Finish v1.1.1

covidnpi/config.toml

@@ -14,15 +14,15 @@ movavg = 7
 link = "https://cnecovid.isciii.es/covid19/resources/casos_tecnica_provincia.csv"
 
 [postal_to_code]
-1 = "VI"
-2 = "AB"
-3 = "A"
-4 = "AL"
-5 = "AV"
-6 = "BA"
-7 = "PM"
-8 = "B"
-9 = "BU"
+01 = "VI"
+02 = "AB"
+03 = "A"
+04 = "AL"
+05 = "AV"
+06 = "BA"
+07 = "PM"
+08 = "B"
+09 = "BU"
 10 = "CC"
 11 = "CA"
 12 = "CS"
@@ -67,7 +67,6 @@ link = "https://cnecovid.isciii.es/covid19/resources/casos_tecnica_provincia.csv
 51 = "CE"
 52 = "ML"
 
-
 [code_to_provincia]
 A = "Alacant"
 AB = "Albacete"
@@ -159,6 +158,7 @@ navarra = "NA"
 orense = "OR"
 asturias = "O"
 palencia = "P"
+grancanaria = "GC"
 gran_canaria = "GC"
 pontevedra = "PO"
 salamanca = "SA"
@@ -168,6 +168,7 @@ segovia = "SG"
 sevilla = "SE"
 soria = "SO"
 tarragona = "T"
+tenerife = "TF"
 teruel = "TE"
 toledo = "TO"
 valencia = "V"
@@ -176,6 +177,14 @@ vizcaya = "BI"
 zamora = "ZA"
 zaragoza = "Z"
 
+[isla_to_provincia]
+elhierro = "grancanaria"
+formentera = "tenerife"
+fuerteventura = "grancanaria"
+ibiza = "tenerife"
+lagomera = "grancanaria"
+lanzarote = "grancanaria"
+menorca = "tenerife"
 
 [code_to_poblacion]
 AB = 388270

covidnpi/preprocess_and_score.py

@@ -10,7 +10,7 @@
     store_dict_scores,
     store_dict_provincia_to_medidas,
 )
-from covidnpi.utils.logging import logger
+from covidnpi.utils.log import logger
 from covidnpi.utils.mobility import mobility_report_to_csv
 from covidnpi.utils.preprocess import read_npi_and_build_dict
 from covidnpi.utils.taxonomia import PATH_TAXONOMIA

covidnpi/score/score_ambitos.py

@@ -2,7 +2,7 @@
 import typer
 
 from covidnpi.utils.dictionaries import store_dict_scores, load_dict_scores
-from covidnpi.utils.logging import logger
+from covidnpi.utils.log import logger
 from covidnpi.utils.taxonomia import return_item_ponderacion, PATH_TAXONOMIA
 
 

covidnpi/score/score_items.py

@@ -5,7 +5,7 @@
 import typer
 
 from covidnpi.utils.dictionaries import store_dict_scores, load_dict_scores
-from covidnpi.utils.logging import logger
+from covidnpi.utils.log import logger
 
 
 def score_items(df: pd.DataFrame):

covidnpi/score/score_medidas.py

@@ -6,7 +6,7 @@
 import typer
 
 from covidnpi.utils.dictionaries import store_dict_scores, load_dict_medidas
-from covidnpi.utils.logging import logger
+from covidnpi.utils.log import logger
 from covidnpi.utils.taxonomia import return_taxonomia, return_all_medidas
 
 warnings.simplefilter(action="ignore", category=FutureWarning)

covidnpi/utils/combine.py

@@ -1,8 +1,14 @@
-import pandas as pd
-import typer
 from pathlib import Path
 from typing import Union
 
+import numpy as np
+import pandas as pd
+import typer
+
+from covidnpi.utils.config import load_config
+from covidnpi.utils.dictionaries import reverse_dictionary
+from covidnpi.utils.log import logger
+
 COLS_AMBITO = [
     "fecha",
     "provincia",
@@ -38,12 +44,53 @@ def combine_csv(path: Union[Path, str], colname: str) -> pd.DataFrame:
     return pd.concat(df_dict, names=[colname]).reset_index().drop(columns="level_1")
 
