Spaces:
Sleeping
Sleeping
update
Browse files- main.py +396 -0
- requirements.txt +11 -0
main.py
ADDED
|
@@ -0,0 +1,396 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import streamlit as st
|
| 2 |
+
import pandas as pd
|
| 3 |
+
import numpy as np
|
| 4 |
+
import plotly.express as px
|
| 5 |
+
import plotly.graph_objects as go
|
| 6 |
+
from plotly.subplots import make_subplots
|
| 7 |
+
from prophet import Prophet
|
| 8 |
+
from prophet.plot import plot_plotly, plot_components_plotly
|
| 9 |
+
from datetime import datetime
|
| 10 |
+
import statsmodels.api as sm
|
| 11 |
+
from datetime import datetime
|
| 12 |
+
import io
|
| 13 |
+
# Configuración de la página
|
| 14 |
+
st.set_page_config(page_title="Analytics Dashboard", layout="wide", page_icon="📈")
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
if 'df' not in st.session_state:
|
| 18 |
+
st.session_state.df = pd.DataFrame()
|
| 19 |
+
|
| 20 |
+
# Función para cargar datos
|
| 21 |
+
@st.cache_data
|
| 22 |
+
def load_data(uploaded_file):
|
| 23 |
+
try:
|
| 24 |
+
if uploaded_file.name.endswith('.csv'):
|
| 25 |
+
# Para CSV, detectar automáticamente el separador
|
| 26 |
+
content = uploaded_file.read().decode('utf-8')
|
| 27 |
+
dialect = io.StringIO(content[:1024]).read()
|
| 28 |
+
sniffer = pd.io.parsing.Sniffer()
|
| 29 |
+
delimiter = sniffer.sniff(dialect).delimiter
|
| 30 |
+
|
| 31 |
+
uploaded_file.seek(0) # Resetear el puntero del archivo
|
| 32 |
+
df = pd.read_csv(uploaded_file, delimiter=delimiter)
|
| 33 |
+
else:
|
| 34 |
+
# Para Excel
|
| 35 |
+
df = pd.read_excel(uploaded_file)
|
| 36 |
+
|
| 37 |
+
# Convertir automáticamente columnas de fecha
|
| 38 |
+
df = df.apply(lambda col: pd.to_datetime(col, errors='ignore')
|
| 39 |
+
if col.dtypes == object else col)
|
| 40 |
+
return df
|
| 41 |
+
except Exception as e:
|
| 42 |
+
st.error(f"Error al cargar el archivo: {e}")
|
| 43 |
+
return None
|
| 44 |
+
|
| 45 |
+
# Función para combinar columnas de fecha
|
| 46 |
+
def create_date_column(df):
|
| 47 |
+
date_cols = st.columns(3)
|
| 48 |
+
with date_cols[0]:
|
| 49 |
+
year_col = st.selectbox("Selecciona columna de AÑO", df.columns)
|
| 50 |
+
with date_cols[1]:
|
| 51 |
+
month_col = st.selectbox("Selecciona columna de MES", df.columns[df.columns != year_col])
|
| 52 |
+
with date_cols[2]:
|
| 53 |
+
condition = [(column != year_col and column != month_col) for column in df.columns]
|
| 54 |
+
day_col = st.selectbox("Selecciona columna de DÍA", df.columns[condition])
|
| 55 |
+
|
| 56 |
+
if st.button("Crear fecha combinada"):
|
| 57 |
+
try:
|
| 58 |
+
# Convertir a enteros primero para mayor seguridad
|
| 59 |
+
df['year'] = df[year_col].astype(int)
|
| 60 |
+
df['month'] = df[month_col].astype(int)
|
| 61 |
+
df['day'] = df[day_col].astype(int)
|
| 62 |
+
|
| 63 |
+
# Crear la columna de fecha
|
| 64 |
+
df['ds'] = pd.to_datetime(df[['year', 'month', 'day']])
|
| 65 |
+
|
| 66 |
+
# Mantener solo la columna resultante
|
| 67 |
