Update app.py
Browse files
app.py
CHANGED
@@ -1,3 +1,5 @@
|
|
|
|
|
|
1 |
import streamlit as st
|
2 |
import pandas as pd
|
3 |
import numpy as np
|
@@ -7,6 +9,7 @@ import plotly.express as px
|
|
7 |
from sklearn.model_selection import train_test_split
|
8 |
from sklearn.preprocessing import StandardScaler
|
9 |
from sklearn.decomposition import PCA
|
|
|
10 |
scaler = StandardScaler()
|
11 |
|
12 |
st.title("Visualización y Clusterización automática de Data de Estudiantes")
|
@@ -62,9 +65,12 @@ if uploaded_file is not None:
|
|
62 |
|
63 |
st.pyplot(plt)
|
64 |
st.write(data_200.columns)
|
|
|
|
|
|
|
65 |
|
66 |
-
VIRTU = st.selectbox('Virtual: ', [
|
67 |
-
INGRE = st.selectbox('Ingresante: ', [
|
68 |
|
69 |
data_210 = data_200[(data_200['COD_DEPARTAMENTO']==VIRTU) & (data_200['ESTADO_ESTUDIANTE']==INGRE)]
|
70 |
|
@@ -72,7 +78,7 @@ if uploaded_file is not None:
|
|
72 |
st.plotly_chart(fig2)
|
73 |
|
74 |
plt.figure(figsize=(10, 8))
|
75 |
-
plt_extracto = plt.hexbin(
|
76 |
plt.colorbar()
|
77 |
plt.title('Hexbin Plot of PCA-Transformed Data')
|
78 |
plt.xlabel('Principal Component 1')
|
@@ -86,4 +92,37 @@ if uploaded_file is not None:
|
|
86 |
plt.ylabel('Frecuencia')
|
87 |
plt.title('Histograma de Densidades')
|
88 |
st.pyplot(plt)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
89 |
|
|
|
1 |
+
# Actualizado por: José Carlos Machicao, Fecha de actualización: 2024_06_19
|
2 |
+
|
3 |
import streamlit as st
|
4 |
import pandas as pd
|
5 |
import numpy as np
|
|
|
9 |
from sklearn.model_selection import train_test_split
|
10 |
from sklearn.preprocessing import StandardScaler
|
11 |
from sklearn.decomposition import PCA
|
12 |
+
pd.DataFrame.iteritems = pd.DataFrame.items
|
13 |
scaler = StandardScaler()
|
14 |
|
15 |
st.title("Visualización y Clusterización automática de Data de Estudiantes")
|
|
|
65 |
|
66 |
st.pyplot(plt)
|
67 |
st.write(data_200.columns)
|
68 |
+
|
69 |
+
#st.write(data_200['COD_DEPARTAMENTO'].unique())
|
70 |
+
#st.write(data_200['ESTADO_ESTUDIANTE'].unique())
|
71 |
|
72 |
+
VIRTU = st.selectbox('Virtual: ', ['UVIR', 'PCGT'])
|
73 |
+
INGRE = st.selectbox('Ingresante: ', ['REGULAR', 'INGRESANTE', 'REINCORPORADO'])
|
74 |
|
75 |
data_210 = data_200[(data_200['COD_DEPARTAMENTO']==VIRTU) & (data_200['ESTADO_ESTUDIANTE']==INGRE)]
|
76 |
|
|
|
78 |
st.plotly_chart(fig2)
|
79 |
|
80 |
plt.figure(figsize=(10, 8))
|
81 |
+
plt_extracto = plt.hexbin(data_210.pca_1, data_210.pca_2, gridsize=50, cmap='inferno')
|
82 |
plt.colorbar()
|
83 |
plt.title('Hexbin Plot of PCA-Transformed Data')
|
84 |
plt.xlabel('Principal Component 1')
|
|
|
92 |
plt.ylabel('Frecuencia')
|
93 |
plt.title('Histograma de Densidades')
|
94 |
st.pyplot(plt)
|
95 |
+
|
96 |
+
offsets = plt_extracto.get_offsets()
|
97 |
+
offsets_df = pd.DataFrame(offsets)
|
98 |
+
st.write(offsets_df.shape)
|
99 |
+
offsets_df['densidad'] = densidades[0]
|
100 |
+
offsets_df.columns = ['col1', 'col2', 'densidad']
|
101 |
+
offset_selec = offsets_df.sort_values(by='densidad', ascending=False)
|
102 |
+
patrones_df = pd.DataFrame(index = [0,1,2,3,4,5,6,7,8,9], data=offset_selec.values[0:10], columns=offset_selec.columns)
|
103 |
+
st.write(patrones_df)
|
104 |
+
|
105 |
+
NUM_CASOS = st.slider("¿Cuántos casos elige explorar?", 1, 10, 3)
|
106 |
+
st.write('Usted ha elegido ', NUM_CASOS, 'casos.')
|
107 |
+
|
108 |
+
radiohex = (data_210.pca_1.max() - data_210.pca_1.min())/50/2
|
109 |
+
|
110 |
+
CASOX = st.selectbox('Elija el caso: ', (1, 2, 3))
|
111 |
+
|
112 |
+
a, b = patrones_df.col1[CASOX], patrones_df.col2[CASOX]
|
113 |
+
enfoqueX = data_210[
|
114 |
+
(data_210.pca_1 > a - radiohex) &
|
115 |
+
(data_210.pca_1 < a + radiohex) &
|
116 |
+
(data_210.pca_2 > b - radiohex) &
|
117 |
+
(data_210.pca_2 < b + radiohex)
|
118 |
+
]
|
119 |
+
|
120 |
+
st.write(enfoqueX.shape)
|
121 |
+
LISTA_SELEC = st.multiselect('Escoja la variable de color: ', list(enfoqueX.columns))
|
122 |
+
st.write(LISTA_SELEC)
|
123 |
+
|
124 |
+
fig2 = px.parallel_categories(data_frame=enfoqueX[list(LISTA_SELEC)])
|
125 |
+
st.plotly_chart(fig2)
|
126 |
+
|
127 |
+
|
128 |
|