 
+def add_unidad_territorial(
+    df: pd.DataFrame, path_config: str = "covidnpi/config.toml"
+) -> pd.DataFrame:
+    # Load all conversion dictionaries
+    isle_to_province = load_config(path_config, "isla_to_provincia")
+    # Check for islands
+    unidad = df["provincia"].copy()
+    province = df["provincia"].replace(isle_to_province)
+    # Create unidad_territorial column, that contains the islands
+    df.insert(loc=2, column="unidad_territorial", value=unidad)
+    df.loc[unidad == province, "unidad_territorial"] = np.nan
+    df["provincia"] = province
+    return df
+
+
+def add_province_code(
+    df: pd.DataFrame, path_config: str = "covidnpi/config.toml"
+) -> pd.DataFrame:
+    # Load all conversion dictionaries
+    province_to_code = load_config(path_config, "provincia_to_code")
+    code_to_province = load_config(path_config, "code_to_provincia")
+    postal_to_code = load_config(path_config, "postal_to_code")
+    code_to_postal = reverse_dictionary(postal_to_code)
+    # Get codes
+    code = df["provincia"].map(province_to_code)
+    # Replace province name and add code
+    df["provincia"] = code.map(code_to_province)
+    df.insert(loc=1, column="cod_prov", value=code.map(code_to_postal))
+    return df
+
+
+def add_ccaa(df: pd.DataFrame, path_ccaa: str = "data/CCAA.csv") -> pd.DataFrame:
+    ccaa = pd.read_csv(path_ccaa, dtype={"Codigo": str, "Cod_CCAA": str})
+    code_to_ccaa = dict(zip(ccaa["Codigo"], ccaa["CCAA"]))
+    df.insert(loc=1, column="ccaa", value=df["cod_prov"].map(code_to_ccaa))
+    code_to_codccaa = dict(zip(ccaa["Codigo"], ccaa["Cod_CCAA"]))
+    df.insert(loc=2, column="cod_ccaa", value=df["cod_prov"].map(code_to_codccaa))
+    return df
+
+
 def combine_csv_ambito(
     path_data: str = "output/score_ambito", path_output: str = "npi_stringency.csv"
 ) -> pd.DataFrame:
     df = combine_csv(path_data, "provincia")
     # Tomar las columnas relevantes y ordenar por fecha
     df = df[COLS_AMBITO].sort_values(["fecha", "provincia"])
+    df = df.pipe(add_unidad_territorial).pipe(add_province_code).pipe(add_ccaa)
     df.to_csv(path_output, index=False)
 
 

covidnpi/utils/dictionaries.py

@@ -49,3 +49,8 @@ def load_dict_scores(path_scores: str = "output/score_medidas"):
         df = pd.read_csv(path_file, index_col="fecha")
         dict_scores.update({provincia: df})
     return dict_scores
+
+
+def reverse_dictionary(d: dict) -> dict:
+    reversed_dictionary = {value: key for (key, value) in d.items()}
+    return reversed_dictionary

covidnpi/utils/mobility.py

@@ -4,7 +4,7 @@
 
 from covidnpi.utils.casos import load_casos_df, return_casos_of_provincia_normed
 from covidnpi.utils.config import load_config
-from covidnpi.utils.logging import logger
+from covidnpi.utils.log import logger
 from covidnpi.utils.series import (
     cumulative_incidence,
     compute_growth_rate,

covidnpi/utils/preprocess.py

@@ -7,7 +7,7 @@
 import xlrd
 
 from covidnpi.utils.dictionaries import store_dict_provincia_to_medidas
-from covidnpi.utils.logging import logger, raise_type_warning, raise_value_warning
+from covidnpi.utils.log import logger, raise_type_warning, raise_value_warning
 from covidnpi.utils.taxonomia import return_all_medidas, PATH_TAXONOMIA
 
 LIST_BASE_SHEET = ["base", "base-regional-provincias", "BASE"]
@@ -252,15 +252,6 @@ def rename_unidad(df, rename: dict = None) -> pd.DataFrame:
 
     df = df.copy()
 
-    # Listamos los valores de unidad que no se corresponden a los esperados
-    list_unidad = df["unidad"].dropna().astype(str).unique()
-    list_unidad = sorted(set(list_unidad) - set(DICT_UNIDAD_RENAME.values()))
-    if len(list_unidad) > 0:
-        logger.warning(
-            f"Valores no esperados encontrados en la columna 'unidad': "
-            f"{', '.join(list_unidad)}"
-        )
-
     # If any value contains the exact word, change value to word
     list_rename = set(rename.values())
     for word in list_rename:
@@ -271,6 +262,15 @@ def rename_unidad(df, rename: dict = None) -> pd.DataFrame:
 