+
df = df.drop(['year', 'month', 'day'], axis=1)
|
| 68 |
+
|
| 69 |
+
st.session_state.df = df
|
| 70 |
+
st.success("Fecha creada exitosamente! Muestra de fechas:")
|
| 71 |
+
st.dataframe(st.session_state.df[['ds']].head())
|
| 72 |
+
except Exception as e:
|
| 73 |
+
st.error(f"Error al crear fecha: {str(e)}")
|
| 74 |
+
return df
|
| 75 |
+
|
| 76 |
+
# Función para descomposición de series temporales
|
| 77 |
+
def plot_decomposition(df, date_col, value_col):
|
| 78 |
+
st.header("📈 Descomposición de Series Temporales")
|
| 79 |
+
|
| 80 |
+
col1, col2 = st.columns(2)
|
| 81 |
+
with col1:
|
| 82 |
+
decomposition_model = st.selectbox("Modelo de descomposición", ["aditiva", "multiplicativa"])
|
| 83 |
+
with col2:
|
| 84 |
+
period = st.number_input("Periodo estacional", min_value=2, max_value=365, value=12)
|
| 85 |
+
|
| 86 |
+
if st.button("Analizar componentes"):
|
| 87 |
+
try:
|
| 88 |
+
ts = df.set_index(date_col)[value_col].sort_index()
|
| 89 |
+
decomposition = sm.tsa.seasonal_decompose(ts.dropna(),
|
| 90 |
+
model=decomposition_model,
|
| 91 |
+
period=period)
|
| 92 |
+
|
| 93 |
+
fig = make_subplots(rows=4, cols=1, shared_xaxes=True, vertical_spacing=0.1,
|
| 94 |
+
subplot_titles=("Serie Original", "Tendencia",
|
| 95 |
+
"Estacionalidad", "Residuales"))
|
| 96 |
+
|
| 97 |
+
# Serie Original
|
| 98 |
+
fig.add_trace(go.Scatter(x=ts.index, y=ts, mode='lines', name="Original",
|
| 99 |
+
line=dict(color='#1f77b4')), row=1, col=1)
|
| 100 |
+
|
| 101 |
+
# Tendencia
|
| 102 |
+
fig.add_trace(go.Scatter(x=decomposition.trend.index, y=decomposition.trend,
|
| 103 |
+
mode='lines', name="Tendencia", line=dict(color='#ff7f0e')),
|
| 104 |
+
row=2, col=1)
|
| 105 |
+
|
| 106 |
+
# Estacionalidad
|
| 107 |
+
fig.add_trace(go.Scatter(x=decomposition.seasonal.index, y=decomposition.seasonal,
|
| 108 |
+
mode='lines', name="Estacionalidad", line=dict(color='#2ca02c')),
|
| 109 |
+
row=3, col=1)
|
| 110 |
+
|
| 111 |
+
# Residuales
|
| 112 |
+
fig.add_trace(go.Scatter(x=decomposition.resid.index, y=decomposition.resid,
|
| 113 |
+
mode='lines', name="Residuales", line=dict(color='#d62728')),
|
| 114 |
+
row=4, col=1)
|
| 115 |
+
|
| 116 |
+
fig.update_layout(title_text=f"Descomposición de {value_col}",
|
| 117 |
+
height=800, showlegend=False,
|
| 118 |
+
hovermode="x unified")
|
| 119 |
+
st.plotly_chart(fig, use_container_width=True)
|
| 120 |
+
|
| 121 |
+
except Exception as e:
|
| 122 |
+
st.error(f"Error en descomposición: {str(e)}")
|
| 123 |
+
|
| 124 |
+
# Análisis de datos
|
| 125 |
+
def perform_analysis(df):
|
| 126 |
+
with st.expander("🔍 Análisis Rápido", expanded=True):
|
| 127 |
+
c1, c2, c3 = st.columns(3)
|
| 128 |
+
with c1:
|
| 129 |
+
st.metric("Registros", df.shape[0])
|
| 130 |
+
with c2:
|
| 131 |
+
st.metric("Variables", df.shape[1])
|
| 132 |
+
with c3:
|
| 133 |
+
missing = df.isna().sum().sum()
|
| 134 |
+
st.metric("Valores Faltantes", missing)
|
| 135 |
+
# Análisis estadístico
|
