├── Basic_Pandas_Test
    ├── Basic_Pandas_test.ipynb
    └── readme.md
├── CheatSheet - Exploración de datos usando Pandas
    ├── CheatSheet,  Exploración de datos usando Pandas.ipynb
    └── README.md
├── EDA Iris
    ├── Lab. EDA Iris .ipynb
    └── readme.md
├── Filtrado con Pandas
    ├── Técnicas de filtrado de datos con Pandas.ipynb
    └── readme.md
├── Librerias_EDA
    ├── EDA utilizando la librería de Python Sweetviz.ipynb
    ├── Librería Datatile .ipynb
    ├── README.md
    └── fast EDA.ipynb
├── Pandas Style.
    ├── Pandas-Style.ipynb
    └── readme.md
├── Pandas_Tricks 
    ├── Código
    │   ├── Trucos para usar en la librería pandas (parte1).ipynb
    │   ├── Trucos para usar en la librería pandas(parte2).ipynb
    │   ├── pivot_table().ipynb
    │   └── readme.md
    └── readme.md
├── README.md
├── Sales Data Analysis
    ├── -
    ├── CSV
    │   ├── README.md
    │   ├── Sales_April_2019.csv
    │   ├── Sales_August_2019.csv
    │   ├── Sales_December_2019.csv
    │   ├── Sales_February_2019.csv
    │   ├── Sales_January_2019.csv
    │   ├── Sales_July_2019.csv
    │   ├── Sales_June_2019.csv
    │   ├── Sales_March_2019.csv
    │   ├── Sales_May_2019.csv
    │   ├── Sales_November_2019.csv
    │   ├── Sales_October_2019.csv
    │   └── Sales_September_2019.csv
    ├── README.md
    └── Sales Data Analysis.ipynb
├── Series y dataframes
    ├── Series en Python.ipynb
    └── readme.md
├── Tabula
    ├── Tabula python.pdf
    └── readme.md
├── Titanic Dataset
    ├── EDA - Dataset Titanic.ipynb
    ├── Outliers.ipynb
    ├── Portada
    │   ├── -
    │   └── 2.png
    ├── README.md
    ├── Titanic ejercicio.ipynb
    ├── Titanic group by.ipynb
    ├── _Visualizar datos faltantes con missingno.ipynb
    └── titanic_train.csv
└── Web_scraping_BeautifulSoup
    ├── BeautifulSoup_Ejemplo_libros.ipynb
    └── readme.md


/Basic_Pandas_Test/Basic_Pandas_test.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |   "cells": [
  3 |     {
  4 |       "cell_type": "markdown",
  5 |       "metadata": {
  6 |         "id": "cJ19HeAGZnzw"
  7 |       },
  8 |       "source": [
  9 |         "# Basic Pandas Test"
 10 |       ]
 11 |     },
 12 |     {
 13 |       "cell_type": "code",
 14 |       "execution_count": null,
 15 |       "metadata": {
 16 |         "id": "ttELfGTVAAx_"
 17 |       },
 18 |       "outputs": [],
 19 |       "source": [
 20 |         "import pandas as pd\n",
 21 |         "url = 'https://raw.githubusercontent.com/bcamandone/Python_Analisis_datos/main/Titanic%20Dataset/titanic_train.csv'\n",
 22 |         "titanic = pd.read_csv(url)\n"
 23 |       ]
 24 |     },
 25 |     {
 26 |       "cell_type": "code",
 27 |       "execution_count": null,
 28 |       "metadata": {
 29 |         "cellView": "form",
 30 |         "id": "vSID9Bmj-MJH"
 31 |       },
 32 |       "outputs": [],
 33 |       "source": [
 34 |         "#@markdown ### Preguntas { display-mode: \"form\" }\n",
 35 |         "#@markdown 1. ¿Cuántas filas se muestran al ejecutar este código, asumiendo que el dataframe (titanic) contiene 1000 registros??\n",
 36 |         "\n",
 37 |         "     #@markdown data.head()\n",
 38 |         "\n",
 39 |         "#@markdown Marque la correcta:\n",
 40 |         "#@markdown  - a. 1\n",
 41 |         "#@markdown  - b. 5\n",
 42 |         "#@markdown  - c. 10\n",
 43 |         "#@markdown  - d. 100\n",
 44 |         "\n",
 45 |         "\n",
 46 |         "item_1 = \"Seleccionar respuesta\" # @param [\"a\", \"b\", \"c\", \"d\",\"Seleccionar respuesta\"]"
 47 |       ]
 48 |     },
 49 |     {
 50 |       "cell_type": "code",
 51 |       "execution_count": null,
 52 |       "metadata": {
 53 |         "cellView": "form",
 54 |         "id": "kpnyTCIu_M8q"
 55 |       },
 56 |       "outputs": [],
 57 |       "source": [
 58 |         "#@markdown{ display-mode: \"form\" }\n",
 59 |         "#@markdown 2.¿Qué instrucción me permite conocer el tamaño que tiene el Dataframe del titanic?\n",
 60 |         "\n",
 61 |         "\n",
 62 |         "#@markdown Marque la correcta:\n",
 63 |         "#@markdown  - a. len(titanic)\n",
 64 |         "#@markdown  - b. titanic.columns\n",
 65 |         "#@markdown  - c. titanic.shape\n",
 66 |         "\n",
 67 |         "\n",
 68 |         "\n",
 69 |         "item_2 = \"Seleccionar respuesta\" # @param [\"a\", \"b\", \"c\",\"Seleccionar respuesta\"]"
 70 |       ]
 71 |     },
 72 |     {
 73 |       "cell_type": "code",
 74 |       "execution_count": null,
 75 |       "metadata": {
 76 |         "cellView": "form",
 77 |         "id": "PmRHv-Q9DdVb"
 78 |       },
 79 |       "outputs": [],
 80 |       "source": [
 81 |         "#@markdown{ display-mode: \"form\" }\n",
 82 |         "#@markdown 3.Se cuenta con información en un archivo CSV, sin embargo al momento de crear este archivo los datos fueron separados no con comas (,) sino con punto y comas (;). ¿Qué instrucción me permite cargar esta data?\n",
 83 |         "\n",
 84 |         "\n",
 85 |         "\n",
 86 |         "#@markdown Marque la correcta:\n",
 87 |         "#@markdown  - a. titanic = pd.read_csv('titanic.csv', divide=';')\n",
 88 |         "#@markdown  - b. titanic = pd.read_csv('titanic.csv', separator=';')\n",
 89 |         "#@markdown  - c. titanic = pd.read_csv('titanic.csv', delimiter=';')\n",
 90 |         "\n",
 91 |         "\n",
 92 |         "\n",
 93 |         "item_3 = \"Seleccionar respuesta\" # @param [\"a\", \"b\", \"c\",\"Seleccionar respuesta\"]"
 94 |       ]
 95 |     },
 96 |     {
 97 |       "cell_type": "code",
 98 |       "execution_count": null,
 99 |       "metadata": {
100 |         "cellView": "form",
101 |         "id": "nbchipYuDnM3"
102 |       },
103 |       "outputs": [],
104 |       "source": [
105 |         "#@markdown{ display-mode: \"form\" }\n",
106 |         "#@markdown 4. ¿Cuál de las sentencias muestra la siguiente información del conjunto de datos?\n",
107 |         "\n",
108 |         "\n",
109 |         "\n",
110 |         "#@markdown Marque la correcta:\n",
111 |         "#@markdown  - a. titanic.info()\n",
112 |         "#@markdown  - b. titanic.summary()\n",
113 |         "#@markdown  - c. titanic.describe()\n",
114 |         "\n",
115 |         "\n",
116 |         "\n",
117 |         "item_4 = \"Seleccionar respuesta\" # @param [\"a\", \"b\", \"c\",\"Seleccionar respuesta\"]"
118 |       ]
119 |     },
120 |     {
121 |       "cell_type": "markdown",
122 |       "metadata": {
123 |         "id": "k_oXKh1AFACi"
124 |       },
125 |       "source": [
126 |         "![5.png](data:image/png;base64,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)"
127 |       ]
128 |     },
129 |     {
130 |       "cell_type": "code",
131 |       "execution_count": null,
132 |       "metadata": {
133 |         "cellView": "form",
134 |         "id": "WUXS656ODn67"
135 |       },
136 |       "outputs": [],
137 |       "source": [
138 |         "#@markdown{ display-mode: \"form\" }\n",
139 |         "#@markdown 5.¿Qué instrucción puedo utilizar para obtener los 10 últimos elementos del Dataframe titanic?\n",
140 |         "\n",
141 |         "\n",
142 |         "#@markdown Marque la correcta:\n",
143 |         "#@markdown  - a. titanic.last(10)\n",
144 |         "#@markdown  - b. titanic.tail(10)\n",
145 |         "#@markdown  - c. titanic.limit(10)\n",
146 |         "\n",
147 |         "\n",
148 |         "\n",
149 |         "item_5 = \"Seleccionar respuesta\" # @param [\"a\", \"b\", \"c\",\"Seleccionar respuesta\"]"
150 |       ]
151 |     },
152 |     {
153 |       "cell_type": "code",
154 |       "execution_count": null,
155 |       "metadata": {
156 |         "cellView": "form",
157 |         "id": "QPx5zVpYDogD"
158 |       },
159 |       "outputs": [],
160 |       "source": [
161 |         "#@markdown{ display-mode: \"form\" }\n",
162 |         "#@markdown 6.Obtener aquellos pasajeros que pagaron un ticket > 100, ¿Cuál es la instrucción que nos permite obtener este conjunto de datos?\n",
163 |         "\n",
164 |         "\n",
165 |         "\n",
166 |         "#@markdown Marque la correcta:\n",
167 |         "#@markdown  - a. titanic['fare' > 100]\n",
168 |         "#@markdown  - b. titanic['fare' < 100]\n",
169 |         "#@markdown  - c. titanic[titanic['fare'] > 100]\n",
170 |         "#@markdown  - c. titanic[titanic('fare') > 100]\n",
171 |         "\n",
172 |         "\n",
173 |         "\n",
174 |         "item_6 = \"Seleccionar respuesta\" # @param [\"a\", \"b\", \"c\",\"d\",\"Seleccionar respuesta\"]"
175 |       ]
176 |     },
177 |     {
178 |       "cell_type": "code",
179 |       "execution_count": null,
180 |       "metadata": {
181 |         "cellView": "form",
182 |         "id": "tSof1Sn1G4Zf"
183 |       },
184 |       "outputs": [],
185 |       "source": [
186 |         "#@markdown{ display-mode: \"form\" }\n",
187 |         "#@markdown 7.La siguiente linea de código: titanic.sort_values('fare') ordena el dataframe del titanic en base a la columna fare de mayor a menor\n",
188 |         "\n",
189 |         "\n",
190 |         "\n",
191 |         "#@markdown Marque la correcta:\n",
192 |         "#@markdown  - a. Verdadero\n",
193 |         "#@markdown  - b. Falso\n",
194 |         "\n",
195 |         "\n",
196 |         "item_7 = \"Seleccionar respuesta\" # @param [\"a\", \"b\",\"Seleccionar respuesta\"]"
197 |       ]
198 |     },
199 |     {
200 |       "cell_type": "code",
201 |       "execution_count": null,
202 |       "metadata": {
203 |         "cellView": "form",
204 |         "id": "pGIdlfNVHVcP"
205 |       },
206 |       "outputs": [],
207 |       "source": [
208 |         "#@markdown{ display-mode: \"form\" }\n",
209 |         "#@markdown 8.La siguiente linea de código titanic['Survived'].value_counts() me permite saber cuantos sobrevivientes tuvo el titanic\n",
210 |         "\n",
211 |         "\n",
212 |         "\n",
213 |         "#@markdown Marque la correcta:\n",
214 |         "#@markdown  - a. Verdadero\n",
215 |         "#@markdown  - b. Falso\n",
216 |         "\n",
217 |         "\n",
218 |         "\n",
219 |         "\n",
220 |         "item_8 = \"Seleccionar respuesta\" # @param [\"a\", \"b\",\"Seleccionar respuesta\"]"
221 |       ]
222 |     },
223 |     {
224 |       "cell_type": "code",
225 |       "execution_count": null,
226 |       "metadata": {
227 |         "cellView": "form",
228 |         "id": "MZBvJNaPIfMY"
229 |       },
230 |       "outputs": [],
231 |       "source": [
232 |         "#@markdown{ display-mode: \"form\" }\n",
233 |         "#@markdown 9.La siguiente linea de código: titanic.loc[titanic['Sex'] =='female','Fare'].mean() devuelve la tarifa que pagaron en promedio los hombres\n",
234 |         "\n",
235 |         "\n",
236 |         "\n",
237 |         "#@markdown Marque la correcta:\n",
238 |         "#@markdown  - a. Verdadero\n",
239 |         "#@markdown  - b. Falso\n",
240 |         "\n",
241 |         "\n",
242 |         "\n",
243 |         "\n",
244 |         "item_9 = \"Seleccionar respuesta\" # @param [\"a\", \"b\",\"Seleccionar respuesta\"]"
245 |       ]
246 |     },
247 |     {
248 |       "cell_type": "code",
249 |       "execution_count": null,
250 |       "metadata": {
251 |         "cellView": "form",
252 |         "id": "IH4s4Z6gIf7I"
253 |       },
254 |       "outputs": [],
255 |       "source": [
256 |         "#@markdown{ display-mode: \"form\" }\n",
257 |         "#@markdown 10.La siguiente linea de código: titanic.groupby('Sex').mean()['Age']) devuelve el promedio de edad agrupado por sexo\n",
258 |         "\n",
259 |         "\n",
260 |         "\n",
261 |         "#@markdown Marque la correcta:\n",
262 |         "#@markdown  - a. Verdadero\n",
263 |         "#@markdown  - b. Falso\n",
264 |         "\n",
265 |         "\n",
266 |         "\n",
267 |         "\n",
268 |         "item_10 = \"Seleccionar respuesta\" # @param [\"a\", \"b\",\"Seleccionar respuesta\"]"
269 |       ]
270 |     }
271 |   ],
272 |   "metadata": {
273 |     "colab": {
274 |       "provenance": []
275 |     },
276 |     "kernelspec": {
277 |       "display_name": "Python 3",
278 |       "name": "python3"
279 |     },
280 |     "language_info": {
281 |       "name": "python"
282 |     }
283 |   },
284 |   "nbformat": 4,
285 |   "nbformat_minor": 0
286 | }
287 | 


--------------------------------------------------------------------------------
/Basic_Pandas_Test/readme.md:
--------------------------------------------------------------------------------
 1 | 🐼 Test básico de Pandas - Pon a prueba tus conocimientos 🚀
 2 | 
 3 | ¿Estás aprendiendo Pandas y quieres poner a prueba tus conocimientos? ¡He diseñado un test interactivo de 10 preguntas en Google Colab! 
 4 | 
 5 | 📊 ¿Por qué Pandas?
 6 | Pandas es una biblioteca de Python ampliamente utilizada en ciencia de datos para la manipulación y análisis de datos.
 7 | 
 8 | 👩‍💻 ¿Cómo funciona?
 9 | Simplemente sigue este enlace [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/bcamandone/Python_Analisis_datos/blob/main/Basic_Pandas_Test/Basic_Pandas_test.ipynb)
10 | y ¡comienza a responder las preguntas!
11 | 
12 | 
13 | 
14 | 


--------------------------------------------------------------------------------
/CheatSheet - Exploración de datos usando Pandas/README.md:
--------------------------------------------------------------------------------
 1 | ## Exploración de datos usando Pandas
 2 | 
 3 | 
 4 | Este CheatSheet que realice en Jupyter notebook contiene código de ejemplo para ejecutar una Exploración de datos usando Pandas
 5 | 
 6 | El dataset que utilice es el famoso del Titanic!
 7 | 
 8 | El CheatSheet cuenta con 12 secciones:
 9 | 
10 | 
11 | 1. Lectura de los datos
12 | 
13 | 2. Obtener una primera vista de los datos
14 | 
15 | 3. Modificar el tipo de datos de una columna
16 | 
17 | 4. Renombrar una columna
18 | 
19 | 5. Ordenar
20 | 
21 | 6. Seleccionar y filtrar 
22 | 
23 | 7. Chequear duplicados
24 | 
25 | 8. Manejo de valores faltantes
26 | 
27 | 9. Crear una nueva columna
28 | 
29 | 10. Identificar valores únicos
30 | 
31 | 11. Realizar cálculos y agrupaciones
32 | 
33 | 12. Estadísticos básicos
34 | 
35 | 
36 | 👏 ¡Por favor, dame un ⭐️ si te gusta este repo!
37 | 


--------------------------------------------------------------------------------
/EDA Iris/readme.md:
--------------------------------------------------------------------------------
1 | 
2 | 


--------------------------------------------------------------------------------
/Filtrado con Pandas/readme.md:
--------------------------------------------------------------------------------
1 | ## Tecnicas de filtrado con pandas 🔍🔍
2 | 
3 | En el análisis de datos cotidiano con Python, consultar y filtrar datos es una de las tareas más comunes. Esto nos ayuda a extraer los datos específicos que necesitamos para nuestro análisis.
4 | 
5 | En este notebook vas a encontrar 6 técnicas de uso común de filtrado y consulta de datos.
6 | 


--------------------------------------------------------------------------------
/Librerias_EDA/EDA utilizando la librería de Python Sweetviz.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "8ea3099a",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as  pd\n"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 2,
 16 |    "id": "2c83fe77",
 17 |    "metadata": {},
 18 |    "outputs": [],
 19 |    "source": [
 20 |     "#Utilizamos pandas para importar el CSV\n",
 21 |     "df = pd.read_csv('Advertising.csv')"
 22 |    ]
 23 |   },
 24 |   {
 25 |    "cell_type": "code",
 26 |    "execution_count": 3,
 27 |    "id": "a54d842e",
 28 |    "metadata": {},
 29 |    "outputs": [],
 30 |    "source": [
 31 |     "#importamos la libreria sweetviz\n",
 32 |     "import sweetviz as sv"
 33 |    ]
 34 |   },
 35 |   {
 36 |    "cell_type": "code",
 37 |    "execution_count": 4,
 38 |    "id": "41594b26",
 39 |    "metadata": {},
 40 |    "outputs": [
 41 |     {
 42 |      "data": {
 43 |       "application/vnd.jupyter.widget-view+json": {
 44 |        "model_id": "ba70029db0a140ac94ab8790584f8351",
 45 |        "version_major": 2,
 46 |        "version_minor": 0
 47 |       },
 48 |       "text/plain": [
 49 |        "                                             |          | [  0%]   00:00 -> (? left)"
 50 |       ]
 51 |      },
 52 |      "metadata": {},
 53 |      "output_type": "display_data"
 54 |     }
 55 |    ],
 56 |    "source": [
 57 |     "#Analizamos el dataset\n",
 58 |     "reporte = sv.analyze(df)"
 59 |    ]
 60 |   },
 61 |   {
 62 |    "cell_type": "code",
 63 |    "execution_count": 5,
 64 |    "id": "db61fbdc",
 65 |    "metadata": {},
 66 |    "outputs": [
 67 |     {
 68 |      "name": "stdout",
 69 |      "output_type": "stream",
 70 |      "text": [
 71 |       "Report Advertising.html was generated! NOTEBOOK/COLAB USERS: the web browser MAY not pop up, regardless, the report IS saved in your notebook/colab files.\n"
 72 |      ]
 73 |     }
 74 |    ],
 75 |    "source": [
 76 |     "#Mostramos el informe\n",
 77 |     "reporte.show_html('Advertising.html')"
 78 |    ]
 79 |   },
 80 |   {
 81 |    "cell_type": "markdown",
 82 |    "id": "4bd7c5fa",
 83 |    "metadata": {},
 84 |    "source": [
 85 |     "By María Belén Camandone"
 86 |    ]
 87 |   }
 88 |  ],
 89 |  "metadata": {
 90 |   "kernelspec": {
 91 |    "display_name": "Python 3 (ipykernel)",
 92 |    "language": "python",
 93 |    "name": "python3"
 94 |   },
 95 |   "language_info": {
 96 |    "codemirror_mode": {
 97 |     "name": "ipython",
 98 |     "version": 3
 99 |    },
100 |    "file_extension": ".py",
101 |    "mimetype": "text/x-python",
102 |    "name": "python",
103 |    "nbconvert_exporter": "python",
104 |    "pygments_lexer": "ipython3",
105 |    "version": "3.9.13"
106 |   }
107 |  },
108 |  "nbformat": 4,
109 |  "nbformat_minor": 5
110 | }
111 | 


