Spaces:
Running
Running
Razkaroth commited on
Commit ·
77ed535
1
Parent(s): a11e95a
Explorador listo
Browse files- __pycache__/diagnostics.cpython-311.pyc +0 -0
- app.py +193 -0
- diagnostics.py +21 -0
- requirements.txt +11 -0
__pycache__/diagnostics.cpython-311.pyc
ADDED
|
Binary file (1.88 kB). View file
|
|
|
app.py
CHANGED
|
@@ -0,0 +1,193 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import streamlit as st
|
| 2 |
+
import pandas as pd
|
| 3 |
+
import geopandas as gpd
|
| 4 |
+
from diagnostics import run_df_diagnostics
|
| 5 |
+
import plotly.express as px
|
| 6 |
+
|
| 7 |
+
|
| 8 |
+
st.set_page_config(
|
| 9 |
+
page_title="Explorador REPDA",
|
| 10 |
+
page_icon="🧊",
|
| 11 |
+
layout="wide",
|
| 12 |
+
)
|
| 13 |
+
|
| 14 |
+
st.title("Explorador REPDA")
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
def load_data():
|
| 18 |
+
df = pd.read_json("data.json")
|
| 19 |
+
df = df.drop_duplicates()
|
| 20 |
+
|
| 21 |
+
return df
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
df = load_data()
|
| 25 |
+
|
| 26 |
+
# run_df_diagnostics(df, "Datos iniciales")
|
| 27 |
+
|
| 28 |
+
|
| 29 |
+
# Filters
|
| 30 |
+
|
| 31 |
+
st.sidebar.header("Filtros")
|
| 32 |
+
|
| 33 |
+
categorical_columns = {
|
| 34 |
+
"Titular": "titular",
|
| 35 |
+
"Título": "titulo",
|
| 36 |
+
"Uso amparado": "uso_amparado",
|
| 37 |
+
"Anotaciones marginales": "anotaciones_marginales",
|
| 38 |
+
"Tipo de anexo": "tipo_de_anexo",
|
| 39 |
+
"Estado": "estado",
|
| 40 |
+
"Municipio": "municipio",
|
| 41 |
+
"Región hidrológica": "region_hidrologica",
|
| 42 |
+
"Cuenca": "cuenca",
|
| 43 |
+
"Acuífero": "acuifero",
|
| 44 |
+
"Acuifero homologado": "acuifero_homologado",
|
| 45 |
+
}
|
| 46 |
+
|
| 47 |
+
st.sidebar.write("Filtrado por region via GeoJSON")
|
| 48 |
+
st.sidebar.write("Instrucciones: Entra a https://geojson.io/ y dibuja un poligono")
|
| 49 |
+
st.sidebar.write("Despues descarga el archivo como GeoJSON y cargalo aqui")
|
| 50 |
+
geojson = st.sidebar.file_uploader("Cargar GeoJSON", type=["geojson"])
|
| 51 |
+
|
| 52 |
+
if geojson is not None:
|
| 53 |
+
gdf = gpd.read_file(geojson)
|
| 54 |
+
df = gpd.GeoDataFrame(df)
|
| 55 |
+
df["geometry"] = df.apply(lambda row: gpd.points_from_xy([row.lon], [row.lat])[0], axis=1)
|
| 56 |
+
df.set_geometry('geometry')
|
| 57 |
+
df = gpd.sjoin(df, gdf, op="within")
|
| 58 |
+
df = df.drop(columns=["geometry", "index_right"])
|
| 59 |
+
df = pd.DataFrame(df)
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
columns = st.sidebar.multiselect(
|
| 63 |
+
"Selecciona columnas para filtrar por valor",
|
| 64 |
+
categorical_columns.keys(),
