File size: 7,164 Bytes
4bdf2dd |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 |
import streamlit as st
import warnings
warnings.filterwarnings('ignore')
import pandas as pd
import geopandas as gpd
from difflib import get_close_matches
import tempfile
from io import BytesIO
def convert_to_gdf(uploaded_file):
# Read the file using BytesIO
file_buffer = BytesIO(uploaded_file.read())
# Detect file type and load accordingly
if uploaded_file.name.endswith('.shp'):
gdf = gpd.read_file(file_buffer)
elif uploaded_file.name.endswith(('.geojson', '.json')):
gdf = gpd.read_file(file_buffer, driver='GeoJSON')
else:
raise ValueError("Unsupported file format")
return gdf
# add logo D:\Terradot\repos\crea-carbon-model\app\logo.jpg
st.sidebar.image('logo.jpg', width=200)
st.sidebar.title('Proyecto Crea')
st.sidebar.write('Solo uso interno')
# add sidebar with 2 upload buttons
st.sidebar.header('Upload Files')
uploaded_file = st.sidebar.file_uploader('Upload your shapefile', type=['shp', 'geojson', 'json'], disabled = True)
uploaded_file2 = st.sidebar.file_uploader('Upload your csv file', type=['csv'], disabled = True)
if uploaded_file is not None:
lotes_gdf = convert_to_gdf(uploaded_file)
st.write(lotes_gdf)
if uploaded_file2 is not None:
# read csv and create dataframe
obs_df_2023 = pd.read_csv(uploaded_file2)
# add Test button
test = True #st.sidebar.button('Test')
if 'key' not in st.session_state:
st.session_state['key'] = None
if 'lote_gdf' not in st.session_state:
st.session_state['lote_gdf'] = None
if test:
lotes_gdf = gpd.read_file('data/lotes espacio crea_empresa.shp', encoding='utf-8')
obs_df_2023 = pd.read_csv('data/obs_df_2023_12_1.csv')
obs_df_2023.fillna('-', inplace=True)
obs_df_2023.Campo = obs_df_2023.Campo.astype('str')
empresa_obs = obs_df_2023.EMPRESA.unique().tolist()
# create a state variable to hold the current value of key variable
col1, col2,col3 = st.columns(3)
with col1:
st.header('EMPRESA')
selected_company = st.selectbox(f'Seleccione empresa', empresa_obs, index= 0)
# filter dataframe by selected company
obs_df_2023 = obs_df_2023[obs_df_2023['EMPRESA'] == selected_company]
if st.session_state['lote_gdf'] is not None:
lotes_gdf = st.session_state['lote_gdf']
else:
lotes_gdf = lotes_gdf[lotes_gdf['empresa'] == selected_company]
st.session_state['lote_gdf'] = lotes_gdf
campo_obs = obs_df_2023.Campo.unique().tolist()
campo_gdf = lotes_gdf.campo.unique().tolist()
# Initialize an empty dictionary
similar_dict = {}
N = 3
CUTOFF = 0.72
# Loop through each item in the template list
for item in campo_gdf:
# normalize the stings to lowercase and remove punctuation in campo_obs
campo_obs_norm = [str(c).lower() for c in campo_obs]
campo_obs_norm = [c.replace('.', ' ') for c in campo_obs_norm]
# Find the most similar item in df_columns list
similar_items = get_close_matches(item, campo_obs_norm, N, CUTOFF)
# get the index of the most similar item
similar_items_idx = [campo_obs_norm.index(i) for i in similar_items]
# get the most similar item in the original list
similar_items = [campo_obs[i] for i in similar_items_idx]
# If a similar item is found, add to the dictionary
if similar_items:
similar_dict[item] = similar_items[0]
else:
# If no similar item is found, set value as "no match"
similar_dict[item] = "no match"
similar_dict_df = pd.DataFrame.from_dict(similar_dict, orient='index').reset_index()
similar_dict_df.columns = ['gdf','obs']
# campo_obs = [str(c) for c in campo_obs]
# campo_obs.sort(key=str.lower)
campo_obs.insert(0, 'no match')
all_keys = similar_dict_df['gdf'].unique().tolist()
# Fields
lotes_gdf['campo_obs'] = lotes_gdf['campo'].map(similar_dict)
cutoff = 0.3
def on_click_field(*args):
# key, field, selected_value = key
def inner():
# st.session_state['key'] = key
print(args)
return inner
def show_field(key):
key, selected_value = key
lote_obs = obs_df_2023[obs_df_2023['Campo'] == selected_value]['Lote'].unique().tolist()
lote_obs.insert(0, 'no match')
with col3:
# st.header(st.session_state['key'])
st.header('Lote')
df_field = lotes_gdf[lotes_gdf['campo'] == key]
fields = df_field['lote'].unique().tolist()
for j,field in enumerate(fields):
similar_items = get_close_matches(field, lote_obs, 3, 0.70)
default = similar_items[0] if similar_items else 0
# selected_value = st.multiselect(f'{field} (.shp):', lote_obs, default=default, key='field'+str(j))
selected_value = st.selectbox(f'{field} (.shp):', lote_obs, index = lote_obs.index(default) , key='field'+str(j), on_change=on_click_field(key, field, selected_value))
lotes_gdf.loc[(lotes_gdf['campo'] == key) & (lotes_gdf['lote'] == field), 'lote_obs'] = selected_value
# st.session_state['lote_gdf'] = lotes_gdf
def on_click(key):
def inner():
st.session_state['key'] = key
show_field(key)
return inner
with col2:
st.header('Campo')
for i, key in enumerate(all_keys):
selected_value = st.selectbox(f'{key}:', campo_obs, index=campo_obs.index(similar_dict_df[similar_dict_df['gdf'] == key]['obs'].values[0]))
# selected_value = st.multiselect(f'{key} (.shp):', campo_obs, default=similar_dict_df[similar_dict_df['gdf'] == key]['obs'].values[0], key=i)
lotes_gdf.loc[(lotes_gdf['campo'] == key) & (lotes_gdf['empresa'] == selected_company), 'campo_obs'] = similar_dict_df[similar_dict_df['gdf'] == key]['obs'].values[0]
if selected_value:
similar_dict_df.loc[similar_dict_df['gdf'] == key, 'obs'] = selected_value
value = selected_value
lotes_gdf.loc[(lotes_gdf['campo'] == key) & (lotes_gdf['empresa'] == selected_company), 'campo_obs'] = selected_value
else:
# similar_dict_df.loc[similar_dict_df['gdf'] == key, 'obs'] = 'no match'
value = similar_dict_df.loc[similar_dict_df['gdf'] == key, 'obs']
lotes_gdf.loc[(lotes_gdf['campo'] == key) & (lotes_gdf['empresa'] == selected_company), 'campo_obs'] = value
st.session_state['lote_gdf'] = lotes_gdf
st.button('Show Fields', key=key, on_click=on_click([key,value]))
# st.dataframe(similar_dict_df)
# if st.button('Show Fields'):
# st.dataframe(similar_dict_df)
# add download button
st.sidebar.download_button(
label="Download GeoJSON",
data=lotes_gdf.to_json().encode('utf-8'),
file_name=f'{selected_company}.geojson',
# mime='text/csv',
mime = 'application/json',
)
|