| 136 |
+
with st.expander("📊 Estadísticas Descriptivas"):
|
| 137 |
+
st.dataframe(df.describe().T.style.background_gradient(cmap='Blues'))
|
| 138 |
+
|
| 139 |
+
with st.expander("📊 Vista General", expanded=True):
|
| 140 |
+
|
| 141 |
+
date_col = 'ds'
|
| 142 |
+
values = [column for column in df.select_dtypes(include=np.number).columns if column not in ['ds', "Año", "Mes", "Día", "Dia"]]
|
| 143 |
+
value_col = st.selectbox("Seleccionar variable para análisis",
|
| 144 |
+
values)
|
| 145 |
+
plot_decomposition(df, date_col, value_col)
|
| 146 |
+
|
| 147 |
+
# Análisis de correlación
|
| 148 |
+
with st.expander("🧮 Matriz de Correlación"):
|
| 149 |
+
numeric_df = df.select_dtypes(include=np.number)
|
| 150 |
+
if len(numeric_df.columns) > 1:
|
| 151 |
+
corr = numeric_df.corr()
|
| 152 |
+
fig = go.Figure(data=go.Heatmap(
|
| 153 |
+
z=corr.values,
|
| 154 |
+
x=corr.columns,
|
| 155 |
+
y=corr.index,
|
| 156 |
+
colorscale='RdBu',
|
| 157 |
+
zmin=-1,
|
| 158 |
+
zmax=1,
|
| 159 |
+
hoverongaps=True,
|
| 160 |
+
text=np.round(corr.values, 2)
|
| 161 |
+
))
|
| 162 |
+
fig.update_layout(title='Matriz de Correlación',
|
| 163 |
+
width=800,
|
| 164 |
+
height=600)
|
| 165 |
+
st.plotly_chart(fig, use_container_width=True)
|
| 166 |
+
else:
|
| 167 |
+
st.warning("No hay suficientes columnas numéricas para calcular correlaciones")
|
| 168 |
+
|
| 169 |
+
# Visualización temporal interactiva
|
| 170 |
+
def time_analysis(df, date_col):
|
| 171 |
+
with st.expander("⏳ Análisis Temporal", expanded=True):
|
| 172 |
+
col1, col2 = st.columns([1, 3])
|
| 173 |
+
with col1:
|
| 174 |
+
values = [column for column in df.select_dtypes(include=np.number).columns if column not in ['ds', "Año", "Mes", "Día", "Dia"]]
|
| 175 |
+
value_col = st.selectbox("Seleccionar variable para análisis temporal",
|
| 176 |
+
values)
|
| 177 |
+
resample_freq = st.selectbox("Frecuencia de muestreo",
|
| 178 |
+
['D', 'W', 'M', 'Q', 'Y'])
|
| 179 |
+
with col2:
|
| 180 |
+
try:
|
| 181 |
+
ts_df = df.set_index(date_col)[value_col]
|
| 182 |
+
resampled = ts_df.resample(resample_freq).mean()
|
| 183 |
+
|
| 184 |
+
fig = px.line(resampled,
|
| 185 |
+
title=f"Evolución Temporal - {value_col}",
|
| 186 |
+
labels={'value': value_col, 'index': 'Fecha'},
|
| 187 |
+
markers=True)
|
| 188 |
+
fig.update_traces(line_width=2,
|
| 189 |
+
hovertemplate="Fecha: %{x}<br>Valor: %{y:.2f}")
|
| 190 |
+
fig.update_layout(hovermode="x unified")
|
| 191 |
+
st.plotly_chart(fig, use_container_width=True)
|
| 192 |
+
except Exception as e:
|
| 193 |
+
st.error(f"Error en análisis temporal: {e}")
|
| 194 |
+
|
| 195 |
+
# Pronósticos con Prophet
|
| 196 |
+
def forecast_section(df, date_col):
|
| 197 |
+
st.header("🔮 Modelo Predictivo")
|
| 198 |
+
|
| 199 |
+
# Verificar y convertir a datetime si es necesario
|
| 200 |
+
if not np.issubdtype(df[date_col].dtype, np.datetime64):
|
| 201 |
+
df[date_col] = pd.to_datetime(df[date_col], errors='coerce')
|
| 202 |
+
