jcmachicao commited on
Commit
3f8da09
·
verified ·
1 Parent(s): 35947dd

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +10 -7
app.py CHANGED
@@ -1,4 +1,4 @@
1
- # Actualizado por: José Carlos Machicao, Fecha de actualización: 2024_06_20
2
 
3
  import streamlit as st
4
  import pandas as pd
@@ -25,12 +25,12 @@ if uploaded_file is not None:
25
  df_050.index = df_050.DNI
26
 
27
  st.write(df_050.shape)
28
-
29
  # Depuración de columnas sólo para aquellas que contribuyen al clustering
30
  col_selec = []
31
  for col in df_050.columns:
32
  u_col = df_050[col].unique()
33
- if len(u_col) < 25:
34
  col_selec.append(col)
35
 
36
  st.header('Lista de variables que será usada para la clusterización')
@@ -159,8 +159,11 @@ if uploaded_file is not None:
159
  ]
160
  enfoqueX['HexDens'] = 'Hex_'+str(c)
161
  enfoques = pd.concat([enfoques, enfoqueX])
162
-
163
- csv = enfoques.to_csv(encoding='iso-8859-1')
 
 
 
164
 
165
  st.download_button(
166
  label="Descargar CSV",
@@ -169,7 +172,7 @@ if uploaded_file is not None:
169
  mime='text/csv'
170
  )
171
 
172
- df = enfoques
173
  cat_col = df.select_dtypes(include=['object']).columns.tolist()
174
  df_dummies = pd.get_dummies(df[cat_col])
175
  percentage_presence = df_dummies.mean()*100
@@ -180,6 +183,7 @@ if uploaded_file is not None:
180
  df2['a'] = result
181
  df2['b'] = result.index
182
  df2 = df2.sort_values(by='a', ascending=False)
 
183
  df3 = df2.head(20)
184
  fig3 = px.line_polar(df3, r='a', theta='b')
185
  st.plotly_chart(fig3)
@@ -192,4 +196,3 @@ if uploaded_file is not None:
192
  file_name='frecuencias_experimento.csv',
193
  mime='text/csv'
194
  )
195
-
 
1
+ # Actualizado por: José Carlos Machicao, Fecha de actualización: 2024_06_24, Taller Lima
2
 
3
  import streamlit as st
4
  import pandas as pd
 
25
  df_050.index = df_050.DNI
26
 
27
  st.write(df_050.shape)
28
+ MAX_CAT = st.slider('Maximo numero de categorias: ', 10, 30, 20)
29
  # Depuración de columnas sólo para aquellas que contribuyen al clustering
30
  col_selec = []
31
  for col in df_050.columns:
32
  u_col = df_050[col].unique()
33
+ if len(u_col) < MAX_CAT:
34
  col_selec.append(col)
35
 
36
  st.header('Lista de variables que será usada para la clusterización')
 
159
  ]
160
  enfoqueX['HexDens'] = 'Hex_'+str(c)
161
  enfoques = pd.concat([enfoques, enfoqueX])
162
+
163
+ st.write(enfoques.columns)
164
+
165
+ enfoques2 = enfoques.drop(columns=['pca_1', 'pca_2'])
166
+ csv = enfoques2.to_csv(encoding='iso-8859-1')
167
 
168
  st.download_button(
169
  label="Descargar CSV",
 
172
  mime='text/csv'
173
  )
174
 
175
+ df = enfoques2
176
  cat_col = df.select_dtypes(include=['object']).columns.tolist()
177
  df_dummies = pd.get_dummies(df[cat_col])
178
  percentage_presence = df_dummies.mean()*100
 
183
  df2['a'] = result
184
  df2['b'] = result.index
185
  df2 = df2.sort_values(by='a', ascending=False)
186
+ st.write(df2.columns)
187
  df3 = df2.head(20)
188
  fig3 = px.line_polar(df3, r='a', theta='b')
189
  st.plotly_chart(fig3)
 
196
  file_name='frecuencias_experimento.csv',
197
  mime='text/csv'
198
  )