--------------------------------------------------------------------------------
/Librerias_EDA/Librería Datatile .ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 2,
  6 |    "id": "8ea3099a",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as  pd\n"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 3,
 16 |    "id": "2c83fe77",
 17 |    "metadata": {},
 18 |    "outputs": [],
 19 |    "source": [
 20 |     "#Utilizamos pandas para importar el CSV\n",
 21 |     "df = pd.read_csv('Advertising.csv')"
 22 |    ]
 23 |   },
 24 |   {
 25 |    "cell_type": "code",
 26 |    "execution_count": 4,
 27 |    "id": "7b13f36e",
 28 |    "metadata": {},
 29 |    "outputs": [
 30 |     {
 31 |      "data": {
 32 |       "text/html": [
 33 |        "<div>\n",
 34 |        "<style scoped>\n",
 35 |        "    .dataframe tbody tr th:only-of-type {\n",
 36 |        "        vertical-align: middle;\n",
 37 |        "    }\n",
 38 |        "\n",
 39 |        "    .dataframe tbody tr th {\n",
 40 |        "        vertical-align: top;\n",
 41 |        "    }\n",
 42 |        "\n",
 43 |        "    .dataframe thead th {\n",
 44 |        "        text-align: right;\n",
 45 |        "    }\n",
 46 |        "</style>\n",
 47 |        "<table border=\"1\" class=\"dataframe\">\n",
 48 |        "  <thead>\n",
 49 |        "    <tr style=\"text-align: right;\">\n",
 50 |        "      <th></th>\n",
 51 |        "      <th>TV</th>\n",
 52 |        "      <th>Radio</th>\n",
 53 |        "      <th>Newspaper</th>\n",
 54 |        "      <th>Sales</th>\n",
 55 |        "    </tr>\n",
 56 |        "  </thead>\n",
 57 |        "  <tbody>\n",
 58 |        "    <tr>\n",
 59 |        "      <th>0</th>\n",
 60 |        "      <td>230.1</td>\n",
 61 |        "      <td>37.8</td>\n",
 62 |        "      <td>69.2</td>\n",
 63 |        "      <td>22.1</td>\n",
 64 |        "    </tr>\n",
 65 |        "    <tr>\n",
 66 |        "      <th>1</th>\n",
 67 |        "      <td>44.5</td>\n",
 68 |        "      <td>39.3</td>\n",
 69 |        "      <td>45.1</td>\n",
 70 |        "      <td>10.4</td>\n",
 71 |        "    </tr>\n",
 72 |        "    <tr>\n",
 73 |        "      <th>2</th>\n",
 74 |        "      <td>17.2</td>\n",
 75 |        "      <td>45.9</td>\n",
 76 |        "      <td>69.3</td>\n",
 77 |        "      <td>9.3</td>\n",
 78 |        "    </tr>\n",
 79 |        "    <tr>\n",
 80 |        "      <th>3</th>\n",
 81 |        "      <td>151.5</td>\n",
 82 |        "      <td>41.3</td>\n",
 83 |        "      <td>58.5</td>\n",
 84 |        "      <td>18.5</td>\n",
 85 |        "    </tr>\n",
 86 |        "  </tbody>\n",
 87 |        "</table>\n",
 88 |        "</div>"
 89 |       ],
 90 |       "text/plain": [
 91 |        "      TV  Radio  Newspaper  Sales\n",
 92 |        "0  230.1   37.8       69.2   22.1\n",
 93 |        "1   44.5   39.3       45.1   10.4\n",
 94 |        "2   17.2   45.9       69.3    9.3\n",
 95 |        "3  151.5   41.3       58.5   18.5"
 96 |       ]
 97 |      },
 98 |      "execution_count": 4,
 99 |      "metadata": {},
100 |      "output_type": "execute_result"
101 |     }
102 |    ],
103 |    "source": [
104 |     "df.head(4)"
105 |    ]
106 |   },
107 |   {
108 |    "cell_type": "code",
109 |    "execution_count": 5,
110 |    "id": "a54d842e",
111 |    "metadata": {},
112 |    "outputs": [],
113 |    "source": [
114 |     "#importamos datatile\n",
115 |     "from datatile.summary.df import DataFrameSummary"
116 |    ]
117 |   },
118 |   {
119 |    "cell_type": "code",
120 |    "execution_count": 6,
121 |    "id": "41594b26",
122 |    "metadata": {},
123 |    "outputs": [],
124 |    "source": [
125 |     "#Analizamos el dataset\n",
126 |     "dff = DataFrameSummary(df)"
127 |    ]
128 |   },
129 |   {
130 |    "cell_type": "markdown",
131 |    "id": "cdcbd93d",
132 |    "metadata": {},
133 |    "source": [
134 |     "El método .summary() devuelve la cantidad y el porcentaje de valores faltantes, \n",
135 |     "la cantidad de valores únicos, el tipo de datos y las estadísticas de resumen para cada columna. "
136 |    ]
137 |   },
138 |   {
139 |    "cell_type": "code",
140 |    "execution_count": 11,
141 |    "id": "09ac9ca9",
142 |    "metadata": {},
143 |    "outputs": [
144 |     {
145 |      "data": {
146 |       "text/html": [
147 |        "<div>\n",
148 |        "<style scoped>\n",
149 |        "    .dataframe tbody tr th:only-of-type {\n",
150 |        "        vertical-align: middle;\n",
151 |        "    }\n",
152 |        "\n",
153 |        "    .dataframe tbody tr th {\n",
154 |        "        vertical-align: top;\n",
155 |        "    }\n",
156 |        "\n",
157 |        "    .dataframe thead th {\n",
158 |        "        text-align: right;\n",
159 |        "    }\n",
160 |        "</style>\n",
161 |        "<table border=\"1\" class=\"dataframe\">\n",
162 |        "  <thead>\n",
163 |        "    <tr style=\"text-align: right;\">\n",
164 |        "      <th></th>\n",
165 |        "      <th>TV</th>\n",
166 |        "      <th>Radio</th>\n",
167 |        "      <th>Newspaper</th>\n",
168 |        "      <th>Sales</th>\n",
169 |        "    </tr>\n",
170 |        "  </thead>\n",
171 |        "  <tbody>\n",
172 |        "    <tr>\n",
173 |        "      <th>count</th>\n",
174 |        "      <td>200.0</td>\n",
175 |        "      <td>200.0</td>\n",
176 |        "      <td>200.0</td>\n",
177 |        "      <td>200.0</td>\n",
178 |        "    </tr>\n",
179 |        "    <tr>\n",
180 |        "      <th>mean</th>\n",
181 |        "      <td>147.0425</td>\n",
182 |        "      <td>23.264</td>\n",
183 |        "      <td>30.554</td>\n",
184 |        "      <td>14.0225</td>\n",
185 |        "    </tr>\n",
186 |        "    <tr>\n",
187 |        "      <th>std</th>\n",
188 |        "      <td>85.854236</td>\n",
189 |        "      <td>14.846809</td>\n",
190 |        "      <td>21.778621</td>\n",
191 |        "      <td>5.217457</td>\n",
192 |        "    </tr>\n",
193 |        "    <tr>\n",
194 |        "      <th>min</th>\n",
195 |        "      <td>0.7</td>\n",
196 |        "      <td>0.0</td>\n",
197 |        "      <td>0.3</td>\n",
198 |        "      <td>1.6</td>\n",
199 |        "    </tr>\n",
200 |        "    <tr>\n",
201 |        "      <th>25%</th>\n",
202 |        "      <td>74.375</td>\n",
203 |        "      <td>9.975</td>\n",
204 |        "      <td>12.75</td>\n",
205 |        "      <td>10.375</td>\n",
206 |        "    </tr>\n",
207 |        "    <tr>\n",
208 |        "      <th>50%</th>\n",
209 |        "      <td>149.75</td>\n",
210 |        "      <td>22.9</td>\n",
211 |        "      <td>25.75</td>\n",
212 |        "      <td>12.9</td>\n",
213 |        "    </tr>\n",
214 |        "    <tr>\n",
215 |        "      <th>75%</th>\n",
216 |        "      <td>218.825</td>\n",
217 |        "      <td>36.525</td>\n",
218 |        "      <td>45.1</td>\n",
219 |        "      <td>17.4</td>\n",
220 |        "    </tr>\n",
221 |        "    <tr>\n",
222 |        "      <th>max</th>\n",
223 |        "      <td>296.4</td>\n",
224 |        "      <td>49.6</td>\n",
225 |        "      <td>114.0</td>\n",
226 |        "      <td>27.0</td>\n",
227 |        "    </tr>\n",
228 |        "    <tr>\n",
229 |        "      <th>counts</th>\n",
230 |        "      <td>200</td>\n",
231 |        "      <td>200</td>\n",
232 |        "      <td>200</td>\n",
233 |        "      <td>200</td>\n",
234 |        "    </tr>\n",
235 |        "    <tr>\n",
236 |        "      <th>uniques</th>\n",
237 |        "      <td>190</td>\n",
238 |        "      <td>167</td>\n",
239 |        "      <td>172</td>\n",
240 |        "      <td>121</td>\n",
241 |        "    </tr>\n",
242 |        "    <tr>\n",
243 |        "      <th>missing</th>\n",
244 |        "      <td>0</td>\n",
245 |        "      <td>0</td>\n",
246 |        "      <td>0</td>\n",
247 |        "      <td>0</td>\n",
248 |        "    </tr>\n",
249 |        "    <tr>\n",
250 |        "      <th>missing_perc</th>\n",
251 |        "      <td>0%</td>\n",
252 |        "      <td>0%</td>\n",
253 |        "      <td>0%</td>\n",
254 |        "      <td>0%</td>\n",
255 |        "    </tr>\n",
256 |        "    <tr>\n",
257 |        "      <th>types</th>\n",
258 |        "      <td>numeric</td>\n",
259 |        "      <td>numeric</td>\n",
260 |        "      <td>numeric</td>\n",
261 |        "      <td>numeric</td>\n",
262 |        "    </tr>\n",
263 |        "  </tbody>\n",
264 |        "</table>\n",
265 |        "</div>"
266 |       ],
267 |       "text/plain": [
268 |        "                     TV      Radio  Newspaper     Sales\n",
269 |        "count             200.0      200.0      200.0     200.0\n",
270 |        "mean           147.0425     23.264     30.554   14.0225\n",
271 |        "std           85.854236  14.846809  21.778621  5.217457\n",
272 |        "min                 0.7        0.0        0.3       1.6\n",
273 |        "25%              74.375      9.975      12.75    10.375\n",
274 |        "50%              149.75       22.9      25.75      12.9\n",
275 |        "75%             218.825     36.525       45.1      17.4\n",
276 |        "max               296.4       49.6      114.0      27.0\n",
277 |        "counts              200        200        200       200\n",
278 |        "uniques             190        167        172       121\n",
279 |        "missing               0          0          0         0\n",
280 |        "missing_perc         0%         0%         0%        0%\n",
281 |        "types           numeric    numeric    numeric   numeric"
282 |       ]
283 |      },
284 |      "execution_count": 11,
285 |      "metadata": {},
286 |      "output_type": "execute_result"
287 |     }
288 |    ],
289 |    "source": [
290 |     "\n",
291 |     "dff.summary()"
292 |    ]
293 |   },
294 |   {
295 |    "cell_type": "markdown",
296 |    "id": "1e0eac80",
297 |    "metadata": {},
298 |    "source": [
299 |     "También podemos obtener información solo para columnas seleccionadas. Esto es útil si el conjunto de datos es grande y lleva mucho tiempo calcular la información de todas las columnas, o si queremos analizar solo algunas columnas en particular. "
300 |    ]
301 |   },
302 |   {
303 |    "cell_type": "code",
304 |    "execution_count": 8,
305 |    "id": "c88b924b",
306 |    "metadata": {},
307 |    "outputs": [
308 |     {
309 |      "data": {
310 |       "text/plain": [
311 |        "mean                             147.0425\n",
312 |        "std                             85.854236\n",
313 |        "variance                      7370.949893\n",
314 |        "min                                   0.7\n",
315 |        "max                                 296.4\n",
316 |        "mode                                 17.2\n",
317 |        "5%                                 13.195\n",
318 |        "25%                                74.375\n",
319 |        "50%                                149.75\n",
320 |        "75%                               218.825\n",
321 |        "95%                               280.735\n",
322 |        "iqr                                144.45\n",
323 |        "kurtosis                        -1.226495\n",
324 |        "skewness                        -0.069853\n",
325 |        "sum                               29408.5\n",
326 |        "mad                              75.10465\n",
327 |        "cv                               0.583874\n",
328 |        "zeros_num                               0\n",
329 |        "zeros_perc                             0%\n",
330 |        "deviating_of_mean                       0\n",
331 |        "deviating_of_mean_perc                 0%\n",
332 |        "deviating_of_median                     0\n",
333 |        "deviating_of_median_perc               0%\n",
334 |        "top_correlations            Sales: 78.22%\n",
335 |        "counts                                200\n",
336 |        "uniques                               190\n",
337 |        "missing                                 0\n",
338 |        "missing_perc                           0%\n",
339 |        "types                             numeric\n",
340 |        "Name: TV, dtype: object"
341 |       ]
342 |      },
343 |      "execution_count": 8,
344 |      "metadata": {},
345 |      "output_type": "execute_result"
346 |     }
347 |    ],
348 |    "source": [
349 |     "dff['TV']"
350 |    ]
351 |   },
352 |   {
353 |    "cell_type": "markdown",
354 |    "id": "4bd7c5fa",
355 |    "metadata": {},
356 |    "source": [
357 |     "By María Belén Camandone"
358 |    ]
359 |   }
360 |  ],
361 |  "metadata": {
362 |   "kernelspec": {
363 |    "display_name": "Python 3 (ipykernel)",
364 |    "language": "python",
365 |    "name": "python3"
366 |   },
367 |   "language_info": {
368 |    "codemirror_mode": {
369 |     "name": "ipython",
370 |     "version": 3
371 |    },
372 |    "file_extension": ".py",
373 |    "mimetype": "text/x-python",
374 |    "name": "python",
375 |    "nbconvert_exporter": "python",
376 |    "pygments_lexer": "ipython3",
377 |    "version": "3.9.13"
378 |   }
379 |  },
380 |  "nbformat": 4,
381 |  "nbformat_minor": 5
382 | }
383 | 


--------------------------------------------------------------------------------
/Librerias_EDA/README.md:
--------------------------------------------------------------------------------
1 | ## EDA / Librerías 
2 | 
3 | En esta carpeta vas a poder encontrar código de ejemplo sobre librerías de python, que nos permiten en pocas líneas realizar un Análisis exploratorio de datos. 
4 | 


--------------------------------------------------------------------------------
/Pandas Style./readme.md:
--------------------------------------------------------------------------------
1 | ## Pandas Style 🐼 - Transformando nuestro dataset con estilo 😎 
2 | 
3 | Si trabajaste con Excel, seguro personalizaste tus hojas, agregaste colores a las celdas y marcaste cifras importantes. Sabías que eso también lo podes hacer en la librería Pandas? 
4 | 


--------------------------------------------------------------------------------
/Pandas_Tricks /Código/Trucos para usar en la librería pandas (parte1).ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 2,
  6 |    "id": "42bd20b2",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as pd\n",
 11 |     "import seaborn as sns"
 12 |    ]
 13 |   },
 14 |   {
 15 |    "cell_type": "markdown",
 16 |    "id": "a01a2bcc",
 17 |    "metadata": {},
 18 |    "source": [
 19 |     "### 1.Filtrar datos de manera sencilla con query()"
 20 |    ]
 21 |   },
 22 |   {
 23 |    "cell_type": "markdown",
 24 |    "id": "eefd5dfe",
 25 |    "metadata": {},
 26 |    "source": [
 27 |     "La función de Pandas query() nos brindará una forma concisa de seleccionar filas de un dataframe según la condición"
 28 |    ]
 29 |   },
 30 |   {
 31 |    "cell_type": "code",
 32 |    "execution_count": 3,
 33 |    "id": "3840cffa",
 34 |    "metadata": {},
 35 |    "outputs": [
 36 |     {
 37 |      "data": {
 38 |       "text/html": [
 39 |        "<div>\n",
 40 |        "<style scoped>\n",
 41 |        "    .dataframe tbody tr th:only-of-type {\n",
 42 |        "        vertical-align: middle;\n",
 43 |        "    }\n",
 44 |        "\n",
 45 |        "    .dataframe tbody tr th {\n",
 46 |        "        vertical-align: top;\n",
 47 |        "    }\n",
 48 |        "\n",
 49 |        "    .dataframe thead th {\n",
 50 |        "        text-align: right;\n",
 51 |        "    }\n",
 52 |        "</style>\n",
 53 |        "<table border=\"1\" class=\"dataframe\">\n",
 54 |        "  <thead>\n",
 55 |        "    <tr style=\"text-align: right;\">\n",
 56 |        "      <th></th>\n",
 57 |        "      <th>Producto</th>\n",
 58 |        "      <th>Ventas</th>\n",
 59 |        "    </tr>\n",
 60 |        "  </thead>\n",
 61 |        "  <tbody>\n",
 62 |        "    <tr>\n",
 63 |        "      <th>0</th>\n",
 64 |        "      <td>Leche</td>\n",
 65 |        "      <td>2700</td>\n",
 66 |        "    </tr>\n",
 67 |        "    <tr>\n",
 68 |        "      <th>2</th>\n",
 69 |        "      <td>Harina</td>\n",
 70 |        "      <td>3750</td>\n",
 71 |        "    </tr>\n",
 72 |        "  </tbody>\n",
 73 |        "</table>\n",
 74 |        "</div>"
 75 |       ],
 76 |       "text/plain": [
 77 |        "  Producto  Ventas\n",
 78 |        "0    Leche    2700\n",
 79 |        "2   Harina    3750"
 80 |       ]
 81 |      },
 82 |      "execution_count": 3,
 83 |      "metadata": {},
 84 |      "output_type": "execute_result"
 85 |     }
 86 |    ],
 87 |    "source": [
 88 |     "# dataset \n",
 89 |     "data = {'Producto': ['Leche', 'Manteca', 'Harina', 'Tomate'],\n",
 90 |     "        'Ventas': [2700, 2000, 3750, 1200]}\n",
 91 |     "df = pd.DataFrame(data)\n",
 92 |     "\n",
 93 |     "# Buscamos los valores de venta mayores a 2500\n",
 94 |     "ventas_mayores = df.query('Ventas > 2500')\n",
 95 |     "\n",
 96 |     "ventas_mayores"
 97 |    ]
 98 |   },
 99 |   {
100 |    "cell_type": "markdown",
101 |    "id": "ba2d3106",
102 |    "metadata": {},
103 |    "source": [
104 |     "### 2.Datos categóricos"
105 |    ]
106 |   },
107 |   {
108 |    "cell_type": "markdown",
109 |    "id": "79789080",
110 |    "metadata": {},
111 |    "source": [
112 |     "El uso del tipo de datos categóricos puede hacer que el análisis sea más eficiente y que sea más fácil trabajar con los datos, como por ejemplo a la hora de  aplicar un modelo de ML o filtrar fácilmente."
113 |    ]
114 |   },
115 |   {
116 |    "cell_type": "markdown",
117 |    "id": "db0477a7",
118 |    "metadata": {},
119 |    "source": [
120 |     "Supongamos que estamos trabajando con el dataset de un call center donde tenemos 3 categorías:\n",
121 |     "\n",
122 |     "    - Contactado\n",
123 |     "    \n",
124 |     "    - No contactado\n",
125 |     "    \n",
126 |     "    - Asesorado"
127 |    ]
128 |   },
129 |   {
130 |    "cell_type": "code",
131 |    "execution_count": 4,
132 |    "id": "6cdcea97",
133 |    "metadata": {},
134 |    "outputs": [
135 |     {
136 |      "name": "stdout",
137 |      "output_type": "stream",
138 |      "text": [
139 |       "0       Contactado\n",
140 |       "1        Asesorado\n",
141 |       "2       Contactado\n",
142 |       "3    No contactado\n",
143 |       "Name: Feedback, dtype: category\n",
144 |       "Categories (3, object): ['Asesorado', 'Contactado', 'No contactado']\n",
145 |       "0    1\n",
146 |       "1    0\n",
147 |       "2    1\n",
148 |       "3    2\n",
149 |       "dtype: int8\n"
150 |      ]
151 |     }
152 |    ],
153 |    "source": [
154 |     "# dataset \n",
155 |     "data1 = {'ID_Cliente': ['456231', '987443', '332167', '594361'],\n",
156 |     "        'Feedback': ['Contactado','Asesorado','Contactado','No contactado']}\n",
157 |     "df1 = pd.DataFrame(data1)\n",
158 |     "\n",
159 |     "# Convertimos la columna Feedback a tipo de dato categorico\n",
160 |     "df1['Feedback'] = df1['Feedback'].astype('category')\n",
161 |     "\n",
162 |     "print(df1['Feedback'])\n",
163 |     "print(df1['Feedback'].cat.codes)"
164 |    ]
165 |   },
166 |   {
167 |    "cell_type": "markdown",
168 |    "id": "2233d64d",
169 |    "metadata": {},
170 |    "source": [
171 |     "### 3.Agregación"
172 |    ]
173 |   },
174 |   {
175 |    "cell_type": "markdown",
176 |    "id": "b676d343",
177 |    "metadata": {},
178 |    "source": [
179 |     "Podemos utilizar la función agg para aplicar diferentes agregaciones a diferentes columnas de un DataFrame."
180 |    ]
181 |   },
182 |   {
183 |    "cell_type": "code",
184 |    "execution_count": 5,
185 |    "id": "0fbfdb63",
186 |    "metadata": {},
187 |    "outputs": [
188 |     {
189 |      "data": {
190 |       "text/html": [
191 |        "<div>\n",
192 |        "<style scoped>\n",
193 |        "    .dataframe tbody tr th:only-of-type {\n",
194 |        "        vertical-align: middle;\n",
195 |        "    }\n",
196 |        "\n",
197 |        "    .dataframe tbody tr th {\n",
198 |        "        vertical-align: top;\n",
199 |        "    }\n",
200 |        "\n",
201 |        "    .dataframe thead th {\n",
202 |        "        text-align: right;\n",
203 |        "    }\n",
204 |        "</style>\n",
205 |        "<table border=\"1\" class=\"dataframe\">\n",
206 |        "  <thead>\n",
207 |        "    <tr style=\"text-align: right;\">\n",
208 |        "      <th></th>\n",
209 |        "      <th>age</th>\n",
210 |        "      <th>fare</th>\n",
211 |        "    </tr>\n",
212 |        "  </thead>\n",
213 |        "  <tbody>\n",
214 |        "    <tr>\n",
215 |        "      <th>min</th>\n",
216 |        "      <td>0.420000</td>\n",
217 |        "      <td>NaN</td>\n",
218 |        "    </tr>\n",
219 |        "    <tr>\n",
220 |        "      <th>max</th>\n",
221 |        "      <td>80.000000</td>\n",
222 |        "      <td>NaN</td>\n",
223 |        "    </tr>\n",
224 |        "    <tr>\n",
225 |        "      <th>mean</th>\n",
226 |        "      <td>29.699118</td>\n",
227 |        "      <td>32.204208</td>\n",
228 |        "    </tr>\n",
229 |        "    <tr>\n",
230 |        "      <th>sum</th>\n",
231 |        "      <td>NaN</td>\n",
232 |        "      <td>28693.949300</td>\n",
233 |        "    </tr>\n",
234 |        "  </tbody>\n",
235 |        "</table>\n",
236 |        "</div>"
237 |       ],
238 |       "text/plain": [
239 |        "            age          fare\n",
240 |        "min    0.420000           NaN\n",
241 |        "max   80.000000           NaN\n",
242 |        "mean  29.699118     32.204208\n",
243 |        "sum         NaN  28693.949300"
244 |       ]
245 |      },
246 |      "execution_count": 5,
247 |      "metadata": {},
248 |      "output_type": "execute_result"
249 |     }
250 |    ],
251 |    "source": [
252 |     "df_titanic = sns.load_dataset('titanic')\n",
253 |     "\n",
254 |     "aggregaciones = df_titanic.agg({\n",
255 |     "    'age': ['min', 'max', 'mean'],\n",
256 |     "    'fare': ['sum', 'mean']\n",
257 |     "})\n",
258 |     "\n",
259 |     "agregaciones1 = pd.DataFrame(aggregaciones)\n",
260 |     "\n",
261 |     "agregaciones1"
262 |    ]
263 |   },
264 |   {
265 |    "cell_type": "markdown",
266 |    "id": "94ea2b2d",
267 |    "metadata": {},
268 |    "source": [
269 |     "### 4.Multi-Index"
270 |    ]
271 |   },
272 |   {
273 |    "cell_type": "markdown",
274 |    "id": "09b5a334",
275 |    "metadata": {},
276 |    "source": [
277 |     "Pandas tiene una herramienta llamada MultiIndex o indexación jerárquica. Te permite manejar datos con más de dos niveles, como en una tabla"
278 |    ]
279 |   },
280 |   {
281 |    "cell_type": "code",
282 |    "execution_count": 6,
283 |    "id": "b6a25094",
284 |    "metadata": {},
285 |    "outputs": [
286 |     {
287 |      "data": {
288 |       "text/html": [
289 |        "<div>\n",
290 |        "<style scoped>\n",
291 |        "    .dataframe tbody tr th:only-of-type {\n",
292 |        "        vertical-align: middle;\n",
293 |        "    }\n",
294 |        "\n",
295 |        "    .dataframe tbody tr th {\n",
296 |        "        vertical-align: top;\n",
297 |        "    }\n",
298 |        "\n",
299 |        "    .dataframe thead th {\n",
300 |        "        text-align: right;\n",
301 |        "    }\n",
302 |        "</style>\n",
303 |        "<table border=\"1\" class=\"dataframe\">\n",
304 |        "  <thead>\n",
305 |        "    <tr style=\"text-align: right;\">\n",
306 |        "      <th></th>\n",
307 |        "      <th></th>\n",
308 |        "      <th>Ventas</th>\n",
309 |        "    </tr>\n",
310 |        "    <tr>\n",
311 |        "      <th>Año</th>\n",
312 |        "      <th>Mes</th>\n",
313 |        "      <th></th>\n",
314 |        "    </tr>\n",
315 |        "  </thead>\n",
316 |        "  <tbody>\n",
317 |        "    <tr>\n",
318 |        "      <th rowspan=\"2\" valign=\"top\">2024</th>\n",
319 |        "      <th>1</th>\n",
320 |        "      <td>250000</td>\n",
321 |        "    </tr>\n",
322 |        "    <tr>\n",
323 |        "      <th>2</th>\n",
324 |        "      <td>300000</td>\n",
325 |        "    </tr>\n",
326 |        "    <tr>\n",
327 |        "      <th rowspan=\"4\" valign=\"top\">2023</th>\n",
328 |        "      <th>3</th>\n",
329 |        "      <td>400000</td>\n",
330 |        "    </tr>\n",
331 |        "    <tr>\n",
332 |        "      <th>4</th>\n",
333 |        "      <td>500000</td>\n",
334 |        "    </tr>\n",
335 |        "    <tr>\n",
336 |        "      <th>5</th>\n",
337 |        "      <td>324000</td>\n",
338 |        "    </tr>\n",
339 |        "    <tr>\n",
340 |        "      <th>6</th>\n",
341 |        "      <td>127000</td>\n",
342 |        "    </tr>\n",
343 |        "  </tbody>\n",
344 |        "</table>\n",
345 |        "</div>"
346 |       ],
347 |       "text/plain": [
348 |        "          Ventas\n",
349 |        "Año  Mes        \n",
350 |        "2024 1    250000\n",
351 |        "     2    300000\n",
352 |        "2023 3    400000\n",
353 |        "     4    500000\n",
354 |        "     5    324000\n",
355 |        "     6    127000"
356 |       ]
357 |      },
358 |      "execution_count": 6,
359 |      "metadata": {},
360 |      "output_type": "execute_result"
361 |     }
362 |    ],
363 |    "source": [
364 |     "# dataset\n",
365 |     "data3 = {\n",
366 |     "    'Año': [2024, 2024, 2023, 2023,2023,2023],\n",
367 |     "    'Mes': ['1', '2', '3', '4','5','6'],\n",
368 |     "    'Ventas': [250000, 300000, 400000, 500000,324000,127000]\n",
369 |     "}\n",
370 |     "\n",
371 |     "df3 = pd.DataFrame(data3)\n",
372 |     "\n",
373 |     "# Set MultiIndex\n",
374 |     "df3.set_index(['Año', 'Mes'], inplace=True)\n",
375 |     "\n",
376 |     "df3"
377 |    ]
378 |   },
379 |   {
380 |    "cell_type": "markdown",
381 |    "id": "da3bbe39",
382 |    "metadata": {},
383 |    "source": [
384 |     "### 5.Filtrar con el método isin"
385 |    ]
386 |   },
387 |   {
388 |    "cell_type": "markdown",
389 |    "id": "af33b645",
390 |    "metadata": {},
391 |    "source": [
392 |     "Podemos utilizar el método isin para filtrar filas según una lista de valores.\n",
393 |     "Este método es útil cuando trabajamos con datos categóricos y deseamos seleccionar filas que pertenecen a determinadas categorías. \n",
394 |     "Es más conciso que utilizar múltiples condiciones lógicas con el operador &."
395 |    ]
396 |   },
397 |   {
398 |    "cell_type": "code",
399 |    "execution_count": 7,
400 |    "id": "a6711ee7",
401 |    "metadata": {},
402 |    "outputs": [],
403 |    "source": [
404 |     "titanic_filtrado = df_titanic[df_titanic['class'].isin(['First', 'Second'])]"
405 |    ]
406 |   },
407 |   {
408 |    "cell_type": "code",
409 |    "execution_count": 8,
410 |    "id": "ca4403d4",
411 |    "metadata": {},
412 |    "outputs": [
413 |     {
414 |      "data": {
415 |       "text/html": [
416 |        "<div>\n",
417 |        "<style scoped>\n",
418 |        "    .dataframe tbody tr th:only-of-type {\n",
419 |        "        vertical-align: middle;\n",
420 |        "    }\n",
421 |        "\n",
422 |        "    .dataframe tbody tr th {\n",
423 |        "        vertical-align: top;\n",
424 |        "    }\n",
425 |        "\n",
426 |        "    .dataframe thead th {\n",
427 |        "        text-align: right;\n",
428 |        "    }\n",
429 |        "</style>\n",
430 |        "<table border=\"1\" class=\"dataframe\">\n",
431 |        "  <thead>\n",
432 |        "    <tr style=\"text-align: right;\">\n",
433 |        "      <th></th>\n",
434 |        "      <th>survived</th>\n",
435 |        "      <th>pclass</th>\n",
436 |        "      <th>sex</th>\n",
437 |        "      <th>age</th>\n",
438 |        "      <th>sibsp</th>\n",
439 |        "      <th>parch</th>\n",
440 |        "      <th>fare</th>\n",
441 |        "      <th>embarked</th>\n",
442 |        "      <th>class</th>\n",
443 |        "      <th>who</th>\n",
444 |        "      <th>adult_male</th>\n",
445 |        "      <th>deck</th>\n",
446 |        "      <th>embark_town</th>\n",
447 |        "      <th>alive</th>\n",
448 |        "      <th>alone</th>\n",
449 |        "    </tr>\n",
450 |        "  </thead>\n",
451 |        "  <tbody>\n",
452 |        "    <tr>\n",
453 |        "      <th>1</th>\n",
454 |        "      <td>1</td>\n",
455 |        "      <td>1</td>\n",
456 |        "      <td>female</td>\n",
457 |        "      <td>38.0</td>\n",
458 |        "      <td>1</td>\n",
459 |        "      <td>0</td>\n",
460 |        "      <td>71.2833</td>\n",
461 |        "      <td>C</td>\n",
462 |        "      <td>First</td>\n",
463 |        "      <td>woman</td>\n",
464 |        "      <td>False</td>\n",
465 |        "      <td>C</td>\n",
466 |        "      <td>Cherbourg</td>\n",
467 |        "      <td>yes</td>\n",
468 |        "      <td>False</td>\n",
469 |        "    </tr>\n",
470 |        "    <tr>\n",
471 |        "      <th>3</th>\n",
472 |        "      <td>1</td>\n",
473 |        "      <td>1</td>\n",
474 |        "      <td>female</td>\n",
475 |        "      <td>35.0</td>\n",
476 |        "      <td>1</td>\n",
477 |        "      <td>0</td>\n",
478 |        "      <td>53.1000</td>\n",
479 |        "      <td>S</td>\n",
480 |        "      <td>First</td>\n",
481 |        "      <td>woman</td>\n",
482 |        "      <td>False</td>\n",
483 |        "      <td>C</td>\n",
484 |        "      <td>Southampton</td>\n",
485 |        "      <td>yes</td>\n",
486 |        "      <td>False</td>\n",
487 |        "    </tr>\n",
488 |        "    <tr>\n",
489 |        "      <th>6</th>\n",
490 |        "      <td>0</td>\n",
491 |        "      <td>1</td>\n",
492 |        "      <td>male</td>\n",
493 |        "      <td>54.0</td>\n",
494 |        "      <td>0</td>\n",
495 |        "      <td>0</td>\n",
496 |        "      <td>51.8625</td>\n",
497 |        "      <td>S</td>\n",
498 |        "      <td>First</td>\n",
499 |        "      <td>man</td>\n",
500 |        "      <td>True</td>\n",
501 |        "      <td>E</td>\n",
502 |        "      <td>Southampton</td>\n",
503 |        "      <td>no</td>\n",
504 |        "      <td>True</td>\n",
505 |        "    </tr>\n",
506 |        "    <tr>\n",
507 |        "      <th>9</th>\n",
508 |        "      <td>1</td>\n",
509 |        "      <td>2</td>\n",
510 |        "      <td>female</td>\n",
511 |        "      <td>14.0</td>\n",
512 |        "      <td>1</td>\n",
513 |        "      <td>0</td>\n",
514 |        "      <td>30.0708</td>\n",
515 |        "      <td>C</td>\n",
516 |        "      <td>Second</td>\n",
517 |        "      <td>child</td>\n",
518 |        "      <td>False</td>\n",
519 |        "      <td>NaN</td>\n",
520 |        "      <td>Cherbourg</td>\n",
521 |        "      <td>yes</td>\n",
522 |        "      <td>False</td>\n",
523 |        "    </tr>\n",
524 |        "    <tr>\n",
525 |        "      <th>11</th>\n",
526 |        "      <td>1</td>\n",
527 |        "      <td>1</td>\n",
528 |        "      <td>female</td>\n",
529 |        "      <td>58.0</td>\n",
530 |        "      <td>0</td>\n",
531 |        "      <td>0</td>\n",
532 |        "      <td>26.5500</td>\n",
533 |        "      <td>S</td>\n",
534 |        "      <td>First</td>\n",
535 |        "      <td>woman</td>\n",
536 |        "      <td>False</td>\n",
537 |        "      <td>C</td>\n",
538 |        "      <td>Southampton</td>\n",
539 |        "      <td>yes</td>\n",
540 |        "      <td>True</td>\n",
541 |        "    </tr>\n",
542 |        "  </tbody>\n",
543 |        "</table>\n",
544 |        "</div>"
545 |       ],
546 |       "text/plain": [
547 |        "    survived  pclass     sex   age  sibsp  parch     fare embarked   class  \\\n",
548 |        "1          1       1  female  38.0      1      0  71.2833        C   First   \n",
549 |        "3          1       1  female  35.0      1      0  53.1000        S   First   \n",
550 |        "6          0       1    male  54.0      0      0  51.8625        S   First   \n",
551 |        "9          1       2  female  14.0      1      0  30.0708        C  Second   \n",
552 |        "11         1       1  female  58.0      0      0  26.5500        S   First   \n",
553 |        "\n",
554 |        "      who  adult_male deck  embark_town alive  alone  \n",
555 |        "1   woman       False    C    Cherbourg   yes  False  \n",
556 |        "3   woman       False    C  Southampton   yes  False  \n",
557 |        "6     man        True    E  Southampton    no   True  \n",
558 |        "9   child       False  NaN    Cherbourg   yes  False  \n",
559 |        "11  woman       False    C  Southampton   yes   True  "
560 |       ]
561 |      },
562 |      "execution_count": 8,
563 |      "metadata": {},
564 |      "output_type": "execute_result"
565 |     }
566 |    ],
567 |    "source": [
568 |     "titanic_filtrado.head()"
569 |    ]
570 |   }
571 |  ],
572 |  "metadata": {
573 |   "kernelspec": {
574 |    "display_name": "Python 3 (ipykernel)",
575 |    "language": "python",
576 |    "name": "python3"
577 |   },
578 |   "language_info": {
579 |    "codemirror_mode": {
580 |     "name": "ipython",
581 |     "version": 3
582 |    },
583 |    "file_extension": ".py",
584 |    "mimetype": "text/x-python",
585 |    "name": "python",
586 |    "nbconvert_exporter": "python",
587 |    "pygments_lexer": "ipython3",
588 |    "version": "3.11.4"
589 |   }
590 |  },
591 |  "nbformat": 4,
592 |  "nbformat_minor": 5
593 | }
594 | 