|
| 203 |
+
col1, col2 = st.columns(2)
|
| 204 |
+
with col1:
|
| 205 |
+
# Selección de agrupación temporal
|
| 206 |
+
freq_agrupacion = st.selectbox(
|
| 207 |
+
"Frecuencia de agrupación",
|
| 208 |
+
options=['Diaria', 'Semanal', 'Mensual'],
|
| 209 |
+
help="Agrupa los datos en intervalos temporales antes de modelar"
|
| 210 |
+
)
|
| 211 |
+
|
| 212 |
+
# Mapeo de frecuencias de pandas
|
| 213 |
+
freq_map = {
|
| 214 |
+
'Diaria': 'D',
|
| 215 |
+
'Semanal': 'W-MON',
|
| 216 |
+
'Mensual': 'MS'
|
| 217 |
+
}
|
| 218 |
+
|
| 219 |
+
# Selección de método de agregación
|
| 220 |
+
metodo_agregacion = st.selectbox(
|
| 221 |
+
"Método de agregación",
|
| 222 |
+
options=['Suma', 'Promedio', 'Maximo', 'Minimo'],
|
| 223 |
+
index=1
|
| 224 |
+
)
|
| 225 |
+
|
| 226 |
+
with col2:
|
| 227 |
+
values = [column for column in df.select_dtypes(include=np.number).columns
|
| 228 |
+
if column not in ['ds', "Año", "Mes", "Día", "Dia"]]
|
| 229 |
+
target_col = st.selectbox("Variable a predecir", values)
|
| 230 |
+
min_value = 1
|
| 231 |
+
max_value = 14
|
| 232 |
+
value = 7
|
| 233 |
+
if freq_agrupacion == "Mensual":
|
| 234 |
+
max_value = 2
|
| 235 |
+
value = 1
|
| 236 |
+
elif freq_agrupacion == "Semanal":
|
| 237 |
+
max_value = 4
|
| 238 |
+
value = 2
|
| 239 |
+
periods = st.number_input(
|
| 240 |
+
"Periodos a predecir",
|
| 241 |
+
min_value=min_value,
|
| 242 |
+
max_value=max_value,
|
| 243 |
+
value=value,
|
| 244 |
+
help="Número de unidades temporales a pronosticar según la frecuencia seleccionada"
|
| 245 |
+
)
|
| 246 |
+
|
| 247 |
+
# Agrupación temporal de los datos
|
| 248 |
+
try:
|
| 249 |
+
df_temp = df.set_index(date_col)[target_col]
|
| 250 |
+
|
| 251 |
+
if metodo_agregacion == 'Suma':
|
| 252 |
+
df_grouped = df_temp.resample(freq_map[freq_agrupacion]).sum()
|
| 253 |
+
elif metodo_agregacion == 'Promedio':
|
| 254 |
+
df_grouped = df_temp.resample(freq_map[freq_agrupacion]).mean()
|
| 255 |
+
elif metodo_agregacion == 'Maximo':
|
| 256 |
+
df_grouped = df_temp.resample(freq_map[freq_agrupacion]).max()
|
| 257 |
+
elif metodo_agregacion == 'Minimo':
|
| 258 |
+
df_grouped = df_temp.resample(freq_map[freq_agrupacion]).min()
|
| 259 |
+
|
| 260 |
+
df_grouped = df_grouped.reset_index()
|
| 261 |
+
df_grouped.columns = [date_col, target_col]
|
| 262 |
+
df = df_grouped.dropna()
|
| 263 |
+
|
| 264 |
+
# Mostrar vista previa de los datos agrupados
|
| 265 |
+
with st.expander("📊 Vista de datos agrupados", expanded=False):
|
| 266 |
+
st.write(f"Formato actual: {freq_agrupacion} ({len(df)} registros)")
|
| 267 |
+
fig = px.line(df, x=date_col, y=target_col, title=f"Datos Agrupados - {target_col}")
|
| 268 |
+
fig.update_traces(mode='lines+markers')
|
| 269 |
+
st.plotly_chart(fig, use_container_width=True)
|
| 270 |
+
|
| 271 |
+
except Exception as e:
|
| 272 |
+
st.error(f"Error al agrupar datos: {str(e)}")
|
| 273 |
+
return
|
| 274 |
+
|
| 275 |
+
# Resto de la configuración del modelo
|
| 276 |
