primer analisis datos

.gitignore

+.ipynb_checkpoints/

codigo/trabajo.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import csv\n",
+    "import numpy as np\n",
+    "import matplotlib as plt\n",
+    "import seaborn as sns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_species = pd.read_csv(\"~/ejercicios-clase-08-datos/data-used/species.csv\")\n",
+    "df_surveys = pd.read_csv(\"~/ejercicios-clase-08-datos/data-used/surveys.csv\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pip install --upgrade pip"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_species.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_surveys.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_surveys"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_species['species_id'].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_surveys['species_id'].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_surveysspecie= pd.merge(df_surveys,df_species,how='left',on=['species_id'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_surveysspecie"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_group_specie_id = df_surveysspecie.groupby('taxa').unique()\n",
+    "df_group_specie_id"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.pyplot.scatter(df_surveysspecie[df_surveysspecie['weight']>0],df_surveysspecie[df_surveysspecie['hindfoot_length']>0]['weight'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.pyplot.scatter(df_surveysspecie[df_surveysspecie['taxa']=='Rodent'][df_surveysspecie['hindfoot_length']>0]['year'],df_surveysspecie[df_surveysspecie['taxa']=='Rodent'][df_surveysspecie['hindfoot_length']>0]['hindfoot_length'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_surveysspecie[df_surveysspecie['taxa']=='Rodent']['weight']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_surveysspecie.info()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_surveysspecie['hindfoot_length']=df_surveysspecie['hindfoot_length'].fillna(0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_surveysspecie['weight']=df_surveysspecie['weight'].fillna(0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "plt.pyplot.scatter(df_surveysspecie['taxa'](skipna=True),df_surveysspecie['weight'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_surveysspecie['taxa'].hist()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_surveysspecie['taxa'].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_surveysspecie[df_surveysspecie['weight']>0]['weight'].max()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df_weight_vs_taxa= pd.concat([df_surveysspecie[df_surveysspecie['weight']>0]['weight'],df_surveysspecie[df_surveysspecie['weight']>0]['taxa']],axis=1)\n",
+    "f,ax=plt.subplots()\n",
+    "fig"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

data-used/analisis.csv

@@ -30,4 +30,4 @@ tur08,Francia,9,15.5
 tur09,Francia,10,17
 tur10,Francia,5,11.5
 tur11,Francia,20,26
-tur12,Francia,27,43.5
+tur12,Francia,27,43.5
\ No newline at end of file