--------------------------------------------------------------------------------
/Pandas_Tricks /Código/Trucos para usar en la librería pandas(parte2).ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |  "cells": [
   3 |   {
   4 |    "cell_type": "code",
   5 |    "execution_count": 73,
   6 |    "id": "5bd69ad6",
   7 |    "metadata": {},
   8 |    "outputs": [],
   9 |    "source": [
  10 |     "import pandas as pd\n",
  11 |     "import seaborn as sns"
  12 |    ]
  13 |   },
  14 |   {
  15 |    "cell_type": "code",
  16 |    "execution_count": 74,
  17 |    "id": "47f83173",
  18 |    "metadata": {},
  19 |    "outputs": [
  20 |     {
  21 |      "data": {
  22 |       "text/html": [
  23 |        "<div>\n",
  24 |        "<style scoped>\n",
  25 |        "    .dataframe tbody tr th:only-of-type {\n",
  26 |        "        vertical-align: middle;\n",
  27 |        "    }\n",
  28 |        "\n",
  29 |        "    .dataframe tbody tr th {\n",
  30 |        "        vertical-align: top;\n",
  31 |        "    }\n",
  32 |        "\n",
  33 |        "    .dataframe thead th {\n",
  34 |        "        text-align: right;\n",
  35 |        "    }\n",
  36 |        "</style>\n",
  37 |        "<table border=\"1\" class=\"dataframe\">\n",
  38 |        "  <thead>\n",
  39 |        "    <tr style=\"text-align: right;\">\n",
  40 |        "      <th></th>\n",
  41 |        "      <th>survived</th>\n",
  42 |        "      <th>pclass</th>\n",
  43 |        "      <th>sex</th>\n",
  44 |        "      <th>age</th>\n",
  45 |        "      <th>sibsp</th>\n",
  46 |        "      <th>parch</th>\n",
  47 |        "      <th>fare</th>\n",
  48 |        "      <th>embarked</th>\n",
  49 |        "      <th>class</th>\n",
  50 |        "      <th>who</th>\n",
  51 |        "      <th>adult_male</th>\n",
  52 |        "      <th>deck</th>\n",
  53 |        "      <th>embark_town</th>\n",
  54 |        "      <th>alive</th>\n",
  55 |        "      <th>alone</th>\n",
  56 |        "    </tr>\n",
  57 |        "  </thead>\n",
  58 |        "  <tbody>\n",
  59 |        "    <tr>\n",
  60 |        "      <th>0</th>\n",
  61 |        "      <td>0</td>\n",
  62 |        "      <td>3</td>\n",
  63 |        "      <td>male</td>\n",
  64 |        "      <td>22.0</td>\n",
  65 |        "      <td>1</td>\n",
  66 |        "      <td>0</td>\n",
  67 |        "      <td>7.2500</td>\n",
  68 |        "      <td>S</td>\n",
  69 |        "      <td>Third</td>\n",
  70 |        "      <td>man</td>\n",
  71 |        "      <td>True</td>\n",
  72 |        "      <td>NaN</td>\n",
  73 |        "      <td>Southampton</td>\n",
  74 |        "      <td>no</td>\n",
  75 |        "      <td>False</td>\n",
  76 |        "    </tr>\n",
  77 |        "    <tr>\n",
  78 |        "      <th>1</th>\n",
  79 |        "      <td>1</td>\n",
  80 |        "      <td>1</td>\n",
  81 |        "      <td>female</td>\n",
  82 |        "      <td>38.0</td>\n",
  83 |        "      <td>1</td>\n",
  84 |        "      <td>0</td>\n",
  85 |        "      <td>71.2833</td>\n",
  86 |        "      <td>C</td>\n",
  87 |        "      <td>First</td>\n",
  88 |        "      <td>woman</td>\n",
  89 |        "      <td>False</td>\n",
  90 |        "      <td>C</td>\n",
  91 |        "      <td>Cherbourg</td>\n",
  92 |        "      <td>yes</td>\n",
  93 |        "      <td>False</td>\n",
  94 |        "    </tr>\n",
  95 |        "    <tr>\n",
  96 |        "      <th>2</th>\n",
  97 |        "      <td>1</td>\n",
  98 |        "      <td>3</td>\n",
  99 |        "      <td>female</td>\n",
 100 |        "      <td>26.0</td>\n",
 101 |        "      <td>0</td>\n",
 102 |        "      <td>0</td>\n",
 103 |        "      <td>7.9250</td>\n",
 104 |        "      <td>S</td>\n",
 105 |        "      <td>Third</td>\n",
 106 |        "      <td>woman</td>\n",
 107 |        "      <td>False</td>\n",
 108 |        "      <td>NaN</td>\n",
 109 |        "      <td>Southampton</td>\n",
 110 |        "      <td>yes</td>\n",
 111 |        "      <td>True</td>\n",
 112 |        "    </tr>\n",
 113 |        "    <tr>\n",
 114 |        "      <th>3</th>\n",
 115 |        "      <td>1</td>\n",
 116 |        "      <td>1</td>\n",
 117 |        "      <td>female</td>\n",
 118 |        "      <td>35.0</td>\n",
 119 |        "      <td>1</td>\n",
 120 |        "      <td>0</td>\n",
 121 |        "      <td>53.1000</td>\n",
 122 |        "      <td>S</td>\n",
 123 |        "      <td>First</td>\n",
 124 |        "      <td>woman</td>\n",
 125 |        "      <td>False</td>\n",
 126 |        "      <td>C</td>\n",
 127 |        "      <td>Southampton</td>\n",
 128 |        "      <td>yes</td>\n",
 129 |        "      <td>False</td>\n",
 130 |        "    </tr>\n",
 131 |        "    <tr>\n",
 132 |        "      <th>4</th>\n",
 133 |        "      <td>0</td>\n",
 134 |        "      <td>3</td>\n",
 135 |        "      <td>male</td>\n",
 136 |        "      <td>35.0</td>\n",
 137 |        "      <td>0</td>\n",
 138 |        "      <td>0</td>\n",
 139 |        "      <td>8.0500</td>\n",
 140 |        "      <td>S</td>\n",
 141 |        "      <td>Third</td>\n",
 142 |        "      <td>man</td>\n",
 143 |        "      <td>True</td>\n",
 144 |        "      <td>NaN</td>\n",
 145 |        "      <td>Southampton</td>\n",
 146 |        "      <td>no</td>\n",
 147 |        "      <td>True</td>\n",
 148 |        "    </tr>\n",
 149 |        "  </tbody>\n",
 150 |        "</table>\n",
 151 |        "</div>"
 152 |       ],
 153 |       "text/plain": [
 154 |        "   survived  pclass     sex   age  sibsp  parch     fare embarked  class  \\\n",
 155 |        "0         0       3    male  22.0      1      0   7.2500        S  Third   \n",
 156 |        "1         1       1  female  38.0      1      0  71.2833        C  First   \n",
 157 |        "2         1       3  female  26.0      0      0   7.9250        S  Third   \n",
 158 |        "3         1       1  female  35.0      1      0  53.1000        S  First   \n",
 159 |        "4         0       3    male  35.0      0      0   8.0500        S  Third   \n",
 160 |        "\n",
 161 |        "     who  adult_male deck  embark_town alive  alone  \n",
 162 |        "0    man        True  NaN  Southampton    no  False  \n",
 163 |        "1  woman       False    C    Cherbourg   yes  False  \n",
 164 |        "2  woman       False  NaN  Southampton   yes   True  \n",
 165 |        "3  woman       False    C  Southampton   yes  False  \n",
 166 |        "4    man        True  NaN  Southampton    no   True  "
 167 |       ]
 168 |      },
 169 |      "execution_count": 74,
 170 |      "metadata": {},
 171 |      "output_type": "execute_result"
 172 |     }
 173 |    ],
 174 |    "source": [
 175 |     "df = sns.load_dataset('titanic')\n",
 176 |     "df.head()"
 177 |    ]
 178 |   },
 179 |   {
 180 |    "cell_type": "markdown",
 181 |    "id": "82bf88db",
 182 |    "metadata": {},
 183 |    "source": [
 184 |     "# 1) Cut()"
 185 |    ]
 186 |   },
 187 |   {
 188 |    "cell_type": "markdown",
 189 |    "id": "78de0b8d",
 190 |    "metadata": {},
 191 |    "source": [
 192 |     "cut() es increíblemente útil para agrupar datos numéricos en intervalos discretos.\n",
 193 |     "\n",
 194 |     "Vamos a  clasificar a las personas en diferentes grupos de edad. cut() simplifica este proceso creando contenedores personalizados y asignando etiquetas en consecuencia:"
 195 |    ]
 196 |   },
 197 |   {
 198 |    "cell_type": "code",
 199 |    "execution_count": 75,
 200 |    "id": "8ec37fc1",
 201 |    "metadata": {},
 202 |    "outputs": [
 203 |     {
 204 |      "data": {
 205 |       "text/html": [
 206 |        "<div>\n",
 207 |        "<style scoped>\n",
 208 |        "    .dataframe tbody tr th:only-of-type {\n",
 209 |        "        vertical-align: middle;\n",
 210 |        "    }\n",
 211 |        "\n",
 212 |        "    .dataframe tbody tr th {\n",
 213 |        "        vertical-align: top;\n",
 214 |        "    }\n",
 215 |        "\n",
 216 |        "    .dataframe thead th {\n",
 217 |        "        text-align: right;\n",
 218 |        "    }\n",
 219 |        "</style>\n",
 220 |        "<table border=\"1\" class=\"dataframe\">\n",
 221 |        "  <thead>\n",
 222 |        "    <tr style=\"text-align: right;\">\n",
 223 |        "      <th></th>\n",
 224 |        "      <th>survived</th>\n",
 225 |        "      <th>pclass</th>\n",
 226 |        "      <th>sex</th>\n",
 227 |        "      <th>age</th>\n",
 228 |        "      <th>sibsp</th>\n",
 229 |        "      <th>parch</th>\n",
 230 |        "      <th>fare</th>\n",
 231 |        "      <th>embarked</th>\n",
 232 |        "      <th>class</th>\n",
 233 |        "      <th>who</th>\n",
 234 |        "      <th>adult_male</th>\n",
 235 |        "      <th>deck</th>\n",
 236 |        "      <th>embark_town</th>\n",
 237 |        "      <th>alive</th>\n",
 238 |        "      <th>alone</th>\n",
 239 |        "      <th>Age Group</th>\n",
 240 |        "    </tr>\n",
 241 |        "  </thead>\n",
 242 |        "  <tbody>\n",
 243 |        "    <tr>\n",
 244 |        "      <th>0</th>\n",
 245 |        "      <td>0</td>\n",
 246 |        "      <td>3</td>\n",
 247 |        "      <td>male</td>\n",
 248 |        "      <td>22.0</td>\n",
 249 |        "      <td>1</td>\n",
 250 |        "      <td>0</td>\n",
 251 |        "      <td>7.2500</td>\n",
 252 |        "      <td>S</td>\n",
 253 |        "      <td>Third</td>\n",
 254 |        "      <td>man</td>\n",
 255 |        "      <td>True</td>\n",
 256 |        "      <td>NaN</td>\n",
 257 |        "      <td>Southampton</td>\n",
 258 |        "      <td>no</td>\n",
 259 |        "      <td>False</td>\n",
 260 |        "      <td>0-30</td>\n",
 261 |        "    </tr>\n",
 262 |        "    <tr>\n",
 263 |        "      <th>1</th>\n",
 264 |        "      <td>1</td>\n",
 265 |        "      <td>1</td>\n",
 266 |        "      <td>female</td>\n",
 267 |        "      <td>38.0</td>\n",
 268 |        "      <td>1</td>\n",
 269 |        "      <td>0</td>\n",
 270 |        "      <td>71.2833</td>\n",
 271 |        "      <td>C</td>\n",
 272 |        "      <td>First</td>\n",
 273 |        "      <td>woman</td>\n",
 274 |        "      <td>False</td>\n",
 275 |        "      <td>C</td>\n",
 276 |        "      <td>Cherbourg</td>\n",
 277 |        "      <td>yes</td>\n",
 278 |        "      <td>False</td>\n",
 279 |        "      <td>31-40</td>\n",
 280 |        "    </tr>\n",
 281 |        "    <tr>\n",
 282 |        "      <th>2</th>\n",
 283 |        "      <td>1</td>\n",
 284 |        "      <td>3</td>\n",
 285 |        "      <td>female</td>\n",
 286 |        "      <td>26.0</td>\n",
 287 |        "      <td>0</td>\n",
 288 |        "      <td>0</td>\n",
 289 |        "      <td>7.9250</td>\n",
 290 |        "      <td>S</td>\n",
 291 |        "      <td>Third</td>\n",
 292 |        "      <td>woman</td>\n",
 293 |        "      <td>False</td>\n",
 294 |        "      <td>NaN</td>\n",
 295 |        "      <td>Southampton</td>\n",
 296 |        "      <td>yes</td>\n",
 297 |        "      <td>True</td>\n",
 298 |        "      <td>0-30</td>\n",
 299 |        "    </tr>\n",
 300 |        "    <tr>\n",
 301 |        "      <th>3</th>\n",
 302 |        "      <td>1</td>\n",
 303 |        "      <td>1</td>\n",
 304 |        "      <td>female</td>\n",
 305 |        "      <td>35.0</td>\n",
 306 |        "      <td>1</td>\n",
 307 |        "      <td>0</td>\n",
 308 |        "      <td>53.1000</td>\n",
 309 |        "      <td>S</td>\n",
 310 |        "      <td>First</td>\n",
 311 |        "      <td>woman</td>\n",
 312 |        "      <td>False</td>\n",
 313 |        "      <td>C</td>\n",
 314 |        "      <td>Southampton</td>\n",
 315 |        "      <td>yes</td>\n",
 316 |        "      <td>False</td>\n",
 317 |        "      <td>31-40</td>\n",
 318 |        "    </tr>\n",
 319 |        "    <tr>\n",
 320 |        "      <th>4</th>\n",
 321 |        "      <td>0</td>\n",
 322 |        "      <td>3</td>\n",
 323 |        "      <td>male</td>\n",
 324 |        "      <td>35.0</td>\n",
 325 |        "      <td>0</td>\n",
 326 |        "      <td>0</td>\n",
 327 |        "      <td>8.0500</td>\n",
 328 |        "      <td>S</td>\n",
 329 |        "      <td>Third</td>\n",
 330 |        "      <td>man</td>\n",
 331 |        "      <td>True</td>\n",
 332 |        "      <td>NaN</td>\n",
 333 |        "      <td>Southampton</td>\n",
 334 |        "      <td>no</td>\n",
 335 |        "      <td>True</td>\n",
 336 |        "      <td>31-40</td>\n",
 337 |        "    </tr>\n",
 338 |        "  </tbody>\n",
 339 |        "</table>\n",
 340 |        "</div>"
 341 |       ],
 342 |       "text/plain": [
 343 |        "   survived  pclass     sex   age  sibsp  parch     fare embarked  class  \\\n",
 344 |        "0         0       3    male  22.0      1      0   7.2500        S  Third   \n",
 345 |        "1         1       1  female  38.0      1      0  71.2833        C  First   \n",
 346 |        "2         1       3  female  26.0      0      0   7.9250        S  Third   \n",
 347 |        "3         1       1  female  35.0      1      0  53.1000        S  First   \n",
 348 |        "4         0       3    male  35.0      0      0   8.0500        S  Third   \n",
 349 |        "\n",
 350 |        "     who  adult_male deck  embark_town alive  alone Age Group  \n",
 351 |        "0    man        True  NaN  Southampton    no  False      0-30  \n",
 352 |        "1  woman       False    C    Cherbourg   yes  False     31-40  \n",
 353 |        "2  woman       False  NaN  Southampton   yes   True      0-30  \n",
 354 |        "3  woman       False    C  Southampton   yes  False     31-40  \n",
 355 |        "4    man        True  NaN  Southampton    no   True     31-40  "
 356 |       ]
 357 |      },
 358 |      "execution_count": 75,
 359 |      "metadata": {},
 360 |      "output_type": "execute_result"
 361 |     }
 362 |    ],
 363 |    "source": [
 364 |     "bins = [0, 30, 40, 50, 60, 100]\n",
 365 |     "labels = ['0-30', '31-40', '41-50', '51-60', '61-100']\n",
 366 |     "\n",
 367 |     "# Creamos una nueva columna Age Group y usamos cut\n",
 368 |     "df['Age Group'] = pd.cut(df['age'], bins=bins, labels=labels)\n",
 369 |     "df.head()"
 370 |    ]
 371 |   },
 372 |   {
 373 |    "cell_type": "markdown",
 374 |    "id": "0c69884a",
 375 |    "metadata": {},
 376 |    "source": [
 377 |     "# 2) Filtrar en negativo "
 378 |    ]
 379 |   },
 380 |   {
 381 |    "cell_type": "markdown",
 382 |    "id": "1865e428",
 383 |    "metadata": {},
 384 |    "source": [
 385 |     "El operador ~ en Pandas se utiliza para filtrar en negativo, es decir, para seleccionar las filas que no cumplen con una condición determinada."
 386 |    ]
 387 |   },
 388 |   {
 389 |    "cell_type": "code",
 390 |    "execution_count": 76,
 391 |    "id": "dc9d4143",
 392 |    "metadata": {},
 393 |    "outputs": [
 394 |     {
 395 |      "data": {
 396 |       "text/html": [
 397 |        "<div>\n",
 398 |        "<style scoped>\n",
 399 |        "    .dataframe tbody tr th:only-of-type {\n",
 400 |        "        vertical-align: middle;\n",
 401 |        "    }\n",
 402 |        "\n",
 403 |        "    .dataframe tbody tr th {\n",
 404 |        "        vertical-align: top;\n",
 405 |        "    }\n",
 406 |        "\n",
 407 |        "    .dataframe thead th {\n",
 408 |        "        text-align: right;\n",
 409 |        "    }\n",
 410 |        "</style>\n",
 411 |        "<table border=\"1\" class=\"dataframe\">\n",
 412 |        "  <thead>\n",
 413 |        "    <tr style=\"text-align: right;\">\n",
 414 |        "      <th></th>\n",
 415 |        "      <th>survived</th>\n",
 416 |        "      <th>pclass</th>\n",
 417 |        "      <th>sex</th>\n",
 418 |        "      <th>age</th>\n",
 419 |        "      <th>sibsp</th>\n",
 420 |        "      <th>parch</th>\n",
 421 |        "      <th>fare</th>\n",
 422 |        "      <th>embarked</th>\n",
 423 |        "      <th>class</th>\n",
 424 |        "      <th>who</th>\n",
 425 |        "      <th>adult_male</th>\n",
 426 |        "      <th>deck</th>\n",
 427 |        "      <th>embark_town</th>\n",
 428 |        "      <th>alive</th>\n",
 429 |        "      <th>alone</th>\n",
 430 |        "      <th>Age Group</th>\n",
 431 |        "    </tr>\n",
 432 |        "  </thead>\n",
 433 |        "  <tbody>\n",
 434 |        "    <tr>\n",
 435 |        "      <th>0</th>\n",
 436 |        "      <td>0</td>\n",
 437 |        "      <td>3</td>\n",
 438 |        "      <td>male</td>\n",
 439 |        "      <td>22.0</td>\n",
 440 |        "      <td>1</td>\n",
 441 |        "      <td>0</td>\n",
 442 |        "      <td>7.2500</td>\n",
 443 |        "      <td>S</td>\n",
 444 |        "      <td>Third</td>\n",
 445 |        "      <td>man</td>\n",
 446 |        "      <td>True</td>\n",
 447 |        "      <td>NaN</td>\n",
 448 |        "      <td>Southampton</td>\n",
 449 |        "      <td>no</td>\n",
 450 |        "      <td>False</td>\n",
 451 |        "      <td>0-30</td>\n",
 452 |        "    </tr>\n",
 453 |        "    <tr>\n",
 454 |        "      <th>4</th>\n",
 455 |        "      <td>0</td>\n",
 456 |        "      <td>3</td>\n",
 457 |        "      <td>male</td>\n",
 458 |        "      <td>35.0</td>\n",
 459 |        "      <td>0</td>\n",
 460 |        "      <td>0</td>\n",
 461 |        "      <td>8.0500</td>\n",
 462 |        "      <td>S</td>\n",
 463 |        "      <td>Third</td>\n",
 464 |        "      <td>man</td>\n",
 465 |        "      <td>True</td>\n",
 466 |        "      <td>NaN</td>\n",
 467 |        "      <td>Southampton</td>\n",
 468 |        "      <td>no</td>\n",
 469 |        "      <td>True</td>\n",
 470 |        "      <td>31-40</td>\n",
 471 |        "    </tr>\n",
 472 |        "    <tr>\n",
 473 |        "      <th>5</th>\n",
 474 |        "      <td>0</td>\n",
 475 |        "      <td>3</td>\n",
 476 |        "      <td>male</td>\n",
 477 |        "      <td>NaN</td>\n",
 478 |        "      <td>0</td>\n",
 479 |        "      <td>0</td>\n",
 480 |        "      <td>8.4583</td>\n",
 481 |        "      <td>Q</td>\n",
 482 |        "      <td>Third</td>\n",
 483 |        "      <td>man</td>\n",
 484 |        "      <td>True</td>\n",
 485 |        "      <td>NaN</td>\n",
 486 |        "      <td>Queenstown</td>\n",
 487 |        "      <td>no</td>\n",
 488 |        "      <td>True</td>\n",
 489 |        "      <td>NaN</td>\n",
 490 |        "    </tr>\n",
 491 |        "    <tr>\n",
 492 |        "      <th>6</th>\n",
 493 |        "      <td>0</td>\n",
 494 |        "      <td>1</td>\n",
 495 |        "      <td>male</td>\n",
 496 |        "      <td>54.0</td>\n",
 497 |        "      <td>0</td>\n",
 498 |        "      <td>0</td>\n",
 499 |        "      <td>51.8625</td>\n",
 500 |        "      <td>S</td>\n",
 501 |        "      <td>First</td>\n",
 502 |        "      <td>man</td>\n",
 503 |        "      <td>True</td>\n",
 504 |        "      <td>E</td>\n",
 505 |        "      <td>Southampton</td>\n",
 506 |        "      <td>no</td>\n",
 507 |        "      <td>True</td>\n",
 508 |        "      <td>51-60</td>\n",
 509 |        "    </tr>\n",
 510 |        "    <tr>\n",
 511 |        "      <th>7</th>\n",
 512 |        "      <td>0</td>\n",
 513 |        "      <td>3</td>\n",
 514 |        "      <td>male</td>\n",
 515 |        "      <td>2.0</td>\n",
 516 |        "      <td>3</td>\n",
 517 |        "      <td>1</td>\n",
 518 |        "      <td>21.0750</td>\n",
 519 |        "      <td>S</td>\n",
 520 |        "      <td>Third</td>\n",
 521 |        "      <td>child</td>\n",
 522 |        "      <td>False</td>\n",
 523 |        "      <td>NaN</td>\n",
 524 |        "      <td>Southampton</td>\n",
 525 |        "      <td>no</td>\n",
 526 |        "      <td>False</td>\n",
 527 |        "      <td>0-30</td>\n",
 528 |        "    </tr>\n",
 529 |        "    <tr>\n",
 530 |        "      <th>...</th>\n",
 531 |        "      <td>...</td>\n",
 532 |        "      <td>...</td>\n",
 533 |        "      <td>...</td>\n",
 534 |        "      <td>...</td>\n",
 535 |        "      <td>...</td>\n",
 536 |        "      <td>...</td>\n",
 537 |        "      <td>...</td>\n",
 538 |        "      <td>...</td>\n",
 539 |        "      <td>...</td>\n",
 540 |        "      <td>...</td>\n",
 541 |        "      <td>...</td>\n",
 542 |        "      <td>...</td>\n",
 543 |        "      <td>...</td>\n",
 544 |        "      <td>...</td>\n",
 545 |        "      <td>...</td>\n",
 546 |        "      <td>...</td>\n",
 547 |        "    </tr>\n",
 548 |        "    <tr>\n",
 549 |        "      <th>884</th>\n",
 550 |        "      <td>0</td>\n",
 551 |        "      <td>3</td>\n",
 552 |        "      <td>male</td>\n",
 553 |        "      <td>25.0</td>\n",
 554 |        "      <td>0</td>\n",
 555 |        "      <td>0</td>\n",
 556 |        "      <td>7.0500</td>\n",
 557 |        "      <td>S</td>\n",
 558 |        "      <td>Third</td>\n",
 559 |        "      <td>man</td>\n",
 560 |        "      <td>True</td>\n",
 561 |        "      <td>NaN</td>\n",
 562 |        "      <td>Southampton</td>\n",
 563 |        "      <td>no</td>\n",
 564 |        "      <td>True</td>\n",
 565 |        "      <td>0-30</td>\n",
 566 |        "    </tr>\n",
 567 |        "    <tr>\n",
 568 |        "      <th>885</th>\n",
 569 |        "      <td>0</td>\n",
 570 |        "      <td>3</td>\n",
 571 |        "      <td>female</td>\n",
 572 |        "      <td>39.0</td>\n",
 573 |        "      <td>0</td>\n",
 574 |        "      <td>5</td>\n",
 575 |        "      <td>29.1250</td>\n",
 576 |        "      <td>Q</td>\n",
 577 |        "      <td>Third</td>\n",
 578 |        "      <td>woman</td>\n",
 579 |        "      <td>False</td>\n",
 580 |        "      <td>NaN</td>\n",
 581 |        "      <td>Queenstown</td>\n",
 582 |        "      <td>no</td>\n",
 583 |        "      <td>False</td>\n",
 584 |        "      <td>31-40</td>\n",
 585 |        "    </tr>\n",
 586 |        "    <tr>\n",
 587 |        "      <th>886</th>\n",
 588 |        "      <td>0</td>\n",
 589 |        "      <td>2</td>\n",
 590 |        "      <td>male</td>\n",
 591 |        "      <td>27.0</td>\n",
 592 |        "      <td>0</td>\n",
 593 |        "      <td>0</td>\n",
 594 |        "      <td>13.0000</td>\n",
 595 |        "      <td>S</td>\n",
 596 |        "      <td>Second</td>\n",
 597 |        "      <td>man</td>\n",
 598 |        "      <td>True</td>\n",
 599 |        "      <td>NaN</td>\n",
 600 |        "      <td>Southampton</td>\n",
 601 |        "      <td>no</td>\n",
 602 |        "      <td>True</td>\n",
 603 |        "      <td>0-30</td>\n",
 604 |        "    </tr>\n",
 605 |        "    <tr>\n",
 606 |        "      <th>888</th>\n",
 607 |        "      <td>0</td>\n",
 608 |        "      <td>3</td>\n",
 609 |        "      <td>female</td>\n",
 610 |        "      <td>NaN</td>\n",
 611 |        "      <td>1</td>\n",
 612 |        "      <td>2</td>\n",
 613 |        "      <td>23.4500</td>\n",
 614 |        "      <td>S</td>\n",
 615 |        "      <td>Third</td>\n",
 616 |        "      <td>woman</td>\n",
 617 |        "      <td>False</td>\n",
 618 |        "      <td>NaN</td>\n",
 619 |        "      <td>Southampton</td>\n",
 620 |        "      <td>no</td>\n",
 621 |        "      <td>False</td>\n",
 622 |        "      <td>NaN</td>\n",
 623 |        "    </tr>\n",
 624 |        "    <tr>\n",
 625 |        "      <th>890</th>\n",
 626 |        "      <td>0</td>\n",
 627 |        "      <td>3</td>\n",
 628 |        "      <td>male</td>\n",
 629 |        "      <td>32.0</td>\n",
 630 |        "      <td>0</td>\n",
 631 |        "      <td>0</td>\n",
 632 |        "      <td>7.7500</td>\n",
 633 |        "      <td>Q</td>\n",
 634 |        "      <td>Third</td>\n",
 635 |        "      <td>man</td>\n",
 636 |        "      <td>True</td>\n",
 637 |        "      <td>NaN</td>\n",
 638 |        "      <td>Queenstown</td>\n",
 639 |        "      <td>no</td>\n",
