updates

main.py

@@ -2,27 +2,46 @@ from data import create_data
 from sklearn.model_selection import train_test_split
 from prerequisite_issues import identify_prerequisite_issues
 from output import gerar_csv
+import streamlit as st
+import pandas as pd
 
 def main():
+    st.title("Sistema de Identificação de Dificuldades Acadêmicas (SIDA)")
+    
     # Criando o DataFrame
     df, pre_reqs = create_data()
 
     # Identificando os pré-requisitos que os alunos precisam melhorar
     recommendations, metrics_summary = identify_prerequisite_issues(df, pre_reqs)
 
-    # Avaliar modelos
-    # metrics = evaluate_models(df)
-
     # Exibir os resultados
-    print("Recomendações:", recommendations)
-    print("\nResumo das Métricas:", metrics_summary)
+    st.subheader("Recomendações por Aluno")
+    for aluno, recs in recommendations.items():
+        st.write(f"**{aluno}:**")
+        for prereq, importance in recs[:3]:  # Mostrar apenas os 3 mais importantes
+            st.write(f"- {prereq}: {importance:.3f}")
+
+    st.subheader("Resumo das Métricas dos Modelos")
+    for subject, metrics in metrics_summary.items():
+        st.write(f"**{subject}:**")
+        for model_name, model_metrics in metrics.items():
+            st.write(f"- {model_name}: R² = {model_metrics['R²']:.3f}, MAE = {model_metrics['MAE']:.3f}")
 
-    # # Criando um arquivo csv com os resultados
-    # gerar_csv(df, 'output.csv')
-    
     # Exporta o DataFrame para um arquivo CSV 
     df.to_csv('output1.csv', index=False, encoding='utf-8')
-    print("Arquivo CSV 'output.csv' criado com sucesso.")
+    st.success("Arquivo CSV 'output1.csv' criado com sucesso.")
+
+    # Visualizações
+    st.subheader("Visualizações dos Dados")
+    
+    # Gráfico de barras das notas médias por disciplina
+    st.write("**Notas Médias por Disciplina:**")
+    mean_scores = df.drop('Aluno', axis=1).mean()
+    st.bar_chart(mean_scores)
+    
+    # Tabela com os dados
+    st.subheader("Dados dos Alunos")
+    st.dataframe(df)
 
 if __name__ == "__main__":
     main()

output1.csv

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c9af9042e581cbfd587242f7c243e991dbba1f26b878e3266e12374d3593590
-size 2157
+oid sha256:149b12b3bd66b5ee26142e681b660fbfbe1804f98bf53a1f2d669aeb940f831d
+size 2158

requirements.txt

@@ -6,7 +6,9 @@ python-dateutil==2.9.0.post0
 pytz==2025.2
 scikit-learn==1.6.1
 scipy==1.13.1
--e git+https://github.com/emanoelopes/sida.git@af9ff30657a57ab50f46e5162d6cbb05cb2b8173#egg=SIDA
+streamlit==1.39.0
+pygwalker==0.3.6
+#-e git+https://github.com/emanoelopes/sida.git@af9ff30657a57ab50f46e5162d6cbb05cb2b8173#egg=SIDA
 six==1.17.0
 threadpoolctl==3.6.0
 tzdata==2025.2