|
| 65 |
+
)
|
| 66 |
+
|
| 67 |
+
if columns:
|
| 68 |
+
for column in columns:
|
| 69 |
+
key = categorical_columns[column]
|
| 70 |
+
column_filters = st.sidebar.multiselect(
|
| 71 |
+
f"Selecciona valores para: {column}",
|
| 72 |
+
df[key].unique().tolist(),
|
| 73 |
+
)
|
| 74 |
+
if column_filters:
|
| 75 |
+
df = df[df[key].isin(column_filters)]
|
| 76 |
+
|
| 77 |
+
numeric_columns = {
|
| 78 |
+
"Volumen total de aguas nacionales": "volumen_total_de_aguas_nacionales",
|
| 79 |
+
"Volumen total de aguas superficiales": "volumen_total_de_aguas_superficiales",
|
| 80 |
+
"Volumen total de aguas subterráneas": "volumen_total_de_aguas_subterraneas",
|
| 81 |
+
"Volumen total de descargas": "volumen_total_de_descargas",
|
| 82 |
+
"Número de descargas en el título": "anexos_descargas",
|
| 83 |
+
"Número de tomas subtarráneas en el título": "anexos_subterraneos",
|
| 84 |
+
"Número de tomas superficiales en el título": "anexos_superficiales",
|
| 85 |
+
"Número de tomas en zonas federales en el título": "anexos_zonas_federales",
|
| 86 |
+
"Volumen individual": "volumen",
|
| 87 |
+
"Superficie": "superficie",
|
| 88 |
+
"Volumen de descarga diario": "volumen_de_descarga_diario",
|
| 89 |
+
"Volumen de descarga anual": "volumen_de_descarga_anual",
|
| 90 |
+
}
|
| 91 |
+
|
| 92 |
+
# Check if there are not None values in columns
|
| 93 |
+
numeric_columns_alive = {}
|
| 94 |
+
other_category_columns = (
|
| 95 |
+
set(df.columns.tolist())
|
| 96 |
+
- set(numeric_columns.values())
|
| 97 |
+
- set(categorical_columns.values())
|
| 98 |
+
)
|
| 99 |
+
|
| 100 |
+
other_catergory_columns_alive = {}
|
| 101 |
+
for key in other_category_columns:
|
| 102 |
+
if df[key].notnull().any():
|
| 103 |
+
other_catergory_columns_alive[key.capitalize().replace("_", " ")] = key
|
| 104 |
+
|
| 105 |
+
if other_catergory_columns_alive.keys() != []:
|
| 106 |
+
other_category_columns = st.sidebar.multiselect(
|
| 107 |
+
"Selecciona columnas para filtrar",
|
| 108 |
+
other_catergory_columns_alive.keys(),
|
| 109 |
+
)
|
| 110 |
+
if other_category_columns:
|
| 111 |
+
for key in other_category_columns:
|
| 112 |
+
column_name = other_catergory_columns_alive[key]
|
| 113 |
+
column_filters = st.sidebar.multiselect(
|
| 114 |
+
f"Selecciona valores para: {key}",
|
| 115 |
+
df[column_name].unique().tolist(),
|
| 116 |
+
)
|
| 117 |
+
if column_filters:
|
| 118 |
+
df = df[df[column_name].isin(column_filters)]
|
| 119 |
+
|
| 120 |
+
for key, column_name in numeric_columns.items():
|
| 121 |
+
if df[column_name].notnull().any():
|
| 122 |
+
if df[column_name].min() != df[column_name].max():