 640 |        "      <td>True</td>\n",
 641 |        "      <td>31-40</td>\n",
 642 |        "    </tr>\n",
 643 |        "  </tbody>\n",
 644 |        "</table>\n",
 645 |        "<p>549 rows × 16 columns</p>\n",
 646 |        "</div>"
 647 |       ],
 648 |       "text/plain": [
 649 |        "     survived  pclass     sex   age  sibsp  parch     fare embarked   class  \\\n",
 650 |        "0           0       3    male  22.0      1      0   7.2500        S   Third   \n",
 651 |        "4           0       3    male  35.0      0      0   8.0500        S   Third   \n",
 652 |        "5           0       3    male   NaN      0      0   8.4583        Q   Third   \n",
 653 |        "6           0       1    male  54.0      0      0  51.8625        S   First   \n",
 654 |        "7           0       3    male   2.0      3      1  21.0750        S   Third   \n",
 655 |        "..        ...     ...     ...   ...    ...    ...      ...      ...     ...   \n",
 656 |        "884         0       3    male  25.0      0      0   7.0500        S   Third   \n",
 657 |        "885         0       3  female  39.0      0      5  29.1250        Q   Third   \n",
 658 |        "886         0       2    male  27.0      0      0  13.0000        S  Second   \n",
 659 |        "888         0       3  female   NaN      1      2  23.4500        S   Third   \n",
 660 |        "890         0       3    male  32.0      0      0   7.7500        Q   Third   \n",
 661 |        "\n",
 662 |        "       who  adult_male deck  embark_town alive  alone Age Group  \n",
 663 |        "0      man        True  NaN  Southampton    no  False      0-30  \n",
 664 |        "4      man        True  NaN  Southampton    no   True     31-40  \n",
 665 |        "5      man        True  NaN   Queenstown    no   True       NaN  \n",
 666 |        "6      man        True    E  Southampton    no   True     51-60  \n",
 667 |        "7    child       False  NaN  Southampton    no  False      0-30  \n",
 668 |        "..     ...         ...  ...          ...   ...    ...       ...  \n",
 669 |        "884    man        True  NaN  Southampton    no   True      0-30  \n",
 670 |        "885  woman       False  NaN   Queenstown    no  False     31-40  \n",
 671 |        "886    man        True  NaN  Southampton    no   True      0-30  \n",
 672 |        "888  woman       False  NaN  Southampton    no  False       NaN  \n",
 673 |        "890    man        True  NaN   Queenstown    no   True     31-40  \n",
 674 |        "\n",
 675 |        "[549 rows x 16 columns]"
 676 |       ]
 677 |      },
 678 |      "execution_count": 76,
 679 |      "metadata": {},
 680 |      "output_type": "execute_result"
 681 |     }
 682 |    ],
 683 |    "source": [
 684 |     "# Filtrar las filas donde el valor de la columna 'alive' no sea yes\n",
 685 |     "df_filtrado = df[~(df['alive'] =='yes')]\n",
 686 |     "\n",
 687 |     "df_filtrado\n"
 688 |    ]
 689 |   },
 690 |   {
 691 |    "cell_type": "markdown",
 692 |    "id": "93d51977",
 693 |    "metadata": {},
 694 |    "source": [
 695 |     "# 3) Crosstab() "
 696 |    ]
 697 |   },
 698 |   {
 699 |    "cell_type": "markdown",
 700 |    "id": "1ae8c8b9",
 701 |    "metadata": {},
 702 |    "source": [
 703 |     "La función crosstab() proporciona una manera poderosa (y súper simple) de explorar las relaciones entre diferentes variables en un conjunto de datos."
 704 |    ]
 705 |   },
 706 |   {
 707 |    "cell_type": "code",
 708 |    "execution_count": 77,
 709 |    "id": "4809b239",
 710 |    "metadata": {},
 711 |    "outputs": [
 712 |     {
 713 |      "data": {
 714 |       "text/html": [
 715 |        "<div>\n",
 716 |        "<style scoped>\n",
 717 |        "    .dataframe tbody tr th:only-of-type {\n",
 718 |        "        vertical-align: middle;\n",
 719 |        "    }\n",
 720 |        "\n",
 721 |        "    .dataframe tbody tr th {\n",
 722 |        "        vertical-align: top;\n",
 723 |        "    }\n",
 724 |        "\n",
 725 |        "    .dataframe thead th {\n",
 726 |        "        text-align: right;\n",
 727 |        "    }\n",
 728 |        "</style>\n",
 729 |        "<table border=\"1\" class=\"dataframe\">\n",
 730 |        "  <thead>\n",
 731 |        "    <tr style=\"text-align: right;\">\n",
 732 |        "      <th>pclass</th>\n",
 733 |        "      <th>1</th>\n",
 734 |        "      <th>2</th>\n",
 735 |        "      <th>3</th>\n",
 736 |        "    </tr>\n",
 737 |        "    <tr>\n",
 738 |        "      <th>alive</th>\n",
 739 |        "      <th></th>\n",
 740 |        "      <th></th>\n",
 741 |        "      <th></th>\n",
 742 |        "    </tr>\n",
 743 |        "  </thead>\n",
 744 |        "  <tbody>\n",
 745 |        "    <tr>\n",
 746 |        "      <th>no</th>\n",
 747 |        "      <td>80</td>\n",
 748 |        "      <td>97</td>\n",
 749 |        "      <td>372</td>\n",
 750 |        "    </tr>\n",
 751 |        "    <tr>\n",
 752 |        "      <th>yes</th>\n",
 753 |        "      <td>136</td>\n",
 754 |        "      <td>87</td>\n",
 755 |        "      <td>119</td>\n",
 756 |        "    </tr>\n",
 757 |        "  </tbody>\n",
 758 |        "</table>\n",
 759 |        "</div>"
 760 |       ],
 761 |       "text/plain": [
 762 |        "pclass    1   2    3\n",
 763 |        "alive               \n",
 764 |        "no       80  97  372\n",
 765 |        "yes     136  87  119"
 766 |       ]
 767 |      },
 768 |      "execution_count": 77,
 769 |      "metadata": {},
 770 |      "output_type": "execute_result"
 771 |     }
 772 |    ],
 773 |    "source": [
 774 |     "cross_table = pd.crosstab(df['alive'], df['pclass'])\n",
 775 |     "cross_table"
 776 |    ]
 777 |   },
 778 |   {
 779 |    "cell_type": "markdown",
 780 |    "id": "3bfaba10",
 781 |    "metadata": {},
 782 |    "source": [
 783 |     "# 4) Dividir una columna"
 784 |    ]
 785 |   },
 786 |   {
 787 |    "cell_type": "markdown",
 788 |    "id": "6d13cf14",
 789 |    "metadata": {},
 790 |    "source": [
 791 |     "Supongamos que queremos dividir la columna «Country» en dos columnas usando el espacio como separador:"
 792 |    ]
 793 |   },
 794 |   {
 795 |    "cell_type": "code",
 796 |    "execution_count": 78,
 797 |    "id": "b1c970b2",
 798 |    "metadata": {},
 799 |    "outputs": [
 800 |     {
 801 |      "data": {
 802 |       "text/html": [
 803 |        "<div>\n",
 804 |        "<style scoped>\n",
 805 |        "    .dataframe tbody tr th:only-of-type {\n",
 806 |        "        vertical-align: middle;\n",
 807 |        "    }\n",
 808 |        "\n",
 809 |        "    .dataframe tbody tr th {\n",
 810 |        "        vertical-align: top;\n",
 811 |        "    }\n",
 812 |        "\n",
 813 |        "    .dataframe thead th {\n",
 814 |        "        text-align: right;\n",
 815 |        "    }\n",
 816 |        "</style>\n",
 817 |        "<table border=\"1\" class=\"dataframe\">\n",
 818 |        "  <thead>\n",
 819 |        "    <tr style=\"text-align: right;\">\n",
 820 |        "      <th></th>\n",
 821 |        "      <th>Revenue</th>\n",
 822 |        "      <th>Employees</th>\n",
 823 |        "      <th>City</th>\n",
 824 |        "      <th>Country</th>\n",
 825 |        "    </tr>\n",
 826 |        "    <tr>\n",
 827 |        "      <th>Company</th>\n",
 828 |        "      <th></th>\n",
 829 |        "      <th></th>\n",
 830 |        "      <th></th>\n",
 831 |        "      <th></th>\n",
 832 |        "    </tr>\n",
 833 |        "  </thead>\n",
 834 |        "  <tbody>\n",
 835 |        "    <tr>\n",
 836 |        "      <th>Apple</th>\n",
 837 |        "      <td>274515</td>\n",
 838 |        "      <td>147000</td>\n",
 839 |        "      <td>California</td>\n",
 840 |        "      <td>United States</td>\n",
 841 |        "    </tr>\n",
 842 |        "    <tr>\n",
 843 |        "      <th>Samsung Electronics</th>\n",
 844 |        "      <td>200734</td>\n",
 845 |        "      <td>267937</td>\n",
 846 |        "      <td>Suwon</td>\n",
 847 |        "      <td>South Korea</td>\n",
 848 |        "    </tr>\n",
 849 |        "    <tr>\n",
 850 |        "      <th>Alphabet</th>\n",
 851 |        "      <td>182527</td>\n",
 852 |        "      <td>135301</td>\n",
 853 |        "      <td>California</td>\n",
 854 |        "      <td>United States</td>\n",
 855 |        "    </tr>\n",
 856 |        "    <tr>\n",
 857 |        "      <th>Foxconn</th>\n",
 858 |        "      <td>181945</td>\n",
 859 |        "      <td>878429</td>\n",
 860 |        "      <td>New Taipei City</td>\n",
 861 |        "      <td>Taiwan</td>\n",
 862 |        "    </tr>\n",
 863 |        "    <tr>\n",
 864 |        "      <th>Microsoft</th>\n",
 865 |        "      <td>143015</td>\n",
 866 |        "      <td>163000</td>\n",
 867 |        "      <td>Washington</td>\n",
 868 |        "      <td>United States</td>\n",
 869 |        "    </tr>\n",
 870 |        "  </tbody>\n",
 871 |        "</table>\n",
 872 |        "</div>"
 873 |       ],
 874 |       "text/plain": [
 875 |        "                     Revenue  Employees             City        Country\n",
 876 |        "Company                                                                \n",
 877 |        "Apple                 274515     147000       California  United States\n",
 878 |        "Samsung Electronics   200734     267937            Suwon    South Korea\n",
 879 |        "Alphabet              182527     135301       California  United States\n",
 880 |        "Foxconn               181945     878429  New Taipei City         Taiwan\n",
 881 |        "Microsoft             143015     163000       Washington  United States"
 882 |       ]
 883 |      },
 884 |      "execution_count": 78,
 885 |      "metadata": {},
 886 |      "output_type": "execute_result"
 887 |     }
 888 |    ],
 889 |    "source": [
 890 |     "df_tech = pd.read_csv('tech.csv', delimiter='\\t', index_col='Company')\n",
 891 |     "df_tech.head()"
 892 |    ]
 893 |   },
 894 |   {
 895 |    "cell_type": "code",
 896 |    "execution_count": 79,
 897 |    "id": "83f97c25",
 898 |    "metadata": {},
 899 |    "outputs": [
 900 |     {
 901 |      "data": {
 902 |       "text/html": [
 903 |        "<div>\n",
 904 |        "<style scoped>\n",
 905 |        "    .dataframe tbody tr th:only-of-type {\n",
 906 |        "        vertical-align: middle;\n",
 907 |        "    }\n",
 908 |        "\n",
 909 |        "    .dataframe tbody tr th {\n",
 910 |        "        vertical-align: top;\n",
 911 |        "    }\n",
 912 |        "\n",
 913 |        "    .dataframe thead th {\n",
 914 |        "        text-align: right;\n",
 915 |        "    }\n",
 916 |        "</style>\n",
 917 |        "<table border=\"1\" class=\"dataframe\">\n",
 918 |        "  <thead>\n",
 919 |        "    <tr style=\"text-align: right;\">\n",
 920 |        "      <th></th>\n",
 921 |        "      <th>0</th>\n",
 922 |        "      <th>1</th>\n",
 923 |        "    </tr>\n",
 924 |        "    <tr>\n",
 925 |        "      <th>Company</th>\n",
 926 |        "      <th></th>\n",
 927 |        "      <th></th>\n",
 928 |        "    </tr>\n",
 929 |        "  </thead>\n",
 930 |        "  <tbody>\n",
 931 |        "    <tr>\n",
 932 |        "      <th>Apple</th>\n",
 933 |        "      <td>United</td>\n",
 934 |        "      <td>States</td>\n",
 935 |        "    </tr>\n",
 936 |        "    <tr>\n",
 937 |        "      <th>Samsung Electronics</th>\n",
 938 |        "      <td>South</td>\n",
 939 |        "      <td>Korea</td>\n",
 940 |        "    </tr>\n",
 941 |        "    <tr>\n",
 942 |        "      <th>Alphabet</th>\n",
 943 |        "      <td>United</td>\n",
 944 |        "      <td>States</td>\n",
 945 |        "    </tr>\n",
 946 |        "    <tr>\n",
 947 |        "      <th>Foxconn</th>\n",
 948 |        "      <td>Taiwan</td>\n",
 949 |        "      <td>None</td>\n",
 950 |        "    </tr>\n",
 951 |        "    <tr>\n",
 952 |        "      <th>Microsoft</th>\n",
 953 |        "      <td>United</td>\n",
 954 |        "      <td>States</td>\n",
 955 |        "    </tr>\n",
 956 |        "    <tr>\n",
 957 |        "      <th>Huawei</th>\n",
 958 |        "      <td>China</td>\n",
 959 |        "      <td>None</td>\n",
 960 |        "    </tr>\n",
 961 |        "    <tr>\n",
 962 |        "      <th>Dell Technologies</th>\n",
 963 |        "      <td>United</td>\n",
 964 |        "      <td>States</td>\n",
 965 |        "    </tr>\n",
 966 |        "    <tr>\n",
 967 |        "      <th>Facebook</th>\n",
 968 |        "      <td>United</td>\n",
 969 |        "      <td>States</td>\n",
 970 |        "    </tr>\n",
 971 |        "    <tr>\n",
 972 |        "      <th>Sony</th>\n",
 973 |        "      <td>Japan</td>\n",
 974 |        "      <td>None</td>\n",
 975 |        "    </tr>\n",
 976 |        "    <tr>\n",
 977 |        "      <th>Hitachi</th>\n",
 978 |        "      <td>Japan</td>\n",
 979 |        "      <td>None</td>\n",
 980 |        "    </tr>\n",
 981 |        "    <tr>\n",
 982 |        "      <th>Intel</th>\n",
 983 |        "      <td>United</td>\n",
 984 |        "      <td>States</td>\n",
 985 |        "    </tr>\n",
 986 |        "    <tr>\n",
 987 |        "      <th>IBM</th>\n",
 988 |        "      <td>United</td>\n",
 989 |        "      <td>States</td>\n",
 990 |        "    </tr>\n",
 991 |        "    <tr>\n",
 992 |        "      <th>Tencent</th>\n",
 993 |        "      <td>China</td>\n",
 994 |        "      <td>None</td>\n",
 995 |        "    </tr>\n",
 996 |        "    <tr>\n",
 997 |        "      <th>Panasonic</th>\n",
 998 |        "      <td>Japan</td>\n",
 999 |        "      <td>None</td>\n",
1000 |        "    </tr>\n",
1001 |        "    <tr>\n",
1002 |        "      <th>Lenovo</th>\n",
1003 |        "      <td>China</td>\n",
1004 |        "      <td>None</td>\n",
1005 |        "    </tr>\n",
1006 |        "    <tr>\n",
1007 |        "      <th>HP Inc.</th>\n",
1008 |        "      <td>United</td>\n",
1009 |        "      <td>States</td>\n",
1010 |        "    </tr>\n",
1011 |        "    <tr>\n",
1012 |        "      <th>LG Electronics</th>\n",
1013 |        "      <td>South</td>\n",
1014 |        "      <td>Korea</td>\n",
1015 |        "    </tr>\n",
1016 |        "  </tbody>\n",
1017 |        "</table>\n",
1018 |        "</div>"
1019 |       ],
1020 |       "text/plain": [
1021 |        "                          0       1\n",
1022 |        "Company                            \n",
1023 |        "Apple                United  States\n",
1024 |        "Samsung Electronics   South   Korea\n",
1025 |        "Alphabet             United  States\n",
1026 |        "Foxconn              Taiwan    None\n",
1027 |        "Microsoft            United  States\n",
1028 |        "Huawei                China    None\n",
1029 |        "Dell Technologies    United  States\n",
1030 |        "Facebook             United  States\n",
1031 |        "Sony                  Japan    None\n",
1032 |        "Hitachi               Japan    None\n",
1033 |        "Intel                United  States\n",
1034 |        "IBM                  United  States\n",
1035 |        "Tencent               China    None\n",
1036 |        "Panasonic             Japan    None\n",
1037 |        "Lenovo                China    None\n",
1038 |        "HP Inc.              United  States\n",
1039 |        "LG Electronics        South   Korea"
1040 |       ]
1041 |      },
1042 |      "execution_count": 79,
1043 |      "metadata": {},
1044 |      "output_type": "execute_result"
1045 |     }
1046 |    ],
1047 |    "source": [
1048 |     "df_tech['Country'].str.split(' ', expand=True)\n"
1049 |    ]
1050 |   },
1051 |   {
1052 |    "cell_type": "markdown",
1053 |    "id": "96dc72fb",
1054 |    "metadata": {},
1055 |    "source": [
1056 |     "# 5) Melt"
1057 |    ]
1058 |   },
1059 |   {
1060 |    "cell_type": "markdown",
1061 |    "id": "556184c3",
1062 |    "metadata": {},
1063 |    "source": [
1064 |     "Los datos suelen venir en formato amplio, donde las variables están distribuidas en columnas. El método melt() proporciona una forma concisa de remodelar su DataFrame de formato ancho a largo, lo que facilita la realización de ciertos análisis y visualizaciones.\n",
1065 |     "\n",
1066 |     "Considere un DataFrame con varias columnas que representan datos de ventas de diferentes meses. Si desea remodelar el DataFrame para que tenga una sola columna para los meses y otra para los valores de ventas correspondientes, melt() puede simplificar el proceso:"
1067 |    ]
1068 |   },
1069 |   {
1070 |    "cell_type": "code",
1071 |    "execution_count": 80,
1072 |    "id": "d7b30ea6",
1073 |    "metadata": {},
1074 |    "outputs": [
1075 |     {
1076 |      "data": {
1077 |       "text/html": [
1078 |        "<div>\n",
1079 |        "<style scoped>\n",
1080 |        "    .dataframe tbody tr th:only-of-type {\n",
1081 |        "        vertical-align: middle;\n",
1082 |        "    }\n",
1083 |        "\n",
1084 |        "    .dataframe tbody tr th {\n",
1085 |        "        vertical-align: top;\n",
1086 |        "    }\n",
1087 |        "\n",
1088 |        "    .dataframe thead th {\n",
1089 |        "        text-align: right;\n",
1090 |        "    }\n",
1091 |        "</style>\n",
1092 |        "<table border=\"1\" class=\"dataframe\">\n",
1093 |        "  <thead>\n",
1094 |        "    <tr style=\"text-align: right;\">\n",
1095 |        "      <th></th>\n",
1096 |        "      <th>Producto</th>\n",
1097 |        "      <th>Enero_Sales</th>\n",
1098 |        "      <th>Febrero_Sales</th>\n",
1099 |        "      <th>Marzo_Sales</th>\n",
1100 |        "    </tr>\n",
1101 |        "  </thead>\n",
1102 |        "  <tbody>\n",
1103 |        "    <tr>\n",
1104 |        "      <th>0</th>\n",
1105 |        "      <td>Remera</td>\n",
1106 |        "      <td>110</td>\n",
1107 |        "      <td>150</td>\n",
1108 |        "      <td>80</td>\n",
1109 |        "    </tr>\n",
1110 |        "    <tr>\n",
1111 |        "      <th>1</th>\n",
1112 |        "      <td>Musculosa</td>\n",
1113 |        "      <td>190</td>\n",
1114 |        "      <td>140</td>\n",
1115 |        "      <td>190</td>\n",
1116 |        "    </tr>\n",
1117 |        "    <tr>\n",
1118 |        "      <th>2</th>\n",
1119 |        "      <td>Top</td>\n",
1120 |        "      <td>220</td>\n",
1121 |        "      <td>180</td>\n",
1122 |        "      <td>210</td>\n",
1123 |        "    </tr>\n",
1124 |        "  </tbody>\n",
1125 |        "</table>\n",
1126 |        "</div>"
1127 |       ],
1128 |       "text/plain": [
1129 |        "    Producto  Enero_Sales  Febrero_Sales  Marzo_Sales\n",
1130 |        "0     Remera          110            150           80\n",
1131 |        "1  Musculosa          190            140          190\n",
1132 |        "2        Top          220            180          210"
1133 |       ]
1134 |      },
1135 |      "execution_count": 80,
1136 |      "metadata": {},
1137 |      "output_type": "execute_result"
1138 |     }
1139 |    ],
1140 |    "source": [
1141 |     "data = {'Producto': ['Remera', 'Musculosa', 'Top'],\n",
1142 |     "        'Enero_Sales': [110, 190, 220],\n",
1143 |     "        'Febrero_Sales': [150, 140, 180],\n",
1144 |     "        'Marzo_Sales': [80, 190, 210]}\n",
1145 |     "\n",
1146 |     "df_ventas = pd.DataFrame(data)\n",
1147 |     "df_ventas"
1148 |    ]
1149 |   },
1150 |   {
1151 |    "cell_type": "code",
1152 |    "execution_count": 81,
1153 |    "id": "cf1cc0ea",
1154 |    "metadata": {},
1155 |    "outputs": [
1156 |     {
1157 |      "data": {
1158 |       "text/html": [
1159 |        "<div>\n",
1160 |        "<style scoped>\n",
1161 |        "    .dataframe tbody tr th:only-of-type {\n",
1162 |        "        vertical-align: middle;\n",
1163 |        "    }\n",
1164 |        "\n",
1165 |        "    .dataframe tbody tr th {\n",
1166 |        "        vertical-align: top;\n",
1167 |        "    }\n",
1168 |        "\n",
1169 |        "    .dataframe thead th {\n",
1170 |        "        text-align: right;\n",
1171 |        "    }\n",
1172 |        "</style>\n",
1173 |        "<table border=\"1\" class=\"dataframe\">\n",
1174 |        "  <thead>\n",
1175 |        "    <tr style=\"text-align: right;\">\n",
1176 |        "      <th></th>\n",
1177 |        "      <th>Producto</th>\n",
1178 |        "      <th>Mes</th>\n",
1179 |        "      <th>Ventas</th>\n",
1180 |        "    </tr>\n",
1181 |        "  </thead>\n",
1182 |        "  <tbody>\n",
1183 |        "    <tr>\n",
1184 |        "      <th>0</th>\n",
1185 |        "      <td>Remera</td>\n",
1186 |        "      <td>Enero_Sales</td>\n",
1187 |        "      <td>110</td>\n",
1188 |        "    </tr>\n",
1189 |        "    <tr>\n",
1190 |        "      <th>1</th>\n",
1191 |        "      <td>Musculosa</td>\n",
1192 |        "      <td>Enero_Sales</td>\n",
1193 |        "      <td>190</td>\n",
1194 |        "    </tr>\n",
1195 |        "    <tr>\n",
1196 |        "      <th>2</th>\n",
1197 |        "      <td>Top</td>\n",
1198 |        "      <td>Enero_Sales</td>\n",
1199 |        "      <td>220</td>\n",
1200 |        "    </tr>\n",
1201 |        "    <tr>\n",
1202 |        "      <th>3</th>\n",
1203 |        "      <td>Remera</td>\n",
1204 |        "      <td>Febrero_Sales</td>\n",
1205 |        "      <td>150</td>\n",
1206 |        "    </tr>\n",
1207 |        "    <tr>\n",
1208 |        "      <th>4</th>\n",
1209 |        "      <td>Musculosa</td>\n",
1210 |        "      <td>Febrero_Sales</td>\n",
1211 |        "      <td>140</td>\n",
1212 |        "    </tr>\n",
1213 |        "    <tr>\n",
1214 |        "      <th>5</th>\n",
1215 |        "      <td>Top</td>\n",
1216 |        "      <td>Febrero_Sales</td>\n",
1217 |        "      <td>180</td>\n",
1218 |        "    </tr>\n",
1219 |        "    <tr>\n",
1220 |        "      <th>6</th>\n",
1221 |        "      <td>Remera</td>\n",
1222 |        "      <td>Marzo_Sales</td>\n",
1223 |        "      <td>80</td>\n",
1224 |        "    </tr>\n",
1225 |        "    <tr>\n",
1226 |        "      <th>7</th>\n",
1227 |        "      <td>Musculosa</td>\n",
1228 |        "      <td>Marzo_Sales</td>\n",
1229 |        "      <td>190</td>\n",
1230 |        "    </tr>\n",
1231 |        "    <tr>\n",
1232 |        "      <th>8</th>\n",
1233 |        "      <td>Top</td>\n",
1234 |        "      <td>Marzo_Sales</td>\n",
1235 |        "      <td>210</td>\n",
1236 |        "    </tr>\n",
1237 |        "  </tbody>\n",
1238 |        "</table>\n",
1239 |        "</div>"
1240 |       ],
1241 |       "text/plain": [
1242 |        "    Producto            Mes  Ventas\n",
1243 |        "0     Remera    Enero_Sales     110\n",
1244 |        "1  Musculosa    Enero_Sales     190\n",
1245 |        "2        Top    Enero_Sales     220\n",
1246 |        "3     Remera  Febrero_Sales     150\n",
1247 |        "4  Musculosa  Febrero_Sales     140\n",
1248 |        "5        Top  Febrero_Sales     180\n",
1249 |        "6     Remera    Marzo_Sales      80\n",
1250 |        "7  Musculosa    Marzo_Sales     190\n",
1251 |        "8        Top    Marzo_Sales     210"
1252 |       ]
1253 |      },
1254 |      "execution_count": 81,
1255 |      "metadata": {},
1256 |      "output_type": "execute_result"
1257 |     }
1258 |    ],
1259 |    "source": [
1260 |     "# Melt\n",
1261 |     "df_melted = pd.melt(df_ventas, id_vars=['Producto'], \n",
1262 |     "var_name='Mes', value_name='Ventas')\n",
1263 |     "\n",
1264 |     "df_melted"
1265 |    ]
1266 |   }
1267 |  ],
1268 |  "metadata": {
1269 |   "kernelspec": {
1270 |    "display_name": "Python 3 (ipykernel)",
1271 |    "language": "python",
1272 |    "name": "python3"
1273 |   },
1274 |   "language_info": {
1275 |    "codemirror_mode": {
1276 |     "name": "ipython",
1277 |     "version": 3
1278 |    },
1279 |    "file_extension": ".py",
1280 |    "mimetype": "text/x-python",
1281 |    "name": "python",
1282 |    "nbconvert_exporter": "python",
1283 |    "pygments_lexer": "ipython3",
1284 |    "version": "3.11.4"
1285 |   }
1286 |  },
1287 |  "nbformat": 4,
1288 |  "nbformat_minor": 5
1289 | }
1290 | 