web.ipynb

@@ -0,0 +1,102 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9e33bf6a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import pygwalker as pyg\n",
+    "import streamlit as st\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b9e80420",
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "KeyError",
+     "evalue": "'Nota'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
+      "File \u001b[0;32m~/sida/.venv/lib/python3.9/site-packages/pandas/core/indexes/base.py:3812\u001b[0m, in \u001b[0;36mIndex.get_loc\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m   3811\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 3812\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_engine\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_loc\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcasted_key\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   3813\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m err:\n",
+      "File \u001b[0;32mpandas/_libs/index.pyx:167\u001b[0m, in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
+      "File \u001b[0;32mpandas/_libs/index.pyx:196\u001b[0m, in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
+      "File \u001b[0;32mpandas/_libs/hashtable_class_helper.pxi:7088\u001b[0m, in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
+      "File \u001b[0;32mpandas/_libs/hashtable_class_helper.pxi:7096\u001b[0m, in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
+      "\u001b[0;31mKeyError\u001b[0m: 'Nota'",
+      "\nThe above exception was the direct cause of the following exception:\n",
+      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[20], line 3\u001b[0m\n\u001b[1;32m      1\u001b[0m df \u001b[38;5;241m=\u001b[39m pd\u001b[38;5;241m.\u001b[39mread_csv(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124moutput1.csv\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m      2\u001b[0m df\u001b[38;5;241m.\u001b[39mset_index(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mAluno\u001b[39m\u001b[38;5;124m'\u001b[39m, inplace\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[0;32m----> 3\u001b[0m st\u001b[38;5;241m.\u001b[39mline_chart(\u001b[43mdf\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mNota\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m]\u001b[49m)\n",
+      "File \u001b[0;32m~/sida/.venv/lib/python3.9/site-packages/pandas/core/frame.py:4107\u001b[0m, in \u001b[0;36mDataFrame.__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m   4105\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcolumns\u001b[38;5;241m.\u001b[39mnlevels \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m   4106\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_getitem_multilevel(key)\n\u001b[0;32m-> 4107\u001b[0m indexer \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcolumns\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_loc\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkey\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   4108\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m is_integer(indexer):\n\u001b[1;32m   4109\u001b[0m     indexer \u001b[38;5;241m=\u001b[39m [indexer]\n",
+      "File \u001b[0;32m~/sida/.venv/lib/python3.9/site-packages/pandas/core/indexes/base.py:3819\u001b[0m, in \u001b[0;36mIndex.get_loc\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m   3814\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(casted_key, \u001b[38;5;28mslice\u001b[39m) \u001b[38;5;129;01mor\u001b[39;00m (\n\u001b[1;32m   3815\u001b[0m         \u001b[38;5;28misinstance\u001b[39m(casted_key, abc\u001b[38;5;241m.\u001b[39mIterable)\n\u001b[1;32m   3816\u001b[0m         \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28many\u001b[39m(\u001b[38;5;28misinstance\u001b[39m(x, \u001b[38;5;28mslice\u001b[39m) \u001b[38;5;28;01mfor\u001b[39;00m x \u001b[38;5;129;01min\u001b[39;00m casted_key)\n\u001b[1;32m   3817\u001b[0m     ):\n\u001b[1;32m   3818\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m InvalidIndexError(key)\n\u001b[0;32m-> 3819\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m(key) \u001b[38;5;28;01mfrom\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01merr\u001b[39;00m\n\u001b[1;32m   3820\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m:\n\u001b[1;32m   3821\u001b[0m     \u001b[38;5;66;03m# If we have a listlike key, _check_indexing_error will raise\u001b[39;00m\n\u001b[1;32m   3822\u001b[0m     \u001b[38;5;66;03m#  InvalidIndexError. Otherwise we fall through and re-raise\u001b[39;00m\n\u001b[1;32m   3823\u001b[0m     \u001b[38;5;66;03m#  the TypeError.\u001b[39;00m\n\u001b[1;32m   3824\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_check_indexing_error(key)\n",
+      "\u001b[0;31mKeyError\u001b[0m: 'Nota'"
+     ]
+    }
+   ],
+   "source": [
+    "# Carregar os dados\n",
+    "df = pd.read_csv('output1.csv')\n",
+    "\n",
+    "# Verificar a estrutura dos dados\n",
+    "print(\"Colunas disponíveis:\", df.columns.tolist())\n",
+    "print(\"Primeiras linhas:\")\n",
+    "print(df.head())\n",
+    "\n",
+    "# Configurar o índice para o nome do aluno\n",
+    "df.set_index('Aluno', inplace=True)\n",
+    "\n",
+    "# Mostrar estatísticas básicas\n",
+    "print(\"\\nEstatísticas descritivas:\")\n",
+    "print(df.describe())\n",
+    "\n",
+    "# Criar visualizações com Streamlit\n",
+    "st.title(\"Análise de Dados Acadêmicos - SIDA\")\n",
+    "\n",
+    "# Gráfico de linha para uma disciplina específica (ex: Números Inteiros)\n",
+    "if 'Números Inteiros' in df.columns:\n",
+    "    st.subheader(\"Notas em Números Inteiros\")\n",
+    "    st.line_chart(df['Números Inteiros'])\n",
+    "else:\n",
+    "    st.write(\"Coluna 'Números Inteiros' não encontrada. Colunas disponíveis:\", df.columns.tolist())\n",
+    "\n",
+    "# Gráfico de barras com as médias por disciplina\n",
+    "st.subheader(\"Médias por Disciplina\")\n",
+    "mean_scores = df.mean()\n",
+    "st.bar_chart(mean_scores)\n",
+    "\n",
+    "# Tabela interativa com PygWalker\n",
+    "st.subheader(\"Exploração Interativa dos Dados\")\n",
+    "pyg.walk(df, spec=\"./gw0.json\", use_kernel_calc=True, kernel_computation=True, debug=False)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}