|
| 123 |
+
numeric_columns_alive[key] = column_name
|
| 124 |
+
|
| 125 |
+
|
| 126 |
+
if numeric_columns_alive.keys() != []:
|
| 127 |
+
numeric_column_filters = st.sidebar.multiselect(
|
| 128 |
+
"Selecciona columnas para filtrar por rango",
|
| 129 |
+
numeric_columns_alive.keys(),
|
| 130 |
+
)
|
| 131 |
+
if numeric_column_filters:
|
| 132 |
+
for key in numeric_column_filters:
|
| 133 |
+
column_name = numeric_columns_alive[key]
|
| 134 |
+
st.sidebar.write(f"Escoge un rango para: {key}")
|
| 135 |
+
min_value = st.sidebar.slider(
|
| 136 |
+
f"Valor mínimo para: {key}",
|
| 137 |
+
df[column_name].min(),
|
| 138 |
+
df[column_name].max(),
|
| 139 |
+
df[column_name].min(),
|
| 140 |
+
)
|
| 141 |
+
max_value = st.sidebar.slider(
|
| 142 |
+
f"Valor máximo para: {key}",
|
| 143 |
+
df[column_name].min(),
|
| 144 |
+
df[column_name].max(),
|
| 145 |
+
df[column_name].max(),
|
| 146 |
+
)
|
| 147 |
+
# drop rows that are NONE for that column
|
| 148 |
+
|
| 149 |
+
df = df[(df[column_name] >= min_value) & (df[column_name] <= max_value)]
|
| 150 |
+
|
| 151 |
+
|
| 152 |
+
# run_df_diagnostics(df, "Datos filtrados")
|
| 153 |
+
|
| 154 |
+
|
| 155 |
+
st.header("Mapa")
|
| 156 |
+
|
| 157 |
+
|
| 158 |
+
mapbox = px.scatter_mapbox(
|
| 159 |
+
df,
|
| 160 |
+
lat="lat",
|
| 161 |
+
lon="lon",
|
| 162 |
+
color="tipo_de_anexo",
|
| 163 |
+
hover_name="titular",
|
| 164 |
+
hover_data=[
|
| 165 |
+
"titulo",
|
| 166 |
+
"estado",
|
| 167 |
+
"municipio",
|
| 168 |
+
"region_hidrologica",
|
| 169 |
+
"cuenca",
|
| 170 |
+
"acuifero",
|
| 171 |
+
],
|
| 172 |
+
color_discrete_sequence=px.colors.qualitative.Vivid,
|
| 173 |
+
zoom=4,
|
| 174 |
+
height=900,
|
| 175 |
+
width=1000,
|
| 176 |
+
center={"lat": 23.634501, "lon": -102.552784},
|
| 177 |
+
mapbox_style="carto-positron",
|
| 178 |
+
)
|
| 179 |
+
mapbox.update_traces(marker={"size": 8})
|
| 180 |
+
|
| 181 |
+
st.plotly_chart(mapbox)
|
| 182 |
+
|
| 183 |
+
|
| 184 |
+
st.header("Datos")
|
| 185 |
+
|
| 186 |
+
st.dataframe(df)
|
| 187 |
+
|
| 188 |
+
st.download_button(
|
| 189 |
+
label="Descargar datos",
|
| 190 |
+
data=df.to_csv().encode("utf-8"),
|
| 191 |
+
file_name="data.csv",
|
| 192 |
+
mime="text/csv",
|
| 193 |
+
)
|
diagnostics.py
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import pandas as pd
|
| 2 |
+
import streamlit as st
|
| 3 |
+
|
| 4 |
+
|
| 5 |
+
def run_df_diagnostics(df: pd.DataFrame, name: str = 'df'):
|
| 6 |
+
show = st.checkbox(f'Mostrar diagnóstico de {name}')
|
| 7 |
+
if show:
|
| 8 |
+
expander = st.expander(f'Diagnóstico de {name}')
|
| 9 |
+
expander.write(f'Filas: {df.shape[0]}')
|
