Skip to content

Instantly share code, notes, and snippets.

@ClebsonDantasUchoa

ClebsonDantasUchoa/enem.ipynb

Created September 6, 2018 01:58
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save ClebsonDantasUchoa/f28beebcbcb91f2a79c191ba39f83470 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save ClebsonDantasUchoa/f28beebcbcb91f2a79c191ba39f83470 to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
enem.ipynb
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"%matplotlib inline\n",
"import pandas as pd\n",
"from sklearn import linear_model\n",
"from sklearn import linear_model\n",
"from sklearn import metrics"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"data = pd.read_csv(\"train.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(13730, 167)"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.shape"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"dados = pd.DataFrame()\n",
"dados['Q047'] = data['Q047'] #Tipo de escola que concluiu o EM, ALFANUMÉRICA, TRATAR\n",
"dados['Q046'] = data['Q046'] #Já concluiu o EM?, ALFANUMÉRICA, TRATAR\n",
"dados['Q006'] = data['Q006'] #RENDA MENSAL DA FAMILIA, ALFANUMÉRICA, TRATAR\n",
"dados['Q005'] = data['Q005'] #quantidade de pessoas na residencia\n",
"dados['IN_TREINEIRO'] = data['IN_TREINEIRO']\n",
"#dados['TP_ENSINO'] = data['TP_ENSINO']\n",
"dados['TP_ESCOLA'] = data['TP_ESCOLA']\n",
"dados['TP_ST_CONCLUSAO'] = data['TP_ST_CONCLUSAO']\n",
"dados['TP_COR_RACA'] = data['TP_COR_RACA']\n",
"dados['NU_IDADE'] = data['NU_IDADE']\n",
"dados['CO_UF_RESIDENCIA'] = data['CO_UF_RESIDENCIA']\n",
"dados['NU_NOTA_CN'] = data['NU_NOTA_CN']\n",
"dados['NU_NOTA_CH'] = data['NU_NOTA_CH']\n",
"dados['NU_NOTA_LC'] = data['NU_NOTA_LC']\n",
"dados['NU_NOTA_REDACAO'] = data['NU_NOTA_REDACAO']\n",
"dados['NU_NOTA_MT'] = data['NU_NOTA_MT']"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(13730, 15)"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dados.shape"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Q047 0\n",
"Q046 0\n",
"Q006 0\n",
"Q005 0\n",
"IN_TREINEIRO 0\n",
"TP_ESCOLA 0\n",
"TP_ST_CONCLUSAO 0\n",
"TP_COR_RACA 0\n",
"NU_IDADE 0\n",
"CO_UF_RESIDENCIA 0\n",
"dtype: int64"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dados.isnull().sum().head(10)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Q047 0\n",
"Q046 0\n",
"Q006 0\n",
"Q005 0\n",
"IN_TREINEIRO 0\n",
"TP_ESCOLA 0\n",
"TP_ST_CONCLUSAO 0\n",
"TP_COR_RACA 0\n",
"NU_IDADE 0\n",
"CO_UF_RESIDENCIA 0\n",
"NU_NOTA_CN 0\n",
"NU_NOTA_CH 0\n",
"NU_NOTA_LC 0\n",
"NU_NOTA_REDACAO 0\n",
"NU_NOTA_MT 0\n",
"dtype: int64"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dados = dados.dropna()\n",
"dados.isnull().sum()"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(10097, 15)"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dados.shape"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"matematica = pd.DataFrame()\n",
"matematica['NU_NOTA_MT'] = dados['NU_NOTA_MT']\n",
"dados = dados.drop('NU_NOTA_MT', axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"dados = pd.get_dummies(dados, drop_first = True)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(10097, 34)"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dados.shape"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"NU_NOTA_MT 0\n",
"dtype: int64"
]
},
"execution_count": 12,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"matematica.isnull().sum()"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"dadosValues = dados.values\n",
"matematicaValues = matematica.values"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"dados_treino = dadosValues[:822, :]\n",
"dados_teste = dadosValues[822: , :]\n",
"matematica_treino = matematicaValues[ :822]\n",
"matematica_teste = matematicaValues[ 822: ]"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"modelo = linear_model.LinearRegression()\n",
"modelo.fit(dados_treino, matematica_treino)\n",
"predicao = modelo.predict(dados_teste)"
]
}
],
"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": "3.6.5"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment