Add application file

.gitignore

@@ -0,0 +1,2 @@
+venv
+secrets.toml    

filter.py

@@ -0,0 +1,83 @@
+import pandas as pd
+import streamlit as st
+from pandas.api.types import (
+    is_categorical_dtype,
+    is_datetime64_any_dtype,
+    is_numeric_dtype,
+    is_object_dtype,
+)
+
+def filter_dataframe(df: pd.DataFrame) -> pd.DataFrame:
+    df = df.copy()
+
+    # Tentar converter datas para um formato padrão (datetime, sem fuso horário)
+    for col in df.columns:
+        if is_object_dtype(df[col]):
+            try:
+                df[col] = pd.to_datetime(df[col])
+            except Exception:
+                pass
+
+        if is_datetime64_any_dtype(df[col]):
+            df[col] = df[col].dt.tz_localize(None)
+
+    modification_container = st.container()
+
+    with modification_container:
+        to_filter_columns = st.multiselect("Filtrar por valor", df.columns)
+        for column in to_filter_columns:
+            left, right = st.columns((1, 20))
+            left.write("↳")
+            # Tratar colunas com < 10 valores únicos como categóricos
+            if is_categorical_dtype(df[column]) or df[column].nunique() < 10:
+                user_cat_input = right.multiselect(
+                    f"Valores para {column}",
+                    df[column].unique(),
+                    default=[],  # Lista vazia para não ter valores pré-selecionados
+                )
+                if user_cat_input:  # Filtrar apenas se houver seleção
+                    df = df[df[column].isin(user_cat_input)]
+            elif is_numeric_dtype(df[column]):
+                _min = float(df[column].min())
+                _max = float(df[column].max())
+                step = (_max - _min) / 100
+                user_num_input = right.slider(
+                    f"Valores para {column}",
+                    min_value=_min,
+                    max_value=_max,
+                    value=(_min, _max),
+                    step=step,
+                )
+                df = df[df[column].between(*user_num_input)]
+            elif is_datetime64_any_dtype(df[column]):
+                user_date_input = right.date_input(
+                    f"Valores para {column}",
+                    value=(
+                        df[column].min(),
+                        df[column].max(),
+                    ),
+                    format="YYYY-MM-DD",
+                )
+                if len(user_date_input) == 2:
+                    user_date_input = tuple(map(pd.to_datetime, user_date_input))
+                    start_date, end_date = user_date_input
+                    df = df.loc[df[column].between(start_date, end_date)]
+            else:
+                # Para colunas de texto, mostre uma seleção múltipla se houver poucos valores únicos
+                unique_values = df[column].dropna().unique()
+                if len(unique_values) < 100:  # Ajuste o limite conforme necessário
+                    user_text_input = right.multiselect(
+                        f"Valores para {column}",
+                        unique_values,
+                        default=[],  # Lista vazia para não ter valores pré-selecionados
+                    )
+                    if user_text_input:  # Filtrar apenas se houver seleção
+                        df = df[df[column].isin(user_text_input)]
+                else:
+                    user_text_input = right.text_input(
+                        f"Substring ou regex em {column}",
+                    )
+                    if user_text_input:
+                        df = df[df[column].astype(str).str.contains(user_text_input, na=False)]
+
+    return df

query.sql

@@ -0,0 +1,67 @@
+SELECT 
+    COALESCE(NULLIF(data->'responseData'->0->>'name', '[null]'), '') AS "Nome documento",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->0->'response'->>'city', '[null]'), '') AS "Cidade",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->0->'response'->>'state', '[null]'), '') AS "Estado",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->0->'response'->>'region', '[null]'), '') AS "Região",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->0->'response'->>'country', '[null]'), '') AS "País",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->0->'response'->>'extra_info', '[null]'), '') AS "Informações adicionais",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->0->'response'->>'target_or_deposit', '[null]'), '') AS "Alvo ou depósito",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->0->'response'->'geological_context'->>'tectonic_context', '[null]'), '') AS "Contexto tectônico",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->0->'response'->'geological_context'->>'geological_context', '[null]'), '') AS "Contexto geológico",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->0->'response'->'geological_context'->>'context_of_present_rocks', '[null]'), '') AS "Contexto das rochas presentes",
+    
+    COALESCE(NULLIF(data->'responseData'->0->'data'->1->'response'->'rockTypes'->'sedimentares'->0->>'name', '[null]'), '') AS "Nome sedimentares",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->1->'response'->'rockTypes'->'sedimentares'->0->>'type', '[null]'), '') AS "Tipo sedimentares",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->1->'response'->'rockTypes'->'sedimentares'->0->>'scientificName', '[null]'), '') AS "Nome científico sedimentares",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->1->'response'->'rockTypes'->'sedimentares'->0->>'contact_relations', '[null]'), '') AS "Relações de contato sedimentares",
+
+    COALESCE(NULLIF(data->'responseData'->0->'data'->1->'response'->'rockTypes'->'metamórficas'->0->>'name', '[null]'), '') AS "Nome metamórficas",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->1->'response'->'rockTypes'->'metamórficas'->0->>'type', '[null]'), '') AS "Tipo metamórficas",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->1->'response'->'rockTypes'->'metamórficas'->0->>'scientificName', '[null]'), '') AS "Nome científico metamórficas",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->1->'response'->'rockTypes'->'metamórficas'->0->>'contact_relations', '[null]'), '') AS "Relações de contato metamórficas",
+
+    COALESCE(NULLIF(data->'responseData'->0->'data'->1->'response'->'rockTypes'->'ígneas_intrusivas'->0->>'name', '[null]'), '') AS "Nome ígneas intrusivas",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->1->'response'->'rockTypes'->'ígneas_intrusivas'->0->>'type', '[null]'), '') AS "Tipo ígneas intrusivas",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->1->'response'->'rockTypes'->'ígneas_intrusivas'->0->>'scientificName', '[null]'), '') AS "Nome científico ígneas intrusivas",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->1->'response'->'rockTypes'->'ígneas_intrusivas'->0->>'contact_relations', '[null]'), '') AS "Relações de contato ígneas intrusivas",
+
+    COALESCE(NULLIF(data->'responseData'->0->'data'->1->'response'->'rockTypes'->'vulcânicas_e_subvulcânicas'->0->>'name', '[null]'), '') AS "Nome vulcânicas e subvulcânicas",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->1->'response'->'rockTypes'->'vulcânicas_e_subvulcânicas'->0->>'type', '[null]'), '') AS "Tipo vulcânicas e subvulcânicas",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->1->'response'->'rockTypes'->'vulcânicas_e_subvulcânicas'->0->>'scientificName', '[null]'), '') AS "Nome científico vulcânicas e subvulcânicas",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->1->'response'->'rockTypes'->'vulcânicas_e_subvulcânicas'->0->>'contact_relations', '[null]'), '') AS "Relações de contato vulcânicas e subvulcânicas",
+   
+    COALESCE(NULLIF(data->'responseData'->0->'data'->2->'response'->>'oreType', '[null]'), '') AS "Tipo de minério",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->2->'response'->>'rockType', '[null]'), '') AS "Tipo de rocha",
+	
+    COALESCE(NULLIF((data->'responseData'->0->'data'->2->'response'->'host_rocks'->>'name')::text, '[null]'), '') AS "Nomes rochas hospedeiras",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->2->'response'->'host_rocks'->>'geologicalEnvironments', '[null]'), '') AS "Eventos geológicos rochas hospedeiras",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->2->'response'->'host_rocks'->>'mineralizationStructures', '[null]'), '') AS "Estruturas de mineralização de rochas hospedeiras",
+
+    COALESCE(NULLIF(data->'responseData'->0->'data'->2->'response'->>'structures', '[null]'), '') AS "Estruturas",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->2->'response'->>'mineralFabric', '[null]'), '') AS "Textura mineral",
+	
+    COALESCE(NULLIF(data->'responseData'->0->'data'->2->'response'->>'definedEstimate', '[null]'), '') AS "Estimativa definida",
+	
+    COALESCE(NULLIF(data->'responseData'->0->'data'->2->'response'->>'associatedMinerals', '[null]'), '') AS "Minerais associados",
+	
+    COALESCE(NULLIF(data->'responseData'->0->'data'->2->'response'->>'estimatedQuantities', '[null]'), '') AS "Quantidades estimadas",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->2->'response'->>'definedConcentration', '[null]'), '') AS "Concentração definida",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->2->'response'->>'estimatedConcentration', '[null]'), '') AS "Concentração estimada",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->2->'response'->>'fluidInclusionsAnalysis', '[null]'), '') AS "Análise de inclusões fluidas",
+	
+    COALESCE(NULLIF(data->'responseData'->0->'data'->2->'response'->'hydrotermal_alterations'->>'alterationTypes', '[null]'), '') AS "Tipos de alterações hidrotermais",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->2->'response'->'hydrotermal_alterations'->>'associatedMinerals', '[null]'), '') AS "Minerais associados a alterações hidrotermais",
+	
+    COALESCE(NULLIF(data->'responseData'->0->'data'->2->'response'->>'mineralizationSignatures', '[null]'), '') AS "Assinaturas de mineralização",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->3->'response'->>'structural_mapping', '[null]'), '') AS "Mapeamento estrutural",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->4->'response'->>'structureMineralizationRelation', '[null]'), '') AS "Relação estrutura-mineralização",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->5->'response'->>'stableIsotopes', '[null]'), '') AS "Isótopos estáveis",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->5->'response'->>'traceElementsAndRareEarths', '[null]'), '') AS "Elementos traço e terras raras",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->6->'response'->>'geophysicalSignatures', '[null]'), '') AS "Assinaturas geofísicas",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->6->'response'->>'mineralizationSignatures', '[null]'), '') AS "Assinaturas de mineralização geofísica",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->7->'response'->>'additionalInformation', '[null]'), '') AS "Informações adicionais de mineralização",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->8->'response'->>'estimates', '[null]'), '') AS "Estimativas de minério",
+    COALESCE(NULLIF(data->'responseData'->0->'data'->9->'response'->>'potential', '[null]'), '') AS "Potencial de descoberta"
+FROM 
+    public."Extraction";
+

requirements.txt

@@ -0,0 +1,4 @@
+pandas==2.2.2
+SQLAlchemy==2.0.31
+streamlit
+toml==0.10.2