     # Rename the rest
     df["unidad"] = df["unidad"].replace(rename)
+
+    # Listamos los valores de unidad que no se corresponden a los esperados
+    list_unidad = df["unidad"].dropna().astype(str).unique()
+    list_unidad = sorted(set(list_unidad) - list_rename)
+    if len(list_unidad) > 0:
+        logger.warning(
+            f"Valores no esperados encontrados en la columna 'unidad': "
+            f"{', '.join(list_unidad)}"
+        )
     return df
 
 

covidnpi/web/datastore.py

@@ -9,7 +9,7 @@
     return_casos_of_provincia_normed,
 )
 from covidnpi.utils.config import load_config
-from covidnpi.utils.logging import logger
+from covidnpi.utils.log import logger
 from covidnpi.utils.series import cumulative_incidence, compute_growth_rate
 from covidnpi.utils.taxonomia import return_taxonomia, PATH_TAXONOMIA
 from covidnpi.web.mongo import load_mongo

covidnpi/web/generate_json.py

@@ -3,7 +3,7 @@
 import typer
 
 from covidnpi.utils.config import load_config
-from covidnpi.utils.logging import logger
+from covidnpi.utils.log import logger
 from covidnpi.web.mongo import load_mongo
 
 

data/CCAA.csv

@@ -0,0 +1,53 @@
+CCAA,Cod_CCAA,Provincia,Texto,Codigo
+Comunitat Valenciana,10,Castelló,Castellón,12
+Andalucía,01,Huelva,Huelva,21
+Canarias,05,Santa Cruz de Tenerife,Santa Cruz de Tenerife,38
+Castilla y León,07,Palencia,Palencia,34
+Castilla - La Mancha,08,Guadalajara,Guadalajara,19
+Comunidad de Madrid,13,Madrid,Madrid,28
+Cantabria,06,Cantabria,Cantabria,39
+País Vasco,16,Bizkaia,Vizcaya,48
+Castilla y León,07,Segovia,Segovia,40
+Castilla y León,07,Zamora,Zamora,49
+Extremadura,11,Badajoz,Badajoz,06
+Aragón,02,Huesca,Huesca,22
+Galicia,12,Lugo,Lugo,27
+Illes Balears,04,Illes Balears,Islas Baleares,07
+Comunidad Foral de Navarra,15,Navarra,Navarra,31
+Comunitat Valenciana,10,Alacant,Alicante,03
+Región de Murcia,14,Murcia,Murcia,30
+Castilla y León,07,Ávila,Ávila,05
+Andalucía,01,Cádiz,Cádiz,11
+Comunitat Valenciana,10,València,Valencia,46
+Cataluña,09,Barcelona,Barcelona,08
+Castilla - La Mancha,08,Cuenca,Cuenca,16
+Castilla - La Mancha,08,Albacete,Albacete,02
+Extremadura,11,Cáceres,Cáceres,10
+Castilla - La Mancha,08,Ciudad Real,Ciudad Real,13
+Cataluña,09,Lleida,Lleida,25
+Galicia,12,Ourense,Orense,32
+Cataluña,09,Tarragona,Tarragona,43
+Castilla y León,07,Burgos,Burgos,09
+País Vasco,16,Gipuzcoa,Guipúzcoa,20
+Castilla y León,07,Salamanca,Salamanca,37
+Melilla,19,Melilla,Melilla,52
+Andalucía,01,Sevilla,Sevilla,41
+Castilla y León,07,Valladolid,Valladolid,47
+Ceuta,18,Ceuta,Ceuta,51
+Andalucía,01,Jaén,Jaén,23
+Andalucía,01,Málaga,Málaga,29
+Andalucía,01,Córdoba,Córdoba,14
+Castilla y León,07,León,León,24
+País Vasco,16,Araba,Álava,01
+Cataluña,09,Girona,Gerona,17
+Andalucía,01,Granada,Granada,18
+"Rioja, La",17,La Rioja,La Rioja,26
+Canarias,05,Las Palmas,Las Palmas,35
+Galicia,12,Pontevedra,Pontevedra,36
+"Asturias, Principado de",03,Asturias,Asturias,33
+Castilla y León,07,Soria,Soria,42
+Castilla - La Mancha,08,Toledo,Toledo,45
+Galicia,12,A Coruña,La Coruña,15
+Aragón,02,Teruel,Teruel,44
+Aragón,02,Zaragoza,Zaragoza,50
+Andalucía,01,Almería,Almería,04