+
|
| 277 |
+
if st.button("Ejecutar Pronóstico", type="primary"):
|
| 278 |
+
with st.spinner("Creando modelo..."):
|
| 279 |
+
try:
|
| 280 |
+
prophet_df = df[[date_col, target_col]].rename(columns={
|
| 281 |
+
date_col: 'ds',
|
| 282 |
+
target_col: 'y'
|
| 283 |
+
}).dropna()
|
| 284 |
+
|
| 285 |
+
model = Prophet()
|
| 286 |
+
|
| 287 |
+
|
| 288 |
+
model.fit(prophet_df)
|
| 289 |
+
|
| 290 |
+
# Generar futuro considerando la frecuencia
|
| 291 |
+
future = model.make_future_dataframe(
|
| 292 |
+
periods=periods,
|
| 293 |
+
freq=freq_map[freq_agrupacion][0] # Tomar primer carácter (D, W, M)
|
| 294 |
+
)
|
| 295 |
+
|
| 296 |
+
forecast = model.predict(future)
|
| 297 |
+
|
| 298 |
+
# Resultados
|
| 299 |
+
st.subheader("Predicción y Componentes")
|
| 300 |
+
fig1 = plot_plotly(model, forecast)
|
| 301 |
+
fig1.update_layout(
|
| 302 |
+
height=600,
|
| 303 |
+
hovermode="x unified",
|
| 304 |
+
xaxis_title="Fecha",
|
| 305 |
+
yaxis_title=target_col,
|
| 306 |
+
annotations=[
|
| 307 |
+
dict(
|
| 308 |
+
text=f"Frecuencia: {freq_agrupacion} | Agregación: {metodo_agregacion}",
|
| 309 |
+
xref="paper",
|
| 310 |
+
yref="paper",
|
| 311 |
+
x=0.5,
|
| 312 |
+
y=-0.15,
|
| 313 |
+
showarrow=False
|
| 314 |
+
)
|
| 315 |
+
]
|
| 316 |
+
)
|
| 317 |
+
st.plotly_chart(fig1, use_container_width=True)
|
| 318 |
+
|
| 319 |
+
st.subheader("Descomposición de Componentes")
|
| 320 |
+
fig2 = plot_components_plotly(model, forecast)
|
| 321 |
+
st.plotly_chart(fig2, use_container_width=True)
|
| 322 |
+
|
| 323 |
+
# Mostrar métricas de rendimiento
|
| 324 |
+
with st.expander("📈 Métricas de Rendimiento", expanded=True):
|
| 325 |
+
from sklearn.metrics import mean_absolute_error, mean_squared_error
|
| 326 |
+
|
| 327 |
+
merged = forecast.set_index('ds')[['yhat']].join(
|
| 328 |
+
prophet_df.set_index('ds')['y']
|
| 329 |
+
).dropna()
|
| 330 |
+
|
| 331 |
+
mae = mean_absolute_error(merged['y'], merged['yhat'])
|
| 332 |
+
rmse = np.sqrt(mean_squared_error(merged['y'], merged['yhat']))
|
| 333 |
+
|
| 334 |
+
col_met1, col_met2 = st.columns(2)
|
| 335 |
+
with col_met1:
|
| 336 |
+
st.metric("MAE (Error Absoluto Medio)", f"{mae:.2f}")
|
| 337 |
+
with col_met2:
|
| 338 |
+
st.metric("RMSE (Raíz del Error Cuadrático Medio)", f"{rmse:.2f}")
|
| 339 |
+
|
| 340 |
+
except Exception as e:
|
| 341 |
+
st.error(f"Error en el modelo: {str(e)}")
|
| 342 |
+
|
| 343 |
+
def main():
|
| 344 |
+
st.title("📈 Dashboard Analítico Interactivo")
|
| 345 |
+
|
| 346 |
+
# Crear pestañas
|
| 347 |
+
tab1, tab2, tab3 = st.tabs(["Carga de Datos", "Análisis Exploratorio", "Pronósticos"])
|
| 348 |
+
|
| 349 |
+
with tab1:
|
| 350 |
+
st.header("📤 Carga de Datos")
|
| 351 |
+
uploaded_file = st.file_uploader("Sube tu archivo (Excel o CSV)", type=["xlsx", "xls", "csv"])
|
| 352 |
+
|
| 353 |
+
if uploaded_file:
|
| 354 |
+
df = load_data(uploaded_file)
|
| 355 |
+
if df is not None:
|
| 356 |
+
st.success("Datos cargados exitosamente!")
|
| 357 |
+
|
| 358 |
+
# Mostrar información básica del archivo
|
| 359 |
+
file_details = {
|
| 360 |
+
"Nombre": uploaded_file.name,
|
| 361 |
+
"Tipo": uploaded_file.type,
|
| 362 |
+
"Tamaño": f"{uploaded_file.size / 1024:.2f} KB"
|
| 363 |
+
}
|
| 364 |
+
|
| 365 |
+
st.json(file_details)
|
| 366 |
+
# Nueva sección de análisis de fecha
|
| 367 |
+
if 'ds' not in st.session_state.df.columns:
|
| 368 |
+
st.warning("⚠️ No se detectó columna de fecha. Se creará una nueva columna 'ds'")
|
| 369 |
+
create_date_column(df)
|
| 370 |
+
|
| 371 |
+
st.dataframe(df.head(), use_container_width=True)
|
| 372 |
+
|
| 373 |
+
if 'df' in st.session_state:
|
| 374 |
+
|
| 375 |
+
with tab2:
|
| 376 |
+
st.header("🔍 Análisis Exploratorio")
|
| 377 |
+
perform_analysis(st.session_state.df)
|
| 378 |
+
|
| 379 |
+
# Selección de columna de fecha para análisis temporal
|
| 380 |
+
date_cols = st.session_state.df.select_dtypes(include=['datetime', 'datetimetz']).columns
|
| 381 |
+
if len(date_cols) > 0:
|
| 382 |
+
selected_date = st.selectbox("Seleccionar columna de fecha", date_cols)
|
| 383 |
+
time_analysis(st.session_state.df, selected_date)
|
| 384 |
+
else:
|
| 385 |
+
st.warning("No se detectaron columnas de fecha en los datos")
|
| 386 |
+
|
| 387 |
+
with tab3:
|
| 388 |
+
st.header("🔮 Pronósticos con Prophet")
|
| 389 |
+
if len(date_cols) > 0:
|
| 390 |
+
selected_date = st.selectbox("Seleccionar fecha para pronóstico", date_cols)
|
| 391 |
+
forecast_section(st.session_state.df, selected_date)
|
| 392 |
+
else:
|
| 393 |
+
st.error("Se requiere al menos una columna de fecha para pronósticos")
|
| 394 |
+
|
| 395 |
+
if __name__ == "__main__":
|
| 396 |
+
main()
|
requirements.txt
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# requirements.txt
|
| 2 |
+
streamlit>=1.22.0
|
| 3 |
+
pandas>=1.5.0
|
| 4 |
+
numpy>=1.24.0
|
| 5 |
+
plotly>=5.13.0
|
| 6 |
+
prophet>=1.1.3
|
| 7 |
+
xlrd>=2.0.1
|
| 8 |
+
openpyxl>=3.0.10
|
| 9 |
+
scikit-learn>=1.2.0
|
| 10 |
+
matplotlib>=3.7.0
|
| 11 |
+
tqdm>=4.65.0
|