sergiolucero

import matplotlib.pyplot as plt

conn=sqlite3.connect('revlocal.db')
sqloc = lambda q: pd.read_sql(q, conn)
odf = sqloc('SELECT * FROM stats_v1 ORDER BY Ocupación_Promedio DESC')
#odf=odf[odf.Ocupación_Minima>0];
odf=odf[odf.Ocupación_Máxima<1.20]

fig = plt.figure(figsize=(20,16));odf['cod_hotel']=odf['cod_hotel'].apply(lambda x: x.rstrip())
plt.hlines(y=odf['cod_hotel'],xmin=0, xmax = 100*odf['Ocupación_Promedio'], lw=8, color='cyan') #, color=my_color,linewidth=3, alpha =0.8)

sergiolucero

import boto3
client = boto3.client('textract')

response = client.analyze_document(
    Document={
        'Bytes': b'bytes',
        'S3Object': {
            'Bucket': 'string',
            'Name': 'string',
            'Version': 'string'

sergiolucero

import datetime, requests
import io, glob, os
import PyPDF2
from bs4 import BeautifulSoup

fecha = datetime.datetime.now().strftime('%Y%m%d')
print('FECHA:', fecha)
root='https://www.mercuriovalpo.cl/impresa/%s/%s/%s/' %(fecha[:4], fecha[4:6], fecha[6:])
base = root + 'papel'

sergiolucero

OBJECTID,ID_CIRCUNSCRIPCION,CIRCUNCRIPCION_ELECTORAL,COD_LOCAL,LOCAL_VOTACION,DIRECCION,Latitud,Longitud,ELECTORES,CUT_PROV,PROVINCIA,CUT_REG,CUT_COM,REGION,COMUNA,CUT_COM_ENT,CUT_REG_ENT,ORD_REG,N_MESAS,CASOS_ACTIVOS,GOOGLE_MAPS
1,589,ALTO HOSPICIO,1036,ANEXO DE COLEGIO SAN ANTONIO DE MATILLA,LOS TAMARUGOS ESQUINA LOS KIWIS,-20.2687,-70.1029,3402,011,Iquique,01,01107,Tarapacá,Alto Hospicio,1107,1,2,10,64.0,"<a href=""https://www.google.cl/maps/dir//-20.2687,-70.1029"" target=_blank"">Ir con Google Maps</a>"
2,589,ALTO HOSPICIO,1025,COLEGIO MARISTA HERMANO FERNANDO,AVENIDA RICARDO LAGOS 4201,-20.2864,-70.0823,6386,011,Iquique,01,01107,Tarapacá,Alto Hospicio,1107,1,2,19,0.0,"<a href=""https://www.google.cl/maps/dir//-20.2864,-70.0823"" target=_blank"">Ir con Google Maps</a>"
3,589,ALTO HOSPICIO,1061,COLEGIO METODISTA WILLIAM TAYLOR,AVENIDA LOS ALAMOS 3025,-20.2678,-70.1044,6405,011,Iquique,01,01107,Tarapacá,Alto Hospicio,1107,1,2,19,64.0,"<a href=""https://www.google.cl/maps/dir//-20.2678,-70.1044"" target=_bl

sergiolucero

import matplotlib.pyplot as plt
import seaborn as sns
import altair as alt
# plot.ly, dash...

fig, ax = plt.subplots(1, figsize=(20,12))

sergiolucero

import glob, fitz, pandas as pd

files = glob.glob('folder/*.pdf')
texts = [' '.join([page.get_text() for page in fitz.open(fn)]) 
          for fn in files]

df = pd.DataFrame(dict(file=files, text=texts))
df['cuerpo'] = df.text.apply(lambda t: remove_headandsentence)
df['fallo'] = df.text.apply(lambda t: extract_fallo)
df.to_csv('sentencias.csv', index=False)

sergiolucero

from tqdm import tqdm
import os
import pickle
import pandas as pd

import torch
from torch.utils.data import TensorDataset
from torch.utils.data import DataLoader, RandomSampler, SequentialSampler

from transformers import BertTokenizer, BertForSequenceClassification

sergiolucero

# shape source: https://geoine-ine-chile.opendata.arcgis.com/datasets/186b78e22db44f96a016f9254de44dd4_0
import geopandas as gp

gdf = gp.read_file('MAESTRO_CALLES',init={'epsg:3857'})
gdf = gdf.to_crs('epsg:4326')
gdf.columns=[c.lower() for c in gdf.columns]

for comuna, cdf in gdf.groupby('comuna'):
    ddf = cdf[['comuna','nombre_aux','geometry']]
    ddf.to_file(f'CALLES/{comuna.replace(" ","_")}.json', engine='GeoJSON', single_file=True)

sergiolucero

import pandas as pd
import os, time

DOWNER = 'wget https://cdn.servel.cl/padron/A%05d.pdf'
UPPER = 'aws s3 cp A%05d.pdf s3://quantcldata/CLIENTES/SERVEL/2021/'
DELETE = 'rm A%05d.pdf'

df=pd.read_excel('cut_2018_v03.xls')
comunas=df['Código Comuna 2017']

sergiolucero

import pandas as pd
import joypy
import matplotlib.pyplot as plt

df2 = pd.read_excel('EC_series.xlsx')
df2 = df2[df2.mes==11]  # November
odf=df2[df2.agno<=1950]
df2 = df2[df2.agno>=1980]  # Last 40
# df2.valor -= 23.58   # deviation from the historic November mean