--------------------------------------------------------------------------------
/Pandas_Tricks /Código/pivot_table().ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "id": "555bdacf",
  6 |    "metadata": {},
  7 |    "source": [
  8 |     "## Función pivot_table()"
  9 |    ]
 10 |   },
 11 |   {
 12 |    "cell_type": "code",
 13 |    "execution_count": 29,
 14 |    "id": "005dae81",
 15 |    "metadata": {},
 16 |    "outputs": [
 17 |     {
 18 |      "data": {
 19 |       "text/html": [
 20 |        "<div>\n",
 21 |        "<style scoped>\n",
 22 |        "    .dataframe tbody tr th:only-of-type {\n",
 23 |        "        vertical-align: middle;\n",
 24 |        "    }\n",
 25 |        "\n",
 26 |        "    .dataframe tbody tr th {\n",
 27 |        "        vertical-align: top;\n",
 28 |        "    }\n",
 29 |        "\n",
 30 |        "    .dataframe thead th {\n",
 31 |        "        text-align: right;\n",
 32 |        "    }\n",
 33 |        "</style>\n",
 34 |        "<table border=\"1\" class=\"dataframe\">\n",
 35 |        "  <thead>\n",
 36 |        "    <tr style=\"text-align: right;\">\n",
 37 |        "      <th></th>\n",
 38 |        "      <th>company</th>\n",
 39 |        "      <th>rank</th>\n",
 40 |        "      <th>rank_change</th>\n",
 41 |        "      <th>revenue</th>\n",
 42 |        "      <th>profit</th>\n",
 43 |        "      <th>num. of employees</th>\n",
 44 |        "      <th>sector</th>\n",
 45 |        "      <th>city</th>\n",
 46 |        "      <th>state</th>\n",
 47 |        "      <th>newcomer</th>\n",
 48 |        "      <th>ceo_founder</th>\n",
 49 |        "      <th>ceo_woman</th>\n",
 50 |        "      <th>profitable</th>\n",
 51 |        "      <th>prev_rank</th>\n",
 52 |        "      <th>CEO</th>\n",
 53 |        "      <th>Website</th>\n",
 54 |        "      <th>Ticker</th>\n",
 55 |        "      <th>Market Cap</th>\n",
 56 |        "    </tr>\n",
 57 |        "  </thead>\n",
 58 |        "  <tbody>\n",
 59 |        "    <tr>\n",
 60 |        "      <th>0</th>\n",
 61 |        "      <td>Walmart</td>\n",
 62 |        "      <td>1</td>\n",
 63 |        "      <td>0.0</td>\n",
 64 |        "      <td>572754.0</td>\n",
 65 |        "      <td>13673.0</td>\n",
 66 |        "      <td>2300000.0</td>\n",
 67 |        "      <td>Retailing</td>\n",
 68 |        "      <td>Bentonville</td>\n",
 69 |        "      <td>AR</td>\n",
 70 |        "      <td>no</td>\n",
 71 |        "      <td>no</td>\n",
 72 |        "      <td>no</td>\n",
 73 |        "      <td>yes</td>\n",
 74 |        "      <td>1.0</td>\n",
 75 |        "      <td>C. Douglas McMillon</td>\n",
 76 |        "      <td>https://www.stock.walmart.com</td>\n",
 77 |        "      <td>WMT</td>\n",
 78 |        "      <td>352037</td>\n",
 79 |        "    </tr>\n",
 80 |        "    <tr>\n",
 81 |        "      <th>1</th>\n",
 82 |        "      <td>Amazon</td>\n",
 83 |        "      <td>2</td>\n",
 84 |        "      <td>0.0</td>\n",
 85 |        "      <td>469822.0</td>\n",
 86 |        "      <td>33364.0</td>\n",
 87 |        "      <td>1608000.0</td>\n",
 88 |        "      <td>Retailing</td>\n",
 89 |        "      <td>Seattle</td>\n",
 90 |        "      <td>WA</td>\n",
 91 |        "      <td>no</td>\n",
 92 |        "      <td>no</td>\n",
 93 |        "      <td>no</td>\n",
 94 |        "      <td>yes</td>\n",
 95 |        "      <td>2.0</td>\n",
 96 |        "      <td>Andrew R. Jassy</td>\n",
 97 |        "      <td>www.amazon.com</td>\n",
 98 |        "      <td>AMZN</td>\n",
 99 |        "      <td>1202717</td>\n",
100 |        "    </tr>\n",
101 |        "    <tr>\n",
102 |        "      <th>2</th>\n",
103 |        "      <td>Apple</td>\n",
104 |        "      <td>3</td>\n",
105 |        "      <td>0.0</td>\n",
106 |        "      <td>365817.0</td>\n",
107 |        "      <td>94680.0</td>\n",
108 |        "      <td>154000.0</td>\n",
109 |        "      <td>Technology</td>\n",
110 |        "      <td>Cupertino</td>\n",
111 |        "      <td>CA</td>\n",
112 |        "      <td>no</td>\n",
113 |        "      <td>no</td>\n",
114 |        "      <td>no</td>\n",
115 |        "      <td>yes</td>\n",
116 |        "      <td>3.0</td>\n",
117 |        "      <td>Timothy D. Cook</td>\n",
118 |        "      <td>www.apple.com</td>\n",
119 |        "      <td>AAPL</td>\n",
120 |        "      <td>2443962</td>\n",
121 |        "    </tr>\n",
122 |        "    <tr>\n",
123 |        "      <th>3</th>\n",
124 |        "      <td>CVS Health</td>\n",
125 |        "      <td>4</td>\n",
126 |        "      <td>0.0</td>\n",
127 |        "      <td>292111.0</td>\n",
128 |        "      <td>7910.0</td>\n",
129 |        "      <td>258000.0</td>\n",
130 |        "      <td>Health Care</td>\n",
131 |        "      <td>Woonsocket</td>\n",
132 |        "      <td>RI</td>\n",
133 |        "      <td>no</td>\n",
134 |        "      <td>no</td>\n",
135 |        "      <td>yes</td>\n",
136 |        "      <td>yes</td>\n",
137 |        "      <td>4.0</td>\n",
138 |        "      <td>Karen Lynch</td>\n",
139 |        "      <td>https://www.cvshealth.com</td>\n",
140 |        "      <td>CVS</td>\n",
141 |        "      <td>125204</td>\n",
142 |        "    </tr>\n",
143 |        "    <tr>\n",
144 |        "      <th>4</th>\n",
145 |        "      <td>UnitedHealth Group</td>\n",
146 |        "      <td>5</td>\n",
147 |        "      <td>0.0</td>\n",
148 |        "      <td>287597.0</td>\n",
149 |        "      <td>17285.0</td>\n",
150 |        "      <td>350000.0</td>\n",
151 |        "      <td>Health Care</td>\n",
152 |        "      <td>Minnetonka</td>\n",
153 |        "      <td>MN</td>\n",
154 |        "      <td>no</td>\n",
155 |        "      <td>no</td>\n",
156 |        "      <td>no</td>\n",
157 |        "      <td>yes</td>\n",
158 |        "      <td>5.0</td>\n",
159 |        "      <td>Andrew P. Witty</td>\n",
160 |        "      <td>www.unitedhealthgroup.com</td>\n",
161 |        "      <td>UNH</td>\n",
162 |        "      <td>500468</td>\n",
163 |        "    </tr>\n",
164 |        "  </tbody>\n",
165 |        "</table>\n",
166 |        "</div>"
167 |       ],
168 |       "text/plain": [
169 |        "              company  rank  rank_change   revenue   profit  \\\n",
170 |        "0             Walmart     1          0.0  572754.0  13673.0   \n",
171 |        "1              Amazon     2          0.0  469822.0  33364.0   \n",
172 |        "2               Apple     3          0.0  365817.0  94680.0   \n",
173 |        "3          CVS Health     4          0.0  292111.0   7910.0   \n",
174 |        "4  UnitedHealth Group     5          0.0  287597.0  17285.0   \n",
175 |        "\n",
176 |        "   num. of employees       sector         city state newcomer ceo_founder  \\\n",
177 |        "0          2300000.0    Retailing  Bentonville    AR       no          no   \n",
178 |        "1          1608000.0    Retailing      Seattle    WA       no          no   \n",
179 |        "2           154000.0   Technology    Cupertino    CA       no          no   \n",
180 |        "3           258000.0  Health Care   Woonsocket    RI       no          no   \n",
181 |        "4           350000.0  Health Care   Minnetonka    MN       no          no   \n",
182 |        "\n",
183 |        "  ceo_woman profitable prev_rank                  CEO  \\\n",
184 |        "0        no        yes       1.0  C. Douglas McMillon   \n",
185 |        "1        no        yes       2.0      Andrew R. Jassy   \n",
186 |        "2        no        yes       3.0      Timothy D. Cook   \n",
187 |        "3       yes        yes       4.0          Karen Lynch   \n",
188 |        "4        no        yes       5.0      Andrew P. Witty   \n",
189 |        "\n",
190 |        "                         Website Ticker Market Cap  \n",
191 |        "0  https://www.stock.walmart.com    WMT     352037  \n",
192 |        "1                 www.amazon.com   AMZN    1202717  \n",
193 |        "2                  www.apple.com   AAPL    2443962  \n",
194 |        "3      https://www.cvshealth.com    CVS     125204  \n",
195 |        "4      www.unitedhealthgroup.com    UNH     500468  "
196 |       ]
197 |      },
198 |      "execution_count": 29,
199 |      "metadata": {},
200 |      "output_type": "execute_result"
201 |     }
202 |    ],
203 |    "source": [
204 |     "import pandas as pd\n",
205 |     "import numpy as np\n",
206 |     "fortune = pd.read_csv(\"Fortune.csv\")\n",
207 |     "fortune.head()"
208 |    ]
209 |   },
210 |   {
211 |    "cell_type": "code",
212 |    "execution_count": 30,
213 |    "id": "c0d511a3",
214 |    "metadata": {},
215 |    "outputs": [],
216 |    "source": [
217 |     "mean_Profits = fortune[\"revenue\"].mean() # calculo el promedio \n",
218 |     "fortune[\"Revenue_segmentation\"] = np.where(fortune[\"revenue\"] > mean_Profits, \"High\", \"Low\")"
219 |    ]
220 |   },
221 |   {
222 |    "cell_type": "code",
223 |    "execution_count": 31,
224 |    "id": "78b24dd3",
225 |    "metadata": {},
226 |    "outputs": [
227 |     {
228 |      "data": {
229 |       "text/plain": [
230 |        "Low     798\n",
231 |        "High    202\n",
232 |        "Name: Revenue_segmentation, dtype: int64"
233 |       ]
234 |      },
235 |      "execution_count": 31,
236 |      "metadata": {},
237 |      "output_type": "execute_result"
238 |     }
239 |    ],
240 |    "source": [
241 |     "fortune[\"Revenue_segmentation\"].value_counts()"
242 |    ]
243 |   },
244 |   {
245 |    "cell_type": "code",
246 |    "execution_count": 32,
247 |    "id": "a89baeee",
248 |    "metadata": {},
249 |    "outputs": [
250 |     {
251 |      "data": {
252 |       "text/html": [
253 |        "<div>\n",
254 |        "<style scoped>\n",
255 |        "    .dataframe tbody tr th:only-of-type {\n",
256 |        "        vertical-align: middle;\n",
257 |        "    }\n",
258 |        "\n",
259 |        "    .dataframe tbody tr th {\n",
260 |        "        vertical-align: top;\n",
261 |        "    }\n",
262 |        "\n",
263 |        "    .dataframe thead th {\n",
264 |        "        text-align: right;\n",
265 |        "    }\n",
266 |        "</style>\n",
267 |        "<table border=\"1\" class=\"dataframe\">\n",
268 |        "  <thead>\n",
269 |        "    <tr style=\"text-align: right;\">\n",
270 |        "      <th>Revenue_segmentation</th>\n",
271 |        "      <th>High</th>\n",
272 |        "      <th>Low</th>\n",
273 |        "    </tr>\n",
274 |        "    <tr>\n",
275 |        "      <th>sector</th>\n",
276 |        "      <th></th>\n",
277 |        "      <th></th>\n",
278 |        "    </tr>\n",
279 |        "  </thead>\n",
280 |        "  <tbody>\n",
281 |        "    <tr>\n",
282 |        "      <th>Aerospace &amp; Defense</th>\n",
283 |        "      <td>5</td>\n",
284 |        "      <td>12</td>\n",
285 |        "    </tr>\n",
286 |        "    <tr>\n",
287 |        "      <th>Apparel</th>\n",
288 |        "      <td>1</td>\n",
289 |        "      <td>15</td>\n",
290 |        "    </tr>\n",
291 |        "    <tr>\n",
292 |        "      <th>Business Services</th>\n",
293 |        "      <td>4</td>\n",
294 |        "      <td>48</td>\n",
295 |        "    </tr>\n",
296 |        "    <tr>\n",
297 |        "      <th>Chemicals</th>\n",
298 |        "      <td>3</td>\n",
299 |        "      <td>26</td>\n",
300 |        "    </tr>\n",
301 |        "    <tr>\n",
302 |        "      <th>Energy</th>\n",
303 |        "      <td>21</td>\n",
304 |        "      <td>79</td>\n",
305 |        "    </tr>\n",
306 |        "    <tr>\n",
307 |        "      <th>Engineering &amp; Construction</th>\n",
308 |        "      <td>2</td>\n",
309 |        "      <td>30</td>\n",
310 |        "    </tr>\n",
311 |        "    <tr>\n",
312 |        "      <th>Financials</th>\n",
313 |        "      <td>39</td>\n",
314 |        "      <td>127</td>\n",
315 |        "    </tr>\n",
316 |        "    <tr>\n",
317 |        "      <th>Food &amp; Drug Stores</th>\n",
318 |        "      <td>5</td>\n",
319 |        "      <td>4</td>\n",
320 |        "    </tr>\n",
321 |        "    <tr>\n",
322 |        "      <th>Food, Beverages &amp; Tobacco</th>\n",
323 |        "      <td>10</td>\n",
324 |        "      <td>24</td>\n",
325 |        "    </tr>\n",
326 |        "    <tr>\n",
327 |        "      <th>Health Care</th>\n",
328 |        "      <td>24</td>\n",
329 |        "      <td>53</td>\n",
330 |        "    </tr>\n",
331 |        "    <tr>\n",
332 |        "      <th>Hotels, Restaurants &amp; Leisure</th>\n",
333 |        "      <td>2</td>\n",
334 |        "      <td>26</td>\n",
335 |        "    </tr>\n",
336 |        "    <tr>\n",
337 |        "      <th>Household Products</th>\n",
338 |        "      <td>2</td>\n",
339 |        "      <td>21</td>\n",
340 |        "    </tr>\n",
341 |        "    <tr>\n",
342 |        "      <th>Industrials</th>\n",
343 |        "      <td>8</td>\n",
344 |        "      <td>42</td>\n",
345 |        "    </tr>\n",
346 |        "    <tr>\n",
347 |        "      <th>Materials</th>\n",
348 |        "      <td>7</td>\n",
349 |        "      <td>39</td>\n",
350 |        "    </tr>\n",
351 |        "    <tr>\n",
352 |        "      <th>Media</th>\n",
353 |        "      <td>3</td>\n",
354 |        "      <td>25</td>\n",
355 |        "    </tr>\n",
356 |        "    <tr>\n",
357 |        "      <th>Motor Vehicles &amp; Parts</th>\n",
358 |        "      <td>6</td>\n",
359 |        "      <td>14</td>\n",
360 |        "    </tr>\n",
361 |        "    <tr>\n",
362 |        "      <th>Retailing</th>\n",
363 |        "      <td>17</td>\n",
364 |        "      <td>60</td>\n",
365 |        "    </tr>\n",
366 |        "    <tr>\n",
367 |        "      <th>Technology</th>\n",
368 |        "      <td>22</td>\n",
369 |        "      <td>99</td>\n",
370 |        "    </tr>\n",
371 |        "    <tr>\n",
372 |        "      <th>Telecommunications</th>\n",
373 |        "      <td>5</td>\n",
374 |        "      <td>4</td>\n",
375 |        "    </tr>\n",
376 |        "    <tr>\n",
377 |        "      <th>Transportation</th>\n",
378 |        "      <td>7</td>\n",
379 |        "      <td>28</td>\n",
380 |        "    </tr>\n",
381 |        "    <tr>\n",
382 |        "      <th>Wholesalers</th>\n",
383 |        "      <td>9</td>\n",
384 |        "      <td>22</td>\n",
385 |        "    </tr>\n",
386 |        "  </tbody>\n",
387 |        "</table>\n",
388 |        "</div>"
389 |       ],
390 |       "text/plain": [
391 |        "Revenue_segmentation           High  Low\n",
392 |        "sector                                  \n",
393 |        "Aerospace & Defense               5   12\n",
394 |        "Apparel                           1   15\n",
395 |        "Business Services                 4   48\n",
396 |        "Chemicals                         3   26\n",
397 |        "Energy                           21   79\n",
398 |        "Engineering & Construction        2   30\n",
399 |        "Financials                       39  127\n",
400 |        "Food & Drug Stores                5    4\n",
401 |        "Food, Beverages & Tobacco        10   24\n",
402 |        "Health Care                      24   53\n",
403 |        "Hotels, Restaurants & Leisure     2   26\n",
404 |        "Household Products                2   21\n",
405 |        "Industrials                       8   42\n",
406 |        "Materials                         7   39\n",
407 |        "Media                             3   25\n",
408 |        "Motor Vehicles & Parts            6   14\n",
409 |        "Retailing                        17   60\n",
410 |        "Technology                       22   99\n",
411 |        "Telecommunications                5    4\n",
412 |        "Transportation                    7   28\n",
413 |        "Wholesalers                       9   22"
414 |       ]
415 |      },
416 |      "execution_count": 32,
417 |      "metadata": {},
418 |      "output_type": "execute_result"
419 |     }
420 |    ],
421 |    "source": [
422 |     "pd.pivot_table(data = fortune, \n",
423 |     "               index = ['sector'],\n",
424 |     "               columns = [\"Revenue_segmentation\"],\n",
425 |     "               aggfunc = 'size',\n",
426 |     "              fill_value = 0) # 'size' indica que se está contando el número de ocurrencias (tamaño) "
427 |    ]
428 |   },
429 |   {
430 |    "cell_type": "code",
431 |    "execution_count": 33,
432 |    "id": "619596d9",
433 |    "metadata": {},
434 |    "outputs": [
435 |     {
436 |      "data": {
437 |       "text/html": [
438 |        "<div>\n",
439 |        "<style scoped>\n",
440 |        "    .dataframe tbody tr th:only-of-type {\n",
441 |        "        vertical-align: middle;\n",
442 |        "    }\n",
443 |        "\n",
444 |        "    .dataframe tbody tr th {\n",
445 |        "        vertical-align: top;\n",
446 |        "    }\n",
447 |        "\n",
448 |        "    .dataframe thead th {\n",
449 |        "        text-align: right;\n",
450 |        "    }\n",
451 |        "</style>\n",
452 |        "<table border=\"1\" class=\"dataframe\">\n",
453 |        "  <thead>\n",
454 |        "    <tr style=\"text-align: right;\">\n",
455 |        "      <th></th>\n",
456 |        "      <th></th>\n",
457 |        "      <th>size_High</th>\n",
458 |        "      <th>size_Low</th>\n",
459 |        "      <th>sum_High</th>\n",
460 |        "      <th>sum_Low</th>\n",
461 |        "    </tr>\n",
462 |        "    <tr>\n",
463 |        "      <th>sector</th>\n",
464 |        "      <th>city</th>\n",
465 |        "      <th></th>\n",
466 |        "      <th></th>\n",
467 |        "      <th></th>\n",
468 |        "      <th></th>\n",
469 |        "    </tr>\n",
470 |        "  </thead>\n",
471 |        "  <tbody>\n",
472 |        "    <tr>\n",
473 |        "      <th rowspan=\"5\" valign=\"top\">Aerospace &amp; Defense</th>\n",
474 |        "      <th>Bethesda</th>\n",
475 |        "      <td>1</td>\n",
476 |        "      <td>0</td>\n",
477 |        "      <td>67044.0</td>\n",
478 |        "      <td>0.0</td>\n",
479 |        "    </tr>\n",
480 |        "    <tr>\n",
481 |        "      <th>Centreville</th>\n",
482 |        "      <td>0</td>\n",
483 |        "      <td>1</td>\n",
484 |        "      <td>0.0</td>\n",
485 |        "      <td>3660.8</td>\n",
486 |        "    </tr>\n",
487 |        "    <tr>\n",
488 |        "      <th>Chicago</th>\n",
489 |        "      <td>1</td>\n",
490 |        "      <td>0</td>\n",
491 |        "      <td>62286.0</td>\n",
492 |        "      <td>0.0</td>\n",
493 |        "    </tr>\n",
494 |        "    <tr>\n",
495 |        "      <th>Cleveland</th>\n",
496 |        "      <td>0</td>\n",
497 |        "      <td>1</td>\n",
498 |        "      <td>0.0</td>\n",
499 |        "      <td>4798.0</td>\n",
500 |        "    </tr>\n",
501 |        "    <tr>\n",
502 |        "      <th>East Aurora</th>\n",
503 |        "      <td>0</td>\n",
504 |        "      <td>1</td>\n",
505 |        "      <td>0.0</td>\n",
506 |        "      <td>2852.0</td>\n",
507 |        "    </tr>\n",
508 |        "    <tr>\n",
509 |        "      <th>...</th>\n",
510 |        "      <th>...</th>\n",
511 |        "      <td>...</td>\n",
512 |        "      <td>...</td>\n",
513 |        "      <td>...</td>\n",
514 |        "      <td>...</td>\n",
515 |        "    </tr>\n",
516 |        "    <tr>\n",
517 |        "      <th rowspan=\"5\" valign=\"top\">Wholesalers</th>\n",
518 |        "      <th>Roswell</th>\n",
519 |        "      <td>0</td>\n",
520 |        "      <td>1</td>\n",
521 |        "      <td>0.0</td>\n",
522 |        "      <td>3475.7</td>\n",
523 |        "    </tr>\n",
524 |        "    <tr>\n",
525 |        "      <th>St. Louis</th>\n",
526 |        "      <td>0</td>\n",
527 |        "      <td>2</td>\n",
528 |        "      <td>0.0</td>\n",
529 |        "      <td>13771.3</td>\n",
530 |        "    </tr>\n",
531 |        "    <tr>\n",
532 |        "      <th>Tucker</th>\n",
533 |        "      <td>0</td>\n",
534 |        "      <td>1</td>\n",
535 |        "      <td>0.0</td>\n",
536 |        "      <td>3298.8</td>\n",
537 |        "    </tr>\n",
538 |        "    <tr>\n",
539 |        "      <th>Waltham</th>\n",
540 |        "      <td>0</td>\n",
541 |        "      <td>1</td>\n",
542 |        "      <td>0.0</td>\n",
543 |        "      <td>13248.3</td>\n",
544 |        "    </tr>\n",
545 |        "    <tr>\n",
546 |        "      <th>Winona</th>\n",
547 |        "      <td>0</td>\n",
548 |        "      <td>1</td>\n",
549 |        "      <td>0.0</td>\n",
550 |        "      <td>6010.9</td>\n",
551 |        "    </tr>\n",
552 |        "  </tbody>\n",
553 |        "</table>\n",
554 |        "<p>739 rows × 4 columns</p>\n",
555 |        "</div>"
556 |       ],
557 |       "text/plain": [
558 |        "                                 size_High  size_Low  sum_High  sum_Low\n",
559 |        "sector              city                                               \n",
560 |        "Aerospace & Defense Bethesda             1         0   67044.0      0.0\n",
561 |        "                    Centreville          0         1       0.0   3660.8\n",
562 |        "                    Chicago              1         0   62286.0      0.0\n",
563 |        "                    Cleveland            0         1       0.0   4798.0\n",
564 |        "                    East Aurora          0         1       0.0   2852.0\n",
565 |        "...                                    ...       ...       ...      ...\n",
566 |        "Wholesalers         Roswell              0         1       0.0   3475.7\n",
567 |        "                    St. Louis            0         2       0.0  13771.3\n",
568 |        "                    Tucker               0         1       0.0   3298.8\n",
569 |        "                    Waltham              0         1       0.0  13248.3\n",
570 |        "                    Winona               0         1       0.0   6010.9\n",
571 |        "\n",
572 |        "[739 rows x 4 columns]"
573 |       ]
574 |      },
575 |      "execution_count": 33,
576 |      "metadata": {},
577 |      "output_type": "execute_result"
578 |     }
579 |    ],
580 |    "source": [
581 |     "# Crear la tabla pivotada\n",
582 |     "pivot_table = pd.pivot_table(data = fortune,\n",
583 |     "                             values = 'revenue', \n",
584 |     "                             index = ['sector','city'],\n",
585 |     "                             columns = [\"Revenue_segmentation\"],\n",
586 |     "                             aggfunc = {\"revenue\": [\"sum\", 'size']}, \n",
587 |     "                             fill_value = 0)\n",
588 |     "\n",
589 |     "\n",
590 |     "pivot_table.columns = ['_'.join(col).strip() for col in pivot_table.columns]\n",
591 |     "\n",
592 |     "\n",
593 |     "pivot_table\n"
594 |    ]
595 |   }
596 |  ],
597 |  "metadata": {
598 |   "kernelspec": {
599 |    "display_name": "Python 3 (ipykernel)",
600 |    "language": "python",
601 |    "name": "python3"
602 |   },
603 |   "language_info": {
604 |    "codemirror_mode": {
605 |     "name": "ipython",
606 |     "version": 3
607 |    },
608 |    "file_extension": ".py",
609 |    "mimetype": "text/x-python",
610 |    "name": "python",
611 |    "nbconvert_exporter": "python",
612 |    "pygments_lexer": "ipython3",
613 |    "version": "3.11.4"
614 |   }
615 |  },
616 |  "nbformat": 4,
617 |  "nbformat_minor": 5
618 | }
619 | 