| 10 |
+
expander.write(f'Columnas: {df.shape[1]}')
|
| 11 |
+
expander.write('Columnas')
|
| 12 |
+
expander.write(df.columns.tolist())
|
| 13 |
+
expander.write('Tipos de datos')
|
| 14 |
+
expander.write(df.dtypes)
|
| 15 |
+
expander.write('Descripción')
|
| 16 |
+
expander.write(df.describe())
|
| 17 |
+
expander.write('Head (5)')
|
| 18 |
+
expander.write(df.head())
|
| 19 |
+
expander.write('Tail (5)')
|
| 20 |
+
expander.write(df.tail())
|
| 21 |
+
|
requirements.txt
CHANGED
|
@@ -1,5 +1,6 @@
|
|
| 1 |
altair==5.1.2
|
| 2 |
attrs==23.1.0
|
|
|
|
| 3 |
blinker==1.7.0
|
| 4 |
cachetools==5.3.2
|
| 5 |
certifi==2023.11.17
|
|
@@ -8,6 +9,7 @@ click==8.1.7
|
|
| 8 |
click-plugins==1.1.1
|
| 9 |
cligj==0.7.2
|
| 10 |
fiona==1.9.5
|
|
|
|
| 11 |
geopandas==0.14.1
|
| 12 |
gitdb==4.0.11
|
| 13 |
GitPython==3.1.40
|
|
@@ -18,14 +20,22 @@ jsonschema==4.20.0
|
|
| 18 |
jsonschema-specifications==2023.11.1
|
| 19 |
markdown-it-py==3.0.0
|
| 20 |
MarkupSafe==2.1.3
|
|
|
|
| 21 |
mdurl==0.1.2
|
|
|
|
| 22 |
numpy==1.26.2
|
| 23 |
packaging==23.2
|
| 24 |
pandas==2.1.3
|
|
|
|
|
|
|
| 25 |
Pillow==10.1.0
|
|
|
|
|
|
|
| 26 |
protobuf==4.25.1
|
| 27 |
pyarrow==14.0.1
|
|
|
|
| 28 |
pydeck==0.8.1b0
|
|
|
|
| 29 |
Pygments==2.17.1
|
| 30 |
pyproj==3.6.1
|
| 31 |
python-dateutil==2.8.2
|
|
@@ -42,6 +52,7 @@ tenacity==8.2.3
|
|
| 42 |
toml==0.10.2
|
| 43 |
toolz==0.12.0
|
| 44 |
tornado==6.3.3
|
|
|
|
| 45 |
typing_extensions==4.8.0
|
| 46 |
tzdata==2023.3
|
| 47 |
tzlocal==5.2
|
|
|
|
| 1 |
altair==5.1.2
|
| 2 |
attrs==23.1.0
|
| 3 |
+
black==23.11.0
|
| 4 |
blinker==1.7.0
|
| 5 |
cachetools==5.3.2
|
| 6 |
certifi==2023.11.17
|
|
|
|
| 9 |
click-plugins==1.1.1
|
| 10 |
cligj==0.7.2
|
| 11 |
fiona==1.9.5
|
| 12 |
+
flake8==6.1.0
|
| 13 |
geopandas==0.14.1
|
| 14 |
gitdb==4.0.11
|
| 15 |
GitPython==3.1.40
|
|
|
|
| 20 |
jsonschema-specifications==2023.11.1
|
| 21 |
markdown-it-py==3.0.0
|
| 22 |
MarkupSafe==2.1.3
|
| 23 |
+
mccabe==0.7.0
|
| 24 |
mdurl==0.1.2
|
| 25 |
+
mypy-extensions==1.0.0
|
| 26 |
numpy==1.26.2
|
| 27 |
packaging==23.2
|
| 28 |
pandas==2.1.3
|
| 29 |
+
pandas-stubs==2.1.1.230928
|
| 30 |
+
pathspec==0.11.2
|
| 31 |
Pillow==10.1.0
|
| 32 |
+
platformdirs==4.0.0
|
| 33 |
+
plotly==5.18.0
|
| 34 |
protobuf==4.25.1
|
| 35 |
pyarrow==14.0.1
|
| 36 |
+
pycodestyle==2.11.1
|
| 37 |
pydeck==0.8.1b0
|
| 38 |
+
pyflakes==3.1.0
|
| 39 |
Pygments==2.17.1
|
| 40 |
pyproj==3.6.1
|
| 41 |
python-dateutil==2.8.2
|
|
|
|
| 52 |
toml==0.10.2
|
| 53 |
toolz==0.12.0
|
| 54 |
tornado==6.3.3
|
| 55 |
+
types-pytz==2023.3.1.1
|
| 56 |
typing_extensions==4.8.0
|
| 57 |
tzdata==2023.3
|
| 58 |
tzlocal==5.2
|