],
+   "source": [
+    "x = 5\n",
+    "print(x)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "El valor de la variable x es: 5\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\"El valor de la variable x es: \"+str(x))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "texto = input(\"Introduce aquí tu nombre: \")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.5.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

scripts/tema1/07-io.ipynb

@@ -6,7 +6,7 @@ output: html_document
 ---
 
 ```{r setup, include=FALSE}
-knitr::opts_chunk$set(echo = TRUE)
+knitr::opts_chunk$set(echo = TRUE, cache = TRUE)
 ```
 
 # Análisis de los diamantes

scripts/tema12/01-diamonds.Rmd

@@ -0,0 +1 @@
+base

scripts/tema12/01-diamonds_cache/html/__packages

@@ -0,0 +1,52 @@
+---
+title: "Pokemon"
+author: "Curso de Estadística Descriptiva"
+date: "9/1/2019"
+output: html_document
+---
+
+```{r setup, include=FALSE}
+knitr::opts_chunk$set(echo = TRUE, cache = TRUE)
+library(reticulate)
+use_python("/anaconda3/bin/python")
+```
+
+# Pokemon (Py -> R)
+
+## Limpieza de datos en Python
+
+```{python}
+import pandas as pd
+pokemon = pd.read_csv("../../data/Pokemon.csv")
+print(pokemon.head())
+print(pokemon.shape)
+pokemon = pokemon[pokemon["Generation"]==1]
+pokemon = pokemon[["Type 1", "Type 2", "Speed"]]
+print(pokemon.shape)
+pokemon = pokemon.dropna()
+print(pokemon.shape)
+```
+
+## Transmisión de los datos de Python a R
+```{r, fig.width=7, fig.height=4}
+hist(py$pokemon[,"Speed"], breaks = 10, main = "Velocidad de los Pokemon")
+```
+
+# Pokemon (R -> Py)
+## Carga de datos en R
+```{r}
+pokemon2 <- read.csv("../../data/Pokemon.csv", header = TRUE)
+head(pokemon2)
+library(tidyverse)
+pokemon2 <- pokemon2 %>% 
+  filter(Generation == 1) %>%
+  select(Type.1, Type.2, Speed) %>%
+  na.omit()
+summary(pokemon2)
+```
+
+## Transmisión de datos de R a Python
+```{python}
+print(r.pokemon2.head())
+```
+

scripts/tema12/01-diamonds_cache/html/unnamed-chunk-10_4779ac4a62c84c0a676202a8ae084b0e.RData

@@ -0,0 +1,12 @@
+base
+reticulate
+tidyverse
+ggplot2
+tibble
+tidyr
+readr
+purrr
+dplyr
+stringr
+forcats
+bindrcpp

scripts/tema12/01-diamonds_cache/html/unnamed-chunk-10_4779ac4a62c84c0a676202a8ae084b0e.rdb

@@ -0,0 +1,36 @@
+---
+title: "Vuelos de NYC"
+author: "Curso de Estadística Descriptiva"
+date: "9/1/2019"
+output: html_document
+---
+
+```{r setup, include=FALSE}
+knitr::opts_chunk$set(echo = TRUE)
+library(reticulate)
+```
+
+## Vuelos de NYC
+
+```{r}
+data <- nycflights13::flights
+head(data)
+nrow(data)
+summary(data)
+```
+
+```{python}
+pydata = r.data
+pydata = pydata[pydata["dest"]=="ORD"]
+pydata = pydata[['carrier', 'dep_delay', 'arr_delay', 'origin']]
+pydata = pydata[pydata['arr_delay']<6*60]
+pydata = pydata.dropna()
+print(pydata.head())
+print(pydata.shape)
+```
+
+```{r}
+summary(py$pydata)
+boxplot(arr_delay~origin, data = py$pydata, main = "Retraso de los vuelo hacia Orlando desde NYC")
+```
+

scripts/tema12/01-diamonds_cache/html/unnamed-chunk-10_4779ac4a62c84c0a676202a8ae084b0e.rdx

@@ -0,0 +1,64 @@
+---
+title: "Coches"
+author: "Curso de Estadística Descriptiva"
+date: "9/1/2019"
+output: html_document
+---
+
+```{r setup, include=FALSE}
+knitr::opts_chunk$set(echo = TRUE, cache = TRUE)
+```
+
+## Análisis de los coches (mtcars)
+
+### Carga de datos
+```{python}
+from ggplot import mtcars
+data = mtcars
+data.index = data["name"]
+print(data.head())
+```
+
+### Medidas de centralización
+```{python}
+print(data.mean()) # Media por columnas
+print(data.mean(axis = 1)) # Media por filas
+print(data.median())
+print(mtcars.mode())
+```
+
+
+### Medidas vs distribuciones
+```{python}
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+plt.clf()
+norm_data = pd.DataFrame(np.random.normal(size=100000))
+norm_data.plot(kind="density", figsize=(10,10))
+plt.vlines(norm_data.mean(), ymin = 0, ymax = 0.4, linewidth=5.0, color = "green")
+plt.vlines(norm_data.median(), ymin = 0, ymax = 0.4, 
+linewidth = 2.0, color = "red")
+plt.show()
+
+
+plt.clf()
+skewed_data = pd.DataFrame(np.random.exponential(size=100000))
+skewed_data.plot(kind="density", figsize=(10,10), xlim = (-1,5))
+plt.vlines(skewed_data.mean(), ymin = 0, ymax = 1.0, linewidth=5.0, color = "green")
+plt.vlines(skewed_data.median(), ymin = 0, ymax = 1.0, 
+linewidth = 2.0, color = "red")
+plt.show()
+
+
+norm_data = np.random.normal(size = 50)
+outliers = np.random.normal(15, size = 3)
+combined_data = pd.DataFrame(np.concatenate((norm_data, outliers), axis = 0))
+
+combined_data.plot(kind="density", figsize=(10,10), xlim = (-5,20))
+plt.vlines(combined_data.mean(), ymin = 0, ymax = 0.3, linewidth=5.0, color = "green")
+plt.vlines(combined_data.median(), ymin = 0, ymax = 0.3, 
+linewidth = 2.0, color = "red")
+plt.show()
+```
+

scripts/tema12/01-diamonds_cache/html/unnamed-chunk-1_096a7a0b64254b3c70c246e7568ba470.RData

@@ -0,0 +1 @@
+base