--------------------------------------------------------------------------------
/Pandas_Tricks /Código/readme.md:
--------------------------------------------------------------------------------
1 | 
2 | 


--------------------------------------------------------------------------------
/Pandas_Tricks /readme.md:
--------------------------------------------------------------------------------
1 | ## Trucos para utilizar en la librería Pandas de Python 
2 | 
3 | ![pandas](https://github.com/bcamandone/Python_Analisis_datos/assets/86261762/85ad9585-13e6-4e57-8dca-a0978a9c6088)
4 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # Análisis de datos con Python
 2 | 
 3 | ![5](https://user-images.githubusercontent.com/86261762/209863473-89108b92-ca1a-4ad2-92b5-25703119aa10.png)
 4 | 
 5 | 
 6 | Python se ha convertido en el lenguaje de programación más utilizado a la hora de hacer análisis de datos. Tiene miles de librerías para las más variadas tareas, lo que permite realizarlas con relativa facilidad. En el entorno de análisis de datos, las tres más conocidas son : Numpy, Pandas y Matplotlib.
 7 | 
 8 | 
 9 | Librerías utilizadas en este repositorio: 
10 | 
11 | - Pandas
12 | - Numpy
13 | - Matplotlib
14 | - Seaborn
15 | - Missingno
16 | - Sweetviz
17 | - BeautifulSoup
18 | - Tabula
19 | - Datatile
20 | - FastEDA
21 | 
22 | # ¡Por favor, dame un ⭐️ si te gusta y utilizas este repo! 👏
23 | 


--------------------------------------------------------------------------------
/Sales Data Analysis/-:
--------------------------------------------------------------------------------
1 | 
2 | 


--------------------------------------------------------------------------------
/Sales Data Analysis/CSV/README.md:
--------------------------------------------------------------------------------
1 | 
2 | 


--------------------------------------------------------------------------------
/Sales Data Analysis/README.md:
--------------------------------------------------------------------------------
 1 | # Análisis de datos de ventas
 2 | 
 3 | ![pr1_A84BA97F19EC6E907968](https://user-images.githubusercontent.com/86261762/197585785-7ab95ab9-a991-4aa8-bddd-d3b7870d6abf.png)
 4 | 
 5 | 
 6 |  Se realiza un analisis sobre las ventas de una empresa para responder a las siguientes preguntas:
 7 |  
 8 | - P: ¿Cuánto se ganó en 2019?
 9 | - P: ¿Cuál fue el mejor mes para las ventas? ¿Cuánto se ganó ese mes?
10 | - P: ¿Qué ciudad tuvo el mayor número de ventas?
11 | - P: ¿A qué hora debemos mostrar publicidad para maximizar probabilidad de que el cliente compre el producto?
12 | - P: ¿Qué producto vendió más? ¿Por qué crees que vendió más?
13 | 
14 | Dataset: https://www.kaggle.com/code/linocondor/sales-data-analysis/data 
15 | 
16 | Librerías
17 | - pandas
18 | - numpy
19 | - seaborn
20 | - matplotlib
21 | 


--------------------------------------------------------------------------------
/Series y dataframes/Series en Python.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "metadata": {
  6 |     "id": "pRw9aCmeTseK"
  7 |    },
  8 |    "source": [
  9 |     "## Series"
 10 |    ]
 11 |   },
 12 |   {
 13 |    "cell_type": "code",
 14 |    "execution_count": 63,
 15 |    "metadata": {
 16 |     "id": "DDzqASMDS1a3"
 17 |    },
 18 |    "outputs": [],
 19 |    "source": [
 20 |     "import pandas as pd"
 21 |    ]
 22 |   },
 23 |   {
 24 |    "cell_type": "markdown",
 25 |    "metadata": {},
 26 |    "source": [
 27 |     "La serie es una estructura de datos unidimensional en donde cada dato tiene además una etiqueta."
 28 |    ]
 29 |   },
 30 |   {
 31 |    "cell_type": "code",
 32 |    "execution_count": 64,
 33 |    "metadata": {
 34 |     "colab": {
 35 |      "base_uri": "https://localhost:8080/"
 36 |     },
 37 |     "id": "PfxKoWtcU-FK",
 38 |     "outputId": "e29538d6-45f0-481c-f4ba-01eed27d4121"
 39 |    },
 40 |    "outputs": [
 41 |     {
 42 |      "data": {
 43 |       "text/plain": [
 44 |        "['Celeste', 'Rosa', 'Violeta', 'Rojo']"
 45 |       ]
 46 |      },
 47 |      "execution_count": 64,
 48 |      "metadata": {},
 49 |      "output_type": "execute_result"
 50 |     }
 51 |    ],
 52 |    "source": [
 53 |     "Colores = [\"Celeste\" , \"Rosa\", \"Violeta\", \"Rojo\"]\n",
 54 |     "Colores"
 55 |    ]
 56 |   },
 57 |   {
 58 |    "cell_type": "markdown",
 59 |    "metadata": {},
 60 |    "source": [
 61 |     "Para crear una serie se usa el constructor pd.Series() que es capaz de convertir a serie distintas estructuras como listas,\n",
 62 |     "diccionarios,etc."
 63 |    ]
 64 |   },
 65 |   {
 66 |    "cell_type": "code",
 67 |    "execution_count": 65,
 68 |    "metadata": {
 69 |     "colab": {
 70 |      "base_uri": "https://localhost:8080/"
 71 |     },
 72 |     "id": "kWEkH24kVhtN",
 73 |     "outputId": "66dd3b3c-d905-4daf-af25-827fca975141"
 74 |    },
 75 |    "outputs": [
 76 |     {
 77 |      "data": {
 78 |       "text/plain": [
 79 |        "0    Celeste\n",
 80 |        "1       Rosa\n",
 81 |        "2    Violeta\n",
 82 |        "3       Rojo\n",
 83 |        "dtype: object"
 84 |       ]
 85 |      },
 86 |      "execution_count": 65,
 87 |      "metadata": {},
 88 |      "output_type": "execute_result"
 89 |     }
 90 |    ],
 91 |    "source": [
 92 |     "pd.Series(Colores) "
 93 |    ]
 94 |   },
 95 |   {
 96 |    "cell_type": "code",
 97 |    "execution_count": 66,
 98 |    "metadata": {
 99 |     "colab": {
100 |      "base_uri": "https://localhost:8080/"
101 |     },
102 |     "id": "DbxRNopZV1By",
103 |     "outputId": "f8f17f6f-01ed-467a-a319-d2fabf460e27"
104 |    },
105 |    "outputs": [
106 |     {
107 |      "data": {
108 |       "text/plain": [
109 |        "0     1\n",
110 |        "1     2\n",
111 |        "2     3\n",
112 |        "3    65\n",
113 |        "4    34\n",
114 |        "5    11\n",
115 |        "dtype: int64"
116 |       ]
117 |      },
118 |      "execution_count": 66,
119 |      "metadata": {},
120 |      "output_type": "execute_result"
121 |     }
122 |    ],
123 |    "source": [
124 |     "numeros = [1,2,3,65,34,11]\n",
125 |     "\n",
126 |     "pd.Series(numeros)"
127 |    ]
128 |   },
129 |   {
130 |    "cell_type": "code",
131 |    "execution_count": 67,
132 |    "metadata": {
133 |     "colab": {
134 |      "base_uri": "https://localhost:8080/"
135 |     },
136 |     "id": "RWH4EPrJWc8T",
137 |     "outputId": "b4b9b94d-37f5-4570-c20e-bafd32a397ac"
138 |    },
139 |    "outputs": [
140 |     {
141 |      "data": {
142 |       "text/plain": [
143 |        "0     True\n",
144 |        "1    False\n",
145 |        "2     True\n",
146 |        "3     True\n",
147 |        "4    False\n",
148 |        "dtype: bool"
149 |       ]
150 |      },
151 |      "execution_count": 67,
152 |      "metadata": {},
153 |      "output_type": "execute_result"
154 |     }
155 |    ],
156 |    "source": [
157 |     "registros = [True, False, True, True, False]\n",
158 |     "\n",
159 |     "pd.Series(registros)"
160 |    ]
161 |   },
162 |   {
163 |    "cell_type": "markdown",
164 |    "metadata": {
165 |     "id": "k8FLvA5LXNGR"
166 |    },
167 |    "source": [
168 |     "## Atributos de una serie"
169 |    ]
170 |   },
171 |   {
172 |    "cell_type": "code",
173 |    "execution_count": 95,
174 |    "metadata": {},
175 |    "outputs": [
176 |     {
177 |      "data": {
178 |       "text/plain": [
179 |        "AAPL      9\n",
180 |        "AMZN     13\n",
181 |        "GOOGL    26\n",
182 |        "MELI     15\n",
183 |        "dtype: int64"
184 |       ]
185 |      },
186 |      "execution_count": 95,
187 |      "metadata": {},
188 |      "output_type": "execute_result"
189 |     }
190 |    ],
191 |    "source": [
192 |     "precios = [ 9, 13, 26, 15]\n",
193 |     "acciones = [\"AAPL\", \"AMZN\", \"GOOGL\",\"MELI\"]\n",
194 |     "\n",
195 |     "acc = pd.Series(data = precios, index = acciones )\n",
196 |     "\n",
197 |     "acc"
198 |    ]
199 |   },
200 |   {
201 |    "cell_type": "code",
202 |    "execution_count": 96,
203 |    "metadata": {
204 |     "colab": {
205 |      "base_uri": "https://localhost:8080/"
206 |     },
207 |     "id": "XUwc6eOoW61P",
208 |     "outputId": "14bbc48e-1acc-441c-dd20-fb1a41024b69"
209 |    },
210 |    "outputs": [
211 |     {
212 |      "data": {
213 |       "text/plain": [
214 |        "Index(['AAPL', 'AMZN', 'GOOGL', 'MELI'], dtype='object')"
215 |       ]
216 |      },
217 |      "execution_count": 96,
218 |      "metadata": {},
219 |      "output_type": "execute_result"
220 |     }
221 |    ],
222 |    "source": [
223 |     "acc.index"
224 |    ]
225 |   },
226 |   {
227 |    "cell_type": "code",
228 |    "execution_count": 97,
229 |    "metadata": {
230 |     "colab": {
231 |      "base_uri": "https://localhost:8080/"
232 |     },
233 |     "id": "E-tDGqPUW65j",
234 |     "outputId": "25093043-4fb0-4c3c-a8ab-b0e98e669415"
235 |    },
236 |    "outputs": [
237 |     {
238 |      "data": {
239 |       "text/plain": [
240 |        "array([ 9, 13, 26, 15], dtype=int64)"
241 |       ]
242 |      },
243 |      "execution_count": 97,
244 |      "metadata": {},
245 |      "output_type": "execute_result"
246 |     }
247 |    ],
248 |    "source": [
249 |     "acc.values # Me muestra los valores de la serie"
250 |    ]
251 |   },
252 |   {
253 |    "cell_type": "code",
254 |    "execution_count": 98,
255 |    "metadata": {
256 |     "colab": {
257 |      "base_uri": "https://localhost:8080/"
258 |     },
259 |     "id": "7oeK00_uW6vH",
260 |     "outputId": "ed814af3-c3f8-4bb4-bf7b-752074f807ae"
261 |    },
262 |    "outputs": [
263 |     {
264 |      "data": {
265 |       "text/plain": [
266 |        "dtype('int64')"
267 |       ]
268 |      },
269 |      "execution_count": 98,
270 |      "metadata": {},
271 |      "output_type": "execute_result"
272 |     }
273 |    ],
274 |    "source": [
275 |     "acc.dtype"
276 |    ]
277 |   },
278 |   {
279 |    "cell_type": "code",
280 |    "execution_count": 99,
281 |    "metadata": {},
282 |    "outputs": [
283 |     {
284 |      "data": {
285 |       "text/plain": [
286 |        "(4,)"
287 |       ]
288 |      },
289 |      "execution_count": 99,
290 |      "metadata": {},
291 |      "output_type": "execute_result"
292 |     }
293 |    ],
294 |    "source": [
295 |     "acc.shape"
296 |    ]
297 |   },
298 |   {
299 |    "cell_type": "code",
300 |    "execution_count": 100,
301 |    "metadata": {},
302 |    "outputs": [
303 |     {
304 |      "data": {
305 |       "text/plain": [
306 |        "4"
307 |       ]
308 |      },
309 |      "execution_count": 100,
310 |      "metadata": {},
311 |      "output_type": "execute_result"
312 |     }
313 |    ],
314 |    "source": [
315 |     "acc.size"
316 |    ]
317 |   },
318 |   {
319 |    "cell_type": "code",
320 |    "execution_count": 101,
321 |    "metadata": {},
322 |    "outputs": [
323 |     {
324 |      "data": {
325 |       "text/plain": [
326 |        "1"
327 |       ]
328 |      },
329 |      "execution_count": 101,
330 |      "metadata": {},
331 |      "output_type": "execute_result"
332 |     }
333 |    ],
334 |    "source": [
335 |     "acc.ndim"
336 |    ]
337 |   },
338 |   {
339 |    "cell_type": "markdown",
340 |    "metadata": {},
341 |    "source": [
342 |     "La serie tiene, además, un atributo name, atributo que también encontramos en el índice. Una vez los hemos fijado, se muestran junto con la estructura al imprimir la serie"
343 |    ]
344 |   },
345 |   {
346 |    "cell_type": "code",
347 |    "execution_count": 102,
348 |    "metadata": {},
349 |    "outputs": [
350 |     {
351 |      "data": {
352 |       "text/plain": [
353 |        "AAPL      9\n",
354 |        "AMZN     13\n",
355 |        "GOOGL    26\n",
356 |        "MELI     15\n",
357 |        "Name: Mi lista de acciones, dtype: int64"
358 |       ]
359 |      },
360 |      "execution_count": 102,
361 |      "metadata": {},
362 |      "output_type": "execute_result"
363 |     }
364 |    ],
365 |    "source": [
366 |     "acc.name = \"Mi lista de acciones\"\n",
367 |     "acc.head(4) "
368 |    ]
369 |   },
370 |   {
371 |    "cell_type": "markdown",
372 |    "metadata": {
373 |     "id": "GhVIldoQYSpa"
374 |    },
375 |    "source": [
376 |     "## Selección de registros"
377 |    ]
378 |   },
379 |   {
380 |    "cell_type": "code",
381 |    "execution_count": 103,
382 |    "metadata": {},
383 |    "outputs": [
384 |     {
385 |      "data": {
386 |       "text/plain": [
387 |        "9"
388 |       ]
389 |      },
390 |      "execution_count": 103,
391 |      "metadata": {},
392 |      "output_type": "execute_result"
393 |     }
394 |    ],
395 |    "source": [
396 |     "acc[0]"
397 |    ]
398 |   },
399 |   {
400 |    "cell_type": "code",
401 |    "execution_count": 104,
402 |    "metadata": {},
403 |    "outputs": [
404 |     {
405 |      "data": {
406 |       "text/plain": [
407 |        "AAPL     9\n",
408 |        "AMZN    13\n",
409 |        "Name: Mi lista de acciones, dtype: int64"
410 |       ]
411 |      },
412 |      "execution_count": 104,
413 |      "metadata": {},
414 |      "output_type": "execute_result"
415 |     }
416 |    ],
417 |    "source": [
418 |     "acc[0:2]"
419 |    ]
420 |   },
421 |   {
422 |    "cell_type": "code",
423 |    "execution_count": 105,
424 |    "metadata": {},
425 |    "outputs": [
426 |     {
427 |      "data": {
428 |       "text/plain": [
429 |        "15"
430 |       ]
431 |      },
432 |      "execution_count": 105,
433 |      "metadata": {},
434 |      "output_type": "execute_result"
435 |     }
436 |    ],
437 |    "source": [
438 |     "acc['MELI']"
439 |    ]
440 |   },
441 |   {
442 |    "cell_type": "code",
443 |    "execution_count": 106,
444 |    "metadata": {},
445 |    "outputs": [
446 |     {
447 |      "data": {
448 |       "text/plain": [
449 |        "<bound method Series.items of AAPL      9\n",
450 |        "AMZN     13\n",
451 |        "GOOGL    26\n",
452 |        "MELI     15\n",
453 |        "Name: Mi lista de acciones, dtype: int64>"
454 |       ]
455 |      },
456 |      "execution_count": 106,
457 |      "metadata": {},
458 |      "output_type": "execute_result"
459 |     }
460 |    ],
461 |    "source": [
462 |     "acc.items"
463 |    ]
464 |   },
465 |   {
466 |    "cell_type": "markdown",
467 |    "metadata": {},
468 |    "source": [
469 |     "## Operaciones con series"
470 |    ]
471 |   },
472 |   {
473 |    "cell_type": "markdown",
474 |    "metadata": {},
475 |    "source": [
476 |     "**Operaciones logicas:**"
477 |    ]
478 |   },
479 |   {
480 |    "cell_type": "code",
481 |    "execution_count": 107,
482 |    "metadata": {},
483 |    "outputs": [
484 |     {
485 |      "data": {
486 |       "text/plain": [
487 |        "AAPL     False\n",
488 |        "AMZN      True\n",
489 |        "GOOGL     True\n",
490 |        "MELI      True\n",
491 |        "Name: Mi lista de acciones, dtype: bool"
492 |       ]
493 |      },
494 |      "execution_count": 107,
495 |      "metadata": {},
496 |      "output_type": "execute_result"
497 |     }
498 |    ],
499 |    "source": [
500 |     "acc > 10"
501 |    ]
502 |   },
503 |   {
504 |    "cell_type": "code",
505 |    "execution_count": 109,
506 |    "metadata": {},
507 |    "outputs": [
508 |     {
509 |      "data": {
510 |       "text/plain": [
511 |        "AMZN     13\n",
512 |        "GOOGL    26\n",
513 |        "MELI     15\n",
514 |        "Name: Mi lista de acciones, dtype: int64"
515 |       ]
516 |      },
517 |      "execution_count": 109,
518 |      "metadata": {},
519 |      "output_type": "execute_result"
520 |     }
521 |    ],
522 |    "source": [
523 |     "acc[acc > 9]"
524 |    ]
525 |   },
526 |   {
527 |    "cell_type": "markdown",
528 |    "metadata": {},
529 |    "source": [
530 |     "**Operaciones Aritméticas**:\n",
531 |     "\n",
532 |     "Podemos operar entre series y escalares sin ningún tipo de problema:"
533 |    ]
534 |   },
535 |   {
536 |    "cell_type": "code",
537 |    "execution_count": 110,
538 |    "metadata": {},
539 |    "outputs": [
540 |     {
541 |      "data": {
542 |       "text/plain": [
543 |        "AAPL      4.5\n",
544 |        "AMZN      6.5\n",
545 |        "GOOGL    13.0\n",
546 |        "MELI      7.5\n",
547 |        "Name: Mi lista de acciones, dtype: float64"
548 |       ]
549 |      },
550 |      "execution_count": 110,
551 |      "metadata": {},
552 |      "output_type": "execute_result"
553 |     }
554 |    ],
555 |    "source": [
556 |     "acc/2"
557 |    ]
558 |   },
559 |   {
560 |    "cell_type": "code",
561 |    "execution_count": 114,
562 |    "metadata": {},
563 |    "outputs": [],
564 |    "source": [
565 |     "comisiones = [0.15,0.18,0.02,0.03]"
566 |    ]
567 |   },
568 |   {
569 |    "cell_type": "code",
570 |    "execution_count": 115,
571 |    "metadata": {},
572 |    "outputs": [
573 |     {
574 |      "data": {
575 |       "text/plain": [
576 |        "AAPL     1.35\n",
577 |        "AMZN     2.34\n",
578 |        "GOOGL    0.52\n",
579 |        "MELI     0.45\n",
580 |        "Name: Mi lista de acciones, dtype: float64"
581 |       ]
582 |      },
583 |      "execution_count": 115,
584 |      "metadata": {},
585 |      "output_type": "execute_result"
586 |     }
587 |    ],
588 |    "source": [
589 |     "acc*comisiones"
590 |    ]
591 |   },
592 |   {
593 |    "cell_type": "markdown",
594 |    "metadata": {},
595 |    "source": [
596 |     "## Ordenación"
597 |    ]
598 |   },
599 |   {
600 |    "cell_type": "code",
601 |    "execution_count": 116,
602 |    "metadata": {},
603 |    "outputs": [
604 |     {
605 |      "data": {
606 |       "text/plain": [
607 |        "GOOGL    26\n",
608 |        "MELI     15\n",
609 |        "AMZN     13\n",
610 |        "AAPL      9\n",
611 |        "Name: Mi lista de acciones, dtype: int64"
612 |       ]
613 |      },
614 |      "execution_count": 116,
615 |      "metadata": {},
616 |      "output_type": "execute_result"
617 |     }
618 |    ],
619 |    "source": [
620 |     "acc.sort_values(ascending = False)"
621 |    ]
622 |   },
623 |   {
624 |    "cell_type": "markdown",
625 |    "metadata": {},
626 |    "source": [
627 |     "## Contando valores"
628 |    ]
629 |   },
630 |   {
631 |    "cell_type": "code",
632 |    "execution_count": 117,
633 |    "metadata": {},
634 |    "outputs": [
635 |     {
636 |      "data": {
637 |       "text/plain": [
638 |        "9     1\n",
639 |        "13    1\n",
640 |        "26    1\n",
641 |        "15    1\n",
642 |        "Name: Mi lista de acciones, dtype: int64"
643 |       ]
644 |      },
645 |      "execution_count": 117,
646 |      "metadata": {},
647 |      "output_type": "execute_result"
648 |     }
649 |    ],
650 |    "source": [
651 |     "acc.value_counts()"
652 |    ]
653 |   },
654 |   {
655 |    "cell_type": "markdown",
656 |    "metadata": {},
657 |    "source": [
658 |     "## Funciones estadisticas\n",
659 |     "A modo de ejemplo:"
660 |    ]
661 |   },
662 |   {
663 |    "cell_type": "code",
664 |    "execution_count": 118,
665 |    "metadata": {
666 |     "colab": {
667 |      "base_uri": "https://localhost:8080/"
668 |     },
669 |     "id": "H6sP7NYdYgIF",
670 |     "outputId": "3c2e07bf-9193-4f9b-d6b8-c0c2656df219"
671 |    },
672 |    "outputs": [
673 |     {
674 |      "data": {
675 |       "text/plain": [
676 |        "15.75"
677 |       ]
678 |      },
679 |      "execution_count": 118,
680 |      "metadata": {},
681 |      "output_type": "execute_result"
682 |     }
683 |    ],
684 |    "source": [
685 |     "acc.mean()"
686 |    ]
687 |   },
688 |   {
689 |    "cell_type": "code",
690 |    "execution_count": 119,
691 |    "metadata": {
692 |     "colab": {
693 |      "base_uri": "https://localhost:8080/"
694 |     },
695 |     "id": "EZpWA4myYsBW",
696 |     "outputId": "18a22017-f18c-4cd1-a417-1eba5a7929c9"
697 |    },
698 |    "outputs": [
699 |     {
700 |      "data": {
701 |       "text/plain": [
702 |        "14.0"
703 |       ]
704 |      },
705 |      "execution_count": 119,
706 |      "metadata": {},
707 |      "output_type": "execute_result"
708 |     }
709 |    ],
710 |    "source": [
711 |     "acc.median()"
712 |    ]
713 |   },
714 |   {
715 |    "cell_type": "code",
716 |    "execution_count": 121,
717 |    "metadata": {},
718 |    "outputs": [
719 |     {
720 |      "data": {
721 |       "text/plain": [
722 |        "count     4.000000\n",
723 |        "mean     15.750000\n",
724 |        "std       7.274384\n",
725 |        "min       9.000000\n",
726 |        "25%      12.000000\n",
727 |        "50%      14.000000\n",
728 |        "75%      17.750000\n",
729 |        "max      26.000000\n",
730 |        "Name: Mi lista de acciones, dtype: float64"
731 |       ]
732 |      },
733 |      "execution_count": 121,
734 |      "metadata": {},
735 |      "output_type": "execute_result"
736 |     }
737 |    ],
738 |    "source": [
739 |     "acc.describe()"
740 |    ]
741 |   },
742 |   {
743 |    "cell_type": "markdown",
744 |    "metadata": {},
745 |    "source": [
746 |     "[Pandas Documentación de Series](https://pandas.pydata.org/pandas-docs/stable/reference/series.html)"
747 |    ]
748 |   },
749 |   {
750 |    "cell_type": "markdown",
751 |    "metadata": {},
752 |    "source": [
753 |     "by María Belén Camandone"
754 |    ]
755 |   }
756 |  ],
757 |  "metadata": {
758 |   "colab": {
759 |    "name": "Laboratorio_2_Series",
760 |    "provenance": []
761 |   },
762 |   "kernelspec": {
763 |    "display_name": "Python 3 (ipykernel)",
764 |    "language": "python",
765 |    "name": "python3"
766 |   },
767 |   "language_info": {
768 |    "codemirror_mode": {
769 |     "name": "ipython",
770 |     "version": 3
771 |    },
772 |    "file_extension": ".py",
773 |    "mimetype": "text/x-python",
774 |    "name": "python",
775 |    "nbconvert_exporter": "python",
776 |    "pygments_lexer": "ipython3",
777 |    "version": "3.11.4"
778 |   }
779 |  },
780 |  "nbformat": 4,
781 |  "nbformat_minor": 1
782 | }
783 | 


--------------------------------------------------------------------------------
/Series y dataframes/readme.md:
--------------------------------------------------------------------------------
1 | 
2 | ![series](https://github.com/bcamandone/Python_Analisis_datos/assets/86261762/8647c5b2-29b7-4e23-abe1-4f84850f3604)
3 | 


--------------------------------------------------------------------------------
/Tabula/Tabula python.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/bcamandone/Python_Analisis_datos/164c777861caa37db598fff37659e9ac99edc8f2/Tabula/Tabula python.pdf


--------------------------------------------------------------------------------
/Tabula/readme.md:
--------------------------------------------------------------------------------
1 | # Tabula 
2 | Con la librería Tabula podemos leer tablas de archivos PDF 
3 | 


--------------------------------------------------------------------------------
/Titanic Dataset/Portada/-:
--------------------------------------------------------------------------------
1 | 
2 | 


--------------------------------------------------------------------------------
/Titanic Dataset/Portada/2.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/bcamandone/Python_Analisis_datos/164c777861caa37db598fff37659e9ac99edc8f2/Titanic Dataset/Portada/2.png


--------------------------------------------------------------------------------
/Titanic Dataset/README.md:
--------------------------------------------------------------------------------
 1 | # Titanic
 2 | 
 3 | ![2](https://user-images.githubusercontent.com/86261762/197585477-a58d5c2f-de0e-498d-81ea-055fe0a3e338.png)
 4 | 
 5 | 
 6 | Sin dudas el Titanic es el dataset que, por excelencia usamos por primera vez para aprender y adentrarnos al mundo del análisis de datos. 
 7 | Este repositorio cuenta con 5 notebooks y el archivo csv. 
 8 | 
 9 | Notebooks: 
10 | 
11 | ## 1) Titanic ejercicio: 
12 | En el cual se responde a la siguientes preguntas: 
13 | a) ¿Cuál era la edad promedio de los pasajeros de cada clase (Pclass)?
14 | b) ¿Cuál fue la tarifa que pagaron en promedio los hombres?
15 | c) ¿Cuánto pagaron en total los pasajeros de primera clase para subir al Titanic? ¿Y los de tercera?
16 | d) ¿Cuántos pasajeros había en cada tipo de clase?
17 | 
18 | ## 2) Titanic group by: 
19 | En el cual se analizan las distintas posibilidades para agrupar datos 
20 | 
21 | 
22 | ## 3) EDA - Dataset Titanic: 
23 | Se realiza un análisis exploratorio de datos, para responder con estos últimos  a preguntas como: ¿sobrevivieron mayor cantidad de hombres? sobrevivieron en mayor cantidad pasajeros de la primera clase? ¿Qué edad tenían los pasajeros? etc.
24 | 
25 | ## 4) Outliers:
26 | Detección de outliers en la columna "Age", a través del método IQR y 𝗭-𝗦𝗖𝗢𝗥𝗘
27 | 
28 | ## 5) Visualizar datos faltantes con missingno:
29 | Se utiliza la libreria missingno, que proporciona una serie de visualizaciones para comprender la presencia y distribución de datos faltantes. 
30 | Se pintan: un gráfico de barras, gráfico de matriz, mapa de calor y dendrograma.
31 | 
32 | 
33 | Librerías
34 | - pandas
35 | - numpy
36 | - matplotlib
37 | - seaborn
38 | - missingno
39 | 


--------------------------------------------------------------------------------
/Titanic Dataset/Titanic ejercicio.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "b8231186",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as pd\n",
 11 |     "import numpy as np\n"
 12 |    ]
 13 |   },
 14 |   {
 15 |    "cell_type": "code",
 16 |    "execution_count": 3,
 17 |    "id": "8325f278",
 18 |    "metadata": {},
 19 |    "outputs": [],
 20 |    "source": [
 21 |     "df =  pd.read_csv(\"titanic_train.csv\")"
 22 |    ]
 23 |   },
 24 |   {
 25 |    "cell_type": "code",
 26 |    "execution_count": 12,
 27 |    "id": "340ac1c5",
 28 |    "metadata": {},
 29 |    "outputs": [
 30 |     {
 31 |      "data": {
 32 |       "text/plain": [
 33 |        "(891, 12)"
 34 |       ]
 35 |      },
 36 |      "execution_count": 12,
 37 |      "metadata": {},
 38 |      "output_type": "execute_result"
 39 |     }
 40 |    ],
 41 |    "source": [
 42 |     "df.shape"
 43 |    ]
 44 |   },
 45 |   {
 46 |    "cell_type": "code",
 47 |    "execution_count": 5,
 48 |    "id": "1d4dbb12",
 49 |    "metadata": {},
 50 |    "outputs": [
 51 |     {
 52 |      "data": {
 53 |       "text/html": [
 54 |        "<div>\n",
 55 |        "<style scoped>\n",
 56 |        "    .dataframe tbody tr th:only-of-type {\n",
 57 |        "        vertical-align: middle;\n",
 58 |        "    }\n",
 59 |        "\n",
 60 |        "    .dataframe tbody tr th {\n",
 61 |        "        vertical-align: top;\n",
 62 |        "    }\n",
 63 |        "\n",
 64 |        "    .dataframe thead th {\n",
 65 |        "        text-align: right;\n",
 66 |        "    }\n",
 67 |        "</style>\n",
 68 |        "<table border=\"1\" class=\"dataframe\">\n",
 69 |        "  <thead>\n",
 70 |        "    <tr style=\"text-align: right;\">\n",
 71 |        "      <th></th>\n",
 72 |        "      <th>PassengerId</th>\n",
 73 |        "      <th>Survived</th>\n",
 74 |        "      <th>Pclass</th>\n",
 75 |        "      <th>Name</th>\n",
 76 |        "      <th>Sex</th>\n",
 77 |        "      <th>Age</th>\n",
 78 |        "      <th>SibSp</th>\n",
 79 |        "      <th>Parch</th>\n",
 80 |        "      <th>Ticket</th>\n",
 81 |        "      <th>Fare</th>\n",
 82 |        "      <th>Cabin</th>\n",
 83 |        "      <th>Embarked</th>\n",
 84 |        "    </tr>\n",
 85 |        "  </thead>\n",
 86 |        "  <tbody>\n",
 87 |        "    <tr>\n",
 88 |        "      <th>0</th>\n",
 89 |        "      <td>1</td>\n",
 90 |        "      <td>0</td>\n",
 91 |        "      <td>3</td>\n",
 92 |        "      <td>Braund, Mr. Owen Harris</td>\n",
 93 |        "      <td>male</td>\n",
 94 |        "      <td>22.0</td>\n",
 95 |        "      <td>1</td>\n",
 96 |        "      <td>0</td>\n",
 97 |        "      <td>A/5 21171</td>\n",
 98 |        "      <td>7.2500</td>\n",
 99 |        "      <td>NaN</td>\n",
100 |        "      <td>S</td>\n",
101 |        "    </tr>\n",
102 |        "    <tr>\n",
103 |        "      <th>1</th>\n",
104 |        "      <td>2</td>\n",
105 |        "      <td>1</td>\n",
106 |        "      <td>1</td>\n",
107 |        "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
108 |        "      <td>female</td>\n",
109 |        "      <td>38.0</td>\n",
110 |        "      <td>1</td>\n",
111 |        "      <td>0</td>\n",
112 |        "      <td>PC 17599</td>\n",
113 |        "      <td>71.2833</td>\n",
114 |        "      <td>C85</td>\n",
115 |        "      <td>C</td>\n",
116 |        "    </tr>\n",
117 |        "    <tr>\n",
118 |        "      <th>2</th>\n",
119 |        "      <td>3</td>\n",
120 |        "      <td>1</td>\n",
121 |        "      <td>3</td>\n",
122 |        "      <td>Heikkinen, Miss. Laina</td>\n",
123 |        "      <td>female</td>\n",
124 |        "      <td>26.0</td>\n",
125 |        "      <td>0</td>\n",
126 |        "      <td>0</td>\n",
127 |        "      <td>STON/O2. 3101282</td>\n",
128 |        "      <td>7.9250</td>\n",
129 |        "      <td>NaN</td>\n",
130 |        "      <td>S</td>\n",
131 |        "    </tr>\n",
132 |        "    <tr>\n",
133 |        "      <th>3</th>\n",
134 |        "      <td>4</td>\n",
135 |        "      <td>1</td>\n",
136 |        "      <td>1</td>\n",
137 |        "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
138 |        "      <td>female</td>\n",
139 |        "      <td>35.0</td>\n",
140 |        "      <td>1</td>\n",
141 |        "      <td>0</td>\n",
142 |        "      <td>113803</td>\n",
143 |        "      <td>53.1000</td>\n",
144 |        "      <td>C123</td>\n",
145 |        "      <td>S</td>\n",
146 |        "    </tr>\n",
147 |        "    <tr>\n",
148 |        "      <th>4</th>\n",
149 |        "      <td>5</td>\n",
150 |        "      <td>0</td>\n",
151 |        "      <td>3</td>\n",
152 |        "      <td>Allen, Mr. William Henry</td>\n",
153 |        "      <td>male</td>\n",
154 |        "      <td>35.0</td>\n",
155 |        "      <td>0</td>\n",
156 |        "      <td>0</td>\n",
157 |        "      <td>373450</td>\n",
158 |        "      <td>8.0500</td>\n",
159 |        "      <td>NaN</td>\n",
160 |        "      <td>S</td>\n",
161 |        "    </tr>\n",
162 |        "  </tbody>\n",
163 |        "</table>\n",
164 |        "</div>"
165 |       ],
166 |       "text/plain": [
167 |        "   PassengerId  Survived  Pclass  \\\n",
168 |        "0            1         0       3   \n",
169 |        "1            2         1       1   \n",
170 |        "2            3         1       3   \n",
171 |        "3            4         1       1   \n",
172 |        "4            5         0       3   \n",
173 |        "\n",
174 |        "                                                Name     Sex   Age  SibSp  \\\n",
175 |        "0                            Braund, Mr. Owen Harris    male  22.0      1   \n",
176 |        "1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
177 |        "2                             Heikkinen, Miss. Laina  female  26.0      0   \n",
178 |        "3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
179 |        "4                           Allen, Mr. William Henry    male  35.0      0   \n",
180 |        "\n",
181 |        "   Parch            Ticket     Fare Cabin Embarked  \n",
182 |        "0      0         A/5 21171   7.2500   NaN        S  \n",
183 |        "1      0          PC 17599  71.2833   C85        C  \n",
184 |        "2      0  STON/O2. 3101282   7.9250   NaN        S  \n",
185 |        "3      0            113803  53.1000  C123        S  \n",
186 |        "4      0            373450   8.0500   NaN        S  "
187 |       ]
188 |      },
189 |      "execution_count": 5,
190 |      "metadata": {},
191 |      "output_type": "execute_result"
192 |     }
193 |    ],
194 |    "source": [
195 |     "df.head()"
196 |    ]
197 |   },
198 |   {
199 |    "cell_type": "code",
200 |    "execution_count": 9,
201 |    "id": "4387d8e7",
202 |    "metadata": {},
203 |    "outputs": [
204 |     {
205 |      "data": {
206 |       "text/plain": [
207 |        "PassengerId      int64\n",
208 |        "Survived         int64\n",
209 |        "Pclass           int64\n",
210 |        "Name            object\n",
211 |        "Sex             object\n",
212 |        "Age            float64\n",
213 |        "SibSp            int64\n",
214 |        "Parch            int64\n",
215 |        "Ticket          object\n",
216 |        "Fare           float64\n",
217 |        "Cabin           object\n",
218 |        "Embarked        object\n",
219 |        "dtype: object"
220 |       ]
221 |      },
222 |      "execution_count": 9,
223 |      "metadata": {},
224 |      "output_type": "execute_result"
225 |     }
226 |    ],
227 |    "source": [
228 |     "df.dtypes"
229 |    ]
230 |   },
231 |   {
232 |    "cell_type": "code",
233 |    "execution_count": 11,
234 |    "id": "03d24511",
235 |    "metadata": {},
236 |    "outputs": [
237 |     {
238 |      "name": "stdout",
239 |      "output_type": "stream",
240 |      "text": [
241 |       "<class 'pandas.core.frame.DataFrame'>\n",
242 |       "RangeIndex: 891 entries, 0 to 890\n",
243 |       "Data columns (total 12 columns):\n",
244 |       " #   Column       Non-Null Count  Dtype  \n",
245 |       "---  ------       --------------  -----  \n",
246 |       " 0   PassengerId  891 non-null    int64  \n",
247 |       " 1   Survived     891 non-null    int64  \n",
248 |       " 2   Pclass       891 non-null    int64  \n",
249 |       " 3   Name         891 non-null    object \n",
250 |       " 4   Sex          891 non-null    object \n",
251 |       " 5   Age          714 non-null    float64\n",
252 |       " 6   SibSp        891 non-null    int64  \n",
253 |       " 7   Parch        891 non-null    int64  \n",
254 |       " 8   Ticket       891 non-null    object \n",
255 |       " 9   Fare         891 non-null    float64\n",
256 |       " 10  Cabin        204 non-null    object \n",
257 |       " 11  Embarked     889 non-null    object \n",
258 |       "dtypes: float64(2), int64(5), object(5)\n",
259 |       "memory usage: 83.7+ KB\n"
260 |      ]
261 |     }
262 |    ],
263 |    "source": [
264 |     "df.info()"
265 |    ]
266 |   },
267 |   {
268 |    "cell_type": "code",
269 |    "execution_count": 14,
270 |    "id": "57ec56a1",
271 |    "metadata": {},
272 |    "outputs": [
273 |     {
274 |      "data": {
275 |       "text/plain": [
276 |        "0"
277 |       ]
278 |      },
279 |      "execution_count": 14,
280 |      "metadata": {},
281 |      "output_type": "execute_result"
282 |     }
283 |    ],
284 |    "source": [
285 |     "df.duplicated().sum(axis = 0)"
286 |    ]
287 |   },
288 |   {
289 |    "cell_type": "code",
290 |    "execution_count": 15,
291 |    "id": "dbf3cc0a",
292 |    "metadata": {},
293 |    "outputs": [
294 |     {
295 |      "data": {
296 |       "text/plain": [
297 |        "PassengerId      0\n",
298 |        "Survived         0\n",
299 |        "Pclass           0\n",
300 |        "Name             0\n",
301 |        "Sex              0\n",
302 |        "Age            177\n",
303 |        "SibSp            0\n",
304 |        "Parch            0\n",
305 |        "Ticket           0\n",
306 |        "Fare             0\n",
307 |        "Cabin          687\n",
308 |        "Embarked         2\n",
309 |        "dtype: int64"
310 |       ]
311 |      },
312 |      "execution_count": 15,
313 |      "metadata": {},
314 |      "output_type": "execute_result"
315 |     }
316 |    ],
317 |    "source": [
318 |     "df.isnull().sum(axis = 0)"
319 |    ]
320 |   },
321 |   {
322 |    "cell_type": "code",
323 |    "execution_count": 16,
324 |    "id": "105b36cd",
325 |    "metadata": {},
326 |    "outputs": [
327 |     {
328 |      "data": {
329 |       "text/plain": [
330 |        "30"
331 |       ]
332 |      },
333 |      "execution_count": 16,
334 |      "metadata": {},
335 |      "output_type": "execute_result"
336 |     }
337 |    ],
338 |    "source": [
339 |     "media_edad = round(df['Age'].mean()) #Obtenemos la media de la columna edad \n",
340 |     "media_edad "
341 |    ]
342 |   },
343 |   {
344 |    "cell_type": "code",
345 |    "execution_count": 17,
346 |    "id": "c78bebd1",
347 |    "metadata": {},
348 |    "outputs": [],
349 |    "source": [
350 |     "df['Age'].fillna(media_edad, inplace=True) #Reemplazamos los valores nulos de la columna edad por la media de la edad "
351 |    ]
352 |   },
353 |   {
354 |    "cell_type": "markdown",
355 |    "id": "178c5fab",
356 |    "metadata": {},
357 |    "source": [
358 |     "### Ejercicio: Volviendo al ejemplo del Titanic.\n",
359 |     "\n",
360 |     "1) ¿Cuál era la edad promedio de los pasajeros de cada clase (Pclass)?\n",
361 |     "\n",
362 |     "2) ¿Cuál fue la tarifa que pagaron en promedio los hombres?\n",
363 |     "\n",
364 |     "3) ¿Cuánto pagaron en total los pasajeros de primera clase para subir al Titanic? ¿Y los de tercera?\n",
365 |     "\n",
366 |     "4) ¿Cuántos pasajeros había en cada tipo de clase?"
367 |    ]
368 |   },
369 |   {
370 |    "cell_type": "markdown",
371 |    "id": "632bcccd",
372 |    "metadata": {},
373 |    "source": [
374 |     "\n",
375 |     "1) ¿Cuál era la edad promedio de los pasajeros de cada clase (Pclass)?\n"
376 |    ]
377 |   },
378 |   {
379 |    "cell_type": "code",
380 |    "execution_count": 19,
381 |    "id": "bf23b224",
382 |    "metadata": {},
383 |    "outputs": [
384 |     {
385 |      "data": {
386 |       "text/html": [
387 |        "<div>\n",
388 |        "<style scoped>\n",
389 |        "    .dataframe tbody tr th:only-of-type {\n",
390 |        "        vertical-align: middle;\n",
391 |        "    }\n",
392 |        "\n",
393 |        "    .dataframe tbody tr th {\n",
394 |        "        vertical-align: top;\n",
395 |        "    }\n",
396 |        "\n",
397 |        "    .dataframe thead th {\n",
398 |        "        text-align: right;\n",
399 |        "    }\n",
400 |        "</style>\n",
401 |        "<table border=\"1\" class=\"dataframe\">\n",
402 |        "  <thead>\n",
403 |        "    <tr style=\"text-align: right;\">\n",
404 |        "      <th></th>\n",
405 |        "      <th>Age</th>\n",
406 |        "    </tr>\n",
407 |        "    <tr>\n",
408 |        "      <th>Pclass</th>\n",
409 |        "      <th></th>\n",
410 |        "    </tr>\n",
411 |        "  </thead>\n",
412 |        "  <tbody>\n",
413 |        "    <tr>\n",
414 |        "      <th>1</th>\n",
415 |        "      <td>37.0</td>\n",
416 |        "    </tr>\n",
417 |        "    <tr>\n",
418 |        "      <th>2</th>\n",
419 |        "      <td>30.0</td>\n",
420 |        "    </tr>\n",
421 |        "    <tr>\n",
422 |        "      <th>3</th>\n",
423 |        "      <td>26.0</td>\n",
424 |        "    </tr>\n",
425 |        "  </tbody>\n",
426 |        "</table>\n",
427 |        "</div>"
428 |       ],
429 |       "text/plain": [
430 |        "         Age\n",
431 |        "Pclass      \n",
432 |        "1       37.0\n",
433 |        "2       30.0\n",
434 |        "3       26.0"
435 |       ]
436 |      },
437 |      "execution_count": 19,
438 |      "metadata": {},
439 |      "output_type": "execute_result"
440 |     }
441 |    ],
442 |    "source": [
443 |     "round(df[['Pclass', 'Age']].groupby('Pclass').mean())"
444 |    ]
445 |   },
446 |   {
447 |    "cell_type": "markdown",
448 |    "id": "f13d1507",
449 |    "metadata": {},
450 |    "source": [
451 |     "2) ¿Cuál fue la tarifa que pagaron en promedio los hombres?"
452 |    ]
453 |   },
454 |   {
455 |    "cell_type": "code",
456 |    "execution_count": 20,
457 |    "id": "430dea69",
458 |    "metadata": {},
459 |    "outputs": [
460 |     {
461 |      "data": {
462 |       "text/plain": [
463 |        "25.52"
464 |       ]
465 |      },
466 |      "execution_count": 20,
467 |      "metadata": {},
468 |      "output_type": "execute_result"
469 |     }
470 |    ],
471 |    "source": [
472 |     "round(df.loc[df['Sex'] =='male','Fare'].mean(),2)"
473 |    ]
474 |   },
475 |   {
476 |    "cell_type": "markdown",
477 |    "id": "77eb607f",
478 |    "metadata": {},
479 |    "source": [
480 |     "3) ¿Cuánto pagaron en total los pasajeros de primera clase para subir al Titanic? ¿Y los de tercera?"
481 |    ]
482 |   },
483 |   {
484 |    "cell_type": "code",
485 |    "execution_count": 21,
486 |    "id": "d8f20d10",
487 |    "metadata": {},
488 |    "outputs": [
489 |     {
490 |      "data": {
491 |       "text/plain": [
492 |        "18177"
493 |       ]
494 |      },
495 |      "execution_count": 21,
496 |      "metadata": {},
497 |      "output_type": "execute_result"
498 |     }
499 |    ],
500 |    "source": [
501 |     "round(df.loc[df['Pclass'] == 1,'Fare'].sum())"
502 |    ]
503 |   },
504 |   {
505 |    "cell_type": "code",
506 |    "execution_count": 22,
507 |    "id": "9f0701ec",
508 |    "metadata": {},
509 |    "outputs": [
510 |     {
511 |      "data": {
512 |       "text/plain": [
513 |        "6715"
514 |       ]
515 |      },
516 |      "execution_count": 22,
517 |      "metadata": {},
518 |      "output_type": "execute_result"
519 |     }
520 |    ],
521 |    "source": [
522 |     "round(df.loc[df['Pclass'] == 3,'Fare'].sum())"
523 |    ]
524 |   },
525 |   {
526 |    "cell_type": "markdown",
527 |    "id": "cb17bb4c",
528 |    "metadata": {},
529 |    "source": [
530 |     "\n",
531 |     "4) ¿Cuántos pasajeros había en cada tipo de clase?"
532 |    ]
533 |   },
534 |   {
535 |    "cell_type": "code",
536 |    "execution_count": 23,
537 |    "id": "a90a5829",
538 |    "metadata": {},
539 |    "outputs": [
540 |     {
541 |      "data": {
542 |       "text/html": [
543 |        "<div>\n",
544 |        "<style scoped>\n",
545 |        "    .dataframe tbody tr th:only-of-type {\n",
546 |        "        vertical-align: middle;\n",
547 |        "    }\n",
548 |        "\n",
549 |        "    .dataframe tbody tr th {\n",
550 |        "        vertical-align: top;\n",
551 |        "    }\n",
552 |        "\n",
553 |        "    .dataframe thead th {\n",
554 |        "        text-align: right;\n",
555 |        "    }\n",
556 |        "</style>\n",
557 |        "<table border=\"1\" class=\"dataframe\">\n",
558 |        "  <thead>\n",
559 |        "    <tr style=\"text-align: right;\">\n",
560 |        "      <th></th>\n",
561 |        "      <th>PassengerId</th>\n",
562 |        "    </tr>\n",
563 |        "    <tr>\n",
564 |        "      <th>Pclass</th>\n",
565 |        "      <th></th>\n",
566 |        "    </tr>\n",
567 |        "  </thead>\n",
568 |        "  <tbody>\n",
569 |        "    <tr>\n",
570 |        "      <th>1</th>\n",
571 |        "      <td>216</td>\n",
572 |        "    </tr>\n",
573 |        "    <tr>\n",
574 |        "      <th>2</th>\n",
575 |        "      <td>184</td>\n",
576 |        "    </tr>\n",
577 |        "    <tr>\n",
578 |        "      <th>3</th>\n",
579 |        "      <td>491</td>\n",
580 |        "    </tr>\n",
581 |        "  </tbody>\n",
582 |        "</table>\n",
583 |        "</div>"
584 |       ],
585 |       "text/plain": [
586 |        "        PassengerId\n",
587 |        "Pclass             \n",
588 |        "1               216\n",
589 |        "2               184\n",
590 |        "3               491"
591 |       ]
592 |      },
593 |      "execution_count": 23,
594 |      "metadata": {},
595 |      "output_type": "execute_result"
596 |     }
597 |    ],
598 |    "source": [
599 |     "df[['Pclass', 'PassengerId']].groupby('Pclass').count()"
600 |    ]
601 |   }
602 |  ],
603 |  "metadata": {
604 |   "kernelspec": {
605 |    "display_name": "Python 3 (ipykernel)",
606 |    "language": "python",
607 |    "name": "python3"
608 |   },
609 |   "language_info": {
610 |    "codemirror_mode": {
611 |     "name": "ipython",
612 |     "version": 3
613 |    },
614 |    "file_extension": ".py",
615 |    "mimetype": "text/x-python",
616 |    "name": "python",
617 |    "nbconvert_exporter": "python",
618 |    "pygments_lexer": "ipython3",
619 |    "version": "3.11.4"
620 |   }
621 |  },
622 |  "nbformat": 4,
623 |  "nbformat_minor": 5
624 | }
625 | 


--------------------------------------------------------------------------------
/Titanic Dataset/Titanic group by.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "code",
  5 |    "execution_count": 1,
  6 |    "id": "f40fd8c3",
  7 |    "metadata": {},
  8 |    "outputs": [],
  9 |    "source": [
 10 |     "import pandas as pd\n"
 11 |    ]
 12 |   },
 13 |   {
 14 |    "cell_type": "code",
 15 |    "execution_count": 2,
 16 |    "id": "d103538c",
 17 |    "metadata": {},
 18 |    "outputs": [],
 19 |    "source": [
 20 |     "df =  pd.read_csv(\"titanic_train.csv\")"
 21 |    ]
 22 |   },
 23 |   {
 24 |    "cell_type": "code",
 25 |    "execution_count": 3,
 26 |    "id": "6e5741c8",
 27 |    "metadata": {},
 28 |    "outputs": [
 29 |     {
 30 |      "data": {
 31 |       "text/html": [
 32 |        "<div>\n",
 33 |        "<style scoped>\n",
 34 |        "    .dataframe tbody tr th:only-of-type {\n",
 35 |        "        vertical-align: middle;\n",
 36 |        "    }\n",
 37 |        "\n",
 38 |        "    .dataframe tbody tr th {\n",
 39 |        "        vertical-align: top;\n",
 40 |        "    }\n",
 41 |        "\n",
 42 |        "    .dataframe thead th {\n",
 43 |        "        text-align: right;\n",
 44 |        "    }\n",
 45 |        "</style>\n",
 46 |        "<table border=\"1\" class=\"dataframe\">\n",
 47 |        "  <thead>\n",
 48 |        "    <tr style=\"text-align: right;\">\n",
 49 |        "      <th></th>\n",
 50 |        "      <th>PassengerId</th>\n",
 51 |        "      <th>Survived</th>\n",
 52 |        "      <th>Pclass</th>\n",
 53 |        "      <th>Name</th>\n",
 54 |        "      <th>Sex</th>\n",
 55 |        "      <th>Age</th>\n",
 56 |        "      <th>SibSp</th>\n",
 57 |        "      <th>Parch</th>\n",
 58 |        "      <th>Ticket</th>\n",
 59 |        "      <th>Fare</th>\n",
 60 |        "      <th>Cabin</th>\n",
 61 |        "      <th>Embarked</th>\n",
 62 |        "    </tr>\n",
 63 |        "  </thead>\n",
 64 |        "  <tbody>\n",
 65 |        "    <tr>\n",
 66 |        "      <th>0</th>\n",
 67 |        "      <td>1</td>\n",
 68 |        "      <td>0</td>\n",
 69 |        "      <td>3</td>\n",
 70 |        "      <td>Braund, Mr. Owen Harris</td>\n",
 71 |        "      <td>male</td>\n",
 72 |        "      <td>22.0</td>\n",
 73 |        "      <td>1</td>\n",
 74 |        "      <td>0</td>\n",
 75 |        "      <td>A/5 21171</td>\n",
 76 |        "      <td>7.2500</td>\n",
 77 |        "      <td>NaN</td>\n",
 78 |        "      <td>S</td>\n",
 79 |        "    </tr>\n",
 80 |        "    <tr>\n",
 81 |        "      <th>1</th>\n",
 82 |        "      <td>2</td>\n",
 83 |        "      <td>1</td>\n",
 84 |        "      <td>1</td>\n",
 85 |        "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
 86 |        "      <td>female</td>\n",
 87 |        "      <td>38.0</td>\n",
 88 |        "      <td>1</td>\n",
 89 |        "      <td>0</td>\n",
 90 |        "      <td>PC 17599</td>\n",
 91 |        "      <td>71.2833</td>\n",
 92 |        "      <td>C85</td>\n",
 93 |        "      <td>C</td>\n",
 94 |        "    </tr>\n",
 95 |        "    <tr>\n",
 96 |        "      <th>2</th>\n",
 97 |        "      <td>3</td>\n",
 98 |        "      <td>1</td>\n",
 99 |        "      <td>3</td>\n",
100 |        "      <td>Heikkinen, Miss. Laina</td>\n",
101 |        "      <td>female</td>\n",
102 |        "      <td>26.0</td>\n",
103 |        "      <td>0</td>\n",
104 |        "      <td>0</td>\n",
105 |        "      <td>STON/O2. 3101282</td>\n",
106 |        "      <td>7.9250</td>\n",
107 |        "      <td>NaN</td>\n",
108 |        "      <td>S</td>\n",
109 |        "    </tr>\n",
110 |        "    <tr>\n",
111 |        "      <th>3</th>\n",
112 |        "      <td>4</td>\n",
113 |        "      <td>1</td>\n",
114 |        "      <td>1</td>\n",
115 |        "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
116 |        "      <td>female</td>\n",
117 |        "      <td>35.0</td>\n",
118 |        "      <td>1</td>\n",
119 |        "      <td>0</td>\n",
120 |        "      <td>113803</td>\n",
121 |        "      <td>53.1000</td>\n",
122 |        "      <td>C123</td>\n",
123 |        "      <td>S</td>\n",
124 |        "    </tr>\n",
125 |        "    <tr>\n",
126 |        "      <th>4</th>\n",
127 |        "      <td>5</td>\n",
128 |        "      <td>0</td>\n",
129 |        "      <td>3</td>\n",
130 |        "      <td>Allen, Mr. William Henry</td>\n",
131 |        "      <td>male</td>\n",
132 |        "      <td>35.0</td>\n",
133 |        "      <td>0</td>\n",
134 |        "      <td>0</td>\n",
135 |        "      <td>373450</td>\n",
136 |        "      <td>8.0500</td>\n",
137 |        "      <td>NaN</td>\n",
138 |        "      <td>S</td>\n",
139 |        "    </tr>\n",
140 |        "  </tbody>\n",
141 |        "</table>\n",
142 |        "</div>"
143 |       ],
144 |       "text/plain": [
145 |        "   PassengerId  Survived  Pclass  \\\n",
146 |        "0            1         0       3   \n",
147 |        "1            2         1       1   \n",
148 |        "2            3         1       3   \n",
149 |        "3            4         1       1   \n",
150 |        "4            5         0       3   \n",
151 |        "\n",
152 |        "                                                Name     Sex   Age  SibSp  \\\n",
153 |        "0                            Braund, Mr. Owen Harris    male  22.0      1   \n",
154 |        "1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
155 |        "2                             Heikkinen, Miss. Laina  female  26.0      0   \n",
156 |        "3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
157 |        "4                           Allen, Mr. William Henry    male  35.0      0   \n",
158 |        "\n",
159 |        "   Parch            Ticket     Fare Cabin Embarked  \n",
160 |        "0      0         A/5 21171   7.2500   NaN        S  \n",
161 |        "1      0          PC 17599  71.2833   C85        C  \n",
162 |        "2      0  STON/O2. 3101282   7.9250   NaN        S  \n",
163 |        "3      0            113803  53.1000  C123        S  \n",
164 |        "4      0            373450   8.0500   NaN        S  "
165 |       ]
166 |      },
167 |      "execution_count": 3,
168 |      "metadata": {},
169 |      "output_type": "execute_result"
170 |     }
171 |    ],
172 |    "source": [
173 |     "df.head()"
174 |    ]
175 |   },
176 |   {
177 |    "cell_type": "markdown",
178 |    "id": "7194ccdb",
179 |    "metadata": {},
180 |    "source": [
181 |     "Group by\n",
182 |     "\n",
183 |     "Usaremos group by para agrupar los datos según los valores de una o más columnas.\n",
184 |     "Este método crea una estructura de datos particular a la que le podemos aplicar diferentes operaciones.\n",
185 |     "Group by sólo crea la estructura de datos a la que se le puede aplicar la función de agregación o estadísticas. \n"
186 |    ]
187 |   },
188 |   {
189 |    "cell_type": "code",
190 |    "execution_count": 4,
191 |    "id": "4c21610b",
192 |    "metadata": {},
193 |    "outputs": [
194 |     {
195 |      "data": {
196 |       "text/html": [
197 |        "<div>\n",
198 |        "<style scoped>\n",
199 |        "    .dataframe tbody tr th:only-of-type {\n",
200 |        "        vertical-align: middle;\n",
201 |        "    }\n",
202 |        "\n",
203 |        "    .dataframe tbody tr th {\n",
204 |        "        vertical-align: top;\n",
205 |        "    }\n",
206 |        "\n",
207 |        "    .dataframe thead th {\n",
208 |        "        text-align: right;\n",
209 |        "    }\n",
210 |        "</style>\n",
211 |        "<table border=\"1\" class=\"dataframe\">\n",
212 |        "  <thead>\n",
213 |        "    <tr style=\"text-align: right;\">\n",
214 |        "      <th></th>\n",
215 |        "      <th>PassengerId</th>\n",
216 |        "      <th>Survived</th>\n",
217 |        "      <th>Pclass</th>\n",
218 |        "      <th>Name</th>\n",
219 |        "      <th>Age</th>\n",
220 |        "      <th>SibSp</th>\n",
221 |        "      <th>Parch</th>\n",
222 |        "      <th>Ticket</th>\n",
223 |        "      <th>Fare</th>\n",
224 |        "      <th>Cabin</th>\n",
225 |        "      <th>Embarked</th>\n",
226 |        "    </tr>\n",
227 |        "    <tr>\n",
228 |        "      <th>Sex</th>\n",
229 |        "      <th></th>\n",
230 |        "      <th></th>\n",
231 |        "      <th></th>\n",
232 |        "      <th></th>\n",
233 |        "      <th></th>\n",
234 |        "      <th></th>\n",
235 |        "      <th></th>\n",
236 |        "      <th></th>\n",
237 |        "      <th></th>\n",
238 |        "      <th></th>\n",
239 |        "      <th></th>\n",
240 |        "    </tr>\n",
241 |        "  </thead>\n",
242 |        "  <tbody>\n",
243 |        "    <tr>\n",
244 |        "      <th>female</th>\n",
245 |        "      <td>314</td>\n",
246 |        "      <td>314</td>\n",
247 |        "      <td>314</td>\n",
248 |        "      <td>314</td>\n",
249 |        "      <td>261</td>\n",
250 |        "      <td>314</td>\n",
251 |        "      <td>314</td>\n",
252 |        "      <td>314</td>\n",
253 |        "      <td>314</td>\n",
254 |        "      <td>97</td>\n",
255 |        "      <td>312</td>\n",
256 |        "    </tr>\n",
257 |        "    <tr>\n",
258 |        "      <th>male</th>\n",
259 |        "      <td>577</td>\n",
260 |        "      <td>577</td>\n",
261 |        "      <td>577</td>\n",
262 |        "      <td>577</td>\n",
263 |        "      <td>453</td>\n",
264 |        "      <td>577</td>\n",
265 |        "      <td>577</td>\n",
266 |        "      <td>577</td>\n",
267 |        "      <td>577</td>\n",
268 |        "      <td>107</td>\n",
269 |        "      <td>577</td>\n",
270 |        "    </tr>\n",
271 |        "  </tbody>\n",
272 |        "</table>\n",
273 |        "</div>"
274 |       ],
275 |       "text/plain": [
276 |        "        PassengerId  Survived  Pclass  Name  Age  SibSp  Parch  Ticket  Fare  \\\n",
277 |        "Sex                                                                            \n",
278 |        "female          314       314     314   314  261    314    314     314   314   \n",
279 |        "male            577       577     577   577  453    577    577     577   577   \n",
280 |        "\n",
281 |        "        Cabin  Embarked  \n",
282 |        "Sex                      \n",
283 |        "female     97       312  \n",
284 |        "male      107       577  "
285 |       ]
286 |      },
287 |      "execution_count": 4,
288 |      "metadata": {},
289 |      "output_type": "execute_result"
290 |     }
291 |    ],
292 |    "source": [
293 |     "df.groupby('Sex').count()"
294 |    ]
295 |   },
296 |   {
297 |    "cell_type": "markdown",
298 |    "id": "11cae7d9",
299 |    "metadata": {},
300 |    "source": [
301 |     "Si la operación a realizar solo admite números, se aplica a las columnas numéricas exclusivamente"
302 |    ]
303 |   },
304 |   {
305 |    "cell_type": "code",
306 |    "execution_count": 5,
307 |    "id": "8628f419",
308 |    "metadata": {},
309 |    "outputs": [
310 |     {
311 |      "data": {
312 |       "text/html": [
313 |        "<div>\n",
314 |        "<style scoped>\n",
315 |        "    .dataframe tbody tr th:only-of-type {\n",
316 |        "        vertical-align: middle;\n",
317 |        "    }\n",
318 |        "\n",
319 |        "    .dataframe tbody tr th {\n",
320 |        "        vertical-align: top;\n",
321 |        "    }\n",
322 |        "\n",
323 |        "    .dataframe thead th {\n",
324 |        "        text-align: right;\n",
325 |        "    }\n",
326 |        "</style>\n",
327 |        "<table border=\"1\" class=\"dataframe\">\n",
328 |        "  <thead>\n",
329 |        "    <tr style=\"text-align: right;\">\n",
330 |        "      <th></th>\n",
331 |        "      <th>PassengerId</th>\n",
332 |        "      <th>Survived</th>\n",
333 |        "      <th>Pclass</th>\n",
334 |        "      <th>Age</th>\n",
335 |        "      <th>SibSp</th>\n",
336 |        "      <th>Parch</th>\n",
337 |        "      <th>Fare</th>\n",
338 |        "    </tr>\n",
339 |        "    <tr>\n",
340 |        "      <th>Sex</th>\n",
341 |        "      <th></th>\n",
342 |        "      <th></th>\n",
343 |        "      <th></th>\n",
344 |        "      <th></th>\n",
345 |        "      <th></th>\n",
346 |        "      <th></th>\n",
347 |        "      <th></th>\n",
348 |        "    </tr>\n",
349 |        "  </thead>\n",
350 |        "  <tbody>\n",
351 |        "    <tr>\n",
352 |        "      <th>female</th>\n",
353 |        "      <td>431.028662</td>\n",
354 |        "      <td>0.742038</td>\n",
355 |        "      <td>2.159236</td>\n",
356 |        "      <td>27.915709</td>\n",
357 |        "      <td>0.694268</td>\n",
358 |        "      <td>0.649682</td>\n",
359 |        "      <td>44.479818</td>\n",
360 |        "    </tr>\n",
361 |        "    <tr>\n",
362 |        "      <th>male</th>\n",
363 |        "      <td>454.147314</td>\n",
364 |        "      <td>0.188908</td>\n",
365 |        "      <td>2.389948</td>\n",
366 |        "      <td>30.726645</td>\n",
367 |        "      <td>0.429809</td>\n",
368 |        "      <td>0.235702</td>\n",
369 |        "      <td>25.523893</td>\n",
370 |        "    </tr>\n",
371 |        "  </tbody>\n",
372 |        "</table>\n",
373 |        "</div>"
374 |       ],
375 |       "text/plain": [
376 |        "        PassengerId  Survived    Pclass        Age     SibSp     Parch  \\\n",
377 |        "Sex                                                                      \n",
378 |        "female   431.028662  0.742038  2.159236  27.915709  0.694268  0.649682   \n",
379 |        "male     454.147314  0.188908  2.389948  30.726645  0.429809  0.235702   \n",
380 |        "\n",
381 |        "             Fare  \n",
382 |        "Sex                \n",
383 |        "female  44.479818  \n",
384 |        "male    25.523893  "
385 |       ]
386 |      },
387 |      "execution_count": 5,
388 |      "metadata": {},
389 |      "output_type": "execute_result"
390 |     }
391 |    ],
392 |    "source": [
393 |     "df.groupby('Sex').mean()"
394 |    ]
395 |   },
396 |   {
397 |    "cell_type": "markdown",
398 |    "id": "0ca0b5ca",
399 |    "metadata": {},
400 |    "source": [
401 |     "Tres maneras de restringir el resultado a ciertas columnas:\n",
402 |     "    \n",
403 |     "1) Seleccionar la columna de interés, luego de hacer las operaciones.\n",
404 |     "2) Seleccionar las columnas necesarias antes de hacer el groupby\n",
405 |     "(se debe incluir la columna con la que agrupar).\n",
406 |     "3) Seleccionar la columna de interés después de hacer el groupby, \n",
407 |     "pero antes de aplicar la función de agregación."
408 |    ]
409 |   },
410 |   {
411 |    "cell_type": "code",
412 |    "execution_count": 10,
413 |    "id": "9ca3515a",
414 |    "metadata": {},
415 |    "outputs": [
416 |     {
417 |      "data": {
418 |       "text/plain": [
419 |        "Sex\n",
420 |        "female    28.0\n",
421 |        "male      31.0\n",
422 |        "Name: Age, dtype: float64"
423 |       ]
424 |      },
425 |      "execution_count": 10,
426 |      "metadata": {},
427 |      "output_type": "execute_result"
428 |     }
429 |    ],
430 |    "source": [
431 |     "round(df.groupby('Sex').mean()['Age']) #Opción 1 "
432 |    ]
433 |   },
434 |   {
435 |    "cell_type": "code",
436 |    "execution_count": 11,
437 |    "id": "99829739",
438 |    "metadata": {},
439 |    "outputs": [
440 |     {
441 |      "data": {
442 |       "text/html": [
443 |        "<div>\n",
444 |        "<style scoped>\n",
445 |        "    .dataframe tbody tr th:only-of-type {\n",
446 |        "        vertical-align: middle;\n",
447 |        "    }\n",
448 |        "\n",
449 |        "    .dataframe tbody tr th {\n",
450 |        "        vertical-align: top;\n",
451 |        "    }\n",
452 |        "\n",
453 |        "    .dataframe thead th {\n",
454 |        "        text-align: right;\n",
455 |        "    }\n",
456 |        "</style>\n",
457 |        "<table border=\"1\" class=\"dataframe\">\n",
458 |        "  <thead>\n",
459 |        "    <tr style=\"text-align: right;\">\n",
460 |        "      <th></th>\n",
461 |        "      <th>Age</th>\n",
462 |        "    </tr>\n",
463 |        "    <tr>\n",
464 |        "      <th>Sex</th>\n",
465 |        "      <th></th>\n",
466 |        "    </tr>\n",
467 |        "  </thead>\n",
468 |        "  <tbody>\n",
469 |        "    <tr>\n",
470 |        "      <th>female</th>\n",
471 |        "      <td>28.0</td>\n",
472 |        "    </tr>\n",
473 |        "    <tr>\n",
474 |        "      <th>male</th>\n",
475 |        "      <td>31.0</td>\n",
476 |        "    </tr>\n",
477 |        "  </tbody>\n",
478 |        "</table>\n",
479 |        "</div>"
480 |       ],
481 |       "text/plain": [
482 |        "         Age\n",
483 |        "Sex         \n",
484 |        "female  28.0\n",
485 |        "male    31.0"
486 |       ]
487 |      },
488 |      "execution_count": 11,
489 |      "metadata": {},
490 |      "output_type": "execute_result"
491 |     }
492 |    ],
493 |    "source": [
494 |     "round(df[['Sex','Age']].groupby('Sex').mean()) #Opción 2 "
495 |    ]
496 |   },
497 |   {
498 |    "cell_type": "code",
499 |    "execution_count": 12,
500 |    "id": "a1b273b9",
501 |    "metadata": {},
502 |    "outputs": [
503 |     {
504 |      "data": {
505 |       "text/plain": [
506 |        "Sex\n",
507 |        "female    28.0\n",
508 |        "male      31.0\n",
509 |        "Name: Age, dtype: float64"
510 |       ]
511 |      },
512 |      "execution_count": 12,
513 |      "metadata": {},
514 |      "output_type": "execute_result"
515 |     }
516 |    ],
517 |    "source": [
518 |     "round(df.groupby('Sex')['Age'].mean()) #Opción 3 "
519 |    ]
520 |   },
521 |   {
522 |    "cell_type": "markdown",
523 |    "id": "31f26f8b",
524 |    "metadata": {},
525 |    "source": [
526 |     "En mi caso prefiero utilizar la opción dos porque me parece mas ordenada, \n",
527 |     "pero con cualquiera de las 3 llegamos al mismo resultado. "
528 |    ]
529 |   }
530 |  ],
531 |  "metadata": {
532 |   "kernelspec": {
533 |    "display_name": "Python 3 (ipykernel)",
534 |    "language": "python",
535 |    "name": "python3"
536 |   },
537 |   "language_info": {
538 |    "codemirror_mode": {
539 |     "name": "ipython",
540 |     "version": 3
541 |    },
542 |    "file_extension": ".py",
543 |    "mimetype": "text/x-python",
544 |    "name": "python",
545 |    "nbconvert_exporter": "python",
546 |    "pygments_lexer": "ipython3",
547 |    "version": "3.11.4"
548 |   }
549 |  },
550 |  "nbformat": 4,
551 |  "nbformat_minor": 5
552 | }
553 | 


--------------------------------------------------------------------------------
/Web_scraping_BeautifulSoup/readme.md:
--------------------------------------------------------------------------------
1 | Beautiful Soup es una librería de python que facilita la extracción de información de páginas web.
2 | 


--------------------------------------------------------------------------------