iints-sdk-python35 0.0.18__py3-none-any.whl

iints/data/demo/demo_cgm.csv

@@ -0,0 +1,289 @@
+timestamp,glucose,carbs,insulin
+0,115.0,0.0,0.0
+5,115.2,0.0,0.0
+10,115.3,0.0,0.0
+15,115.5,0.0,0.0
+20,115.7,0.0,0.0
+25,115.9,0.0,0.0
+30,116.0,0.0,0.0
+35,116.2,0.0,0.0
+40,116.4,0.0,0.0
+45,116.6,0.0,0.0
+50,116.7,0.0,0.0
+55,116.9,0.0,0.0
+60,144.1,45.0,0.0
+65,143.5,0.0,0.0
+70,142.9,0.0,0.0
+75,142.4,0.0,0.0
+80,141.9,0.0,0.0
+85,141.4,0.0,0.0
+90,140.9,0.0,0.0
+95,140.5,0.0,0.0
+100,140.0,0.0,0.0
+105,139.6,0.0,0.0
+110,139.1,0.0,0.0
+115,138.7,0.0,0.0
+120,138.3,0.0,0.0
+125,138.0,0.0,0.0
+130,137.6,0.0,0.0
+135,137.2,0.0,0.0
+140,136.9,0.0,0.0
+145,136.6,0.0,0.0
+150,136.2,0.0,0.0
+155,135.9,0.0,0.0
+160,135.6,0.0,0.0
+165,135.3,0.0,0.0
+170,135.1,0.0,0.0
+175,134.8,0.0,0.0
+180,134.5,0.0,0.0
+185,134.3,0.0,0.0
+190,134.0,0.0,0.0
+195,133.8,0.0,0.0
+200,133.5,0.0,0.0
+205,133.3,0.0,0.0
+210,133.1,0.0,0.0
+215,132.9,0.0,0.0
+220,132.7,0.0,0.0
+225,132.4,0.0,0.0
+230,132.2,0.0,0.0
+235,132.1,0.0,0.0
+240,131.9,0.0,0.0
+245,131.7,0.0,0.0
+250,131.5,0.0,0.0
+255,131.3,0.0,0.0
+260,131.1,0.0,0.0
+265,131.0,0.0,0.0
+270,130.8,0.0,0.0
+275,130.6,0.0,0.0
+280,130.5,0.0,0.0
+285,130.3,0.0,0.0
+290,130.2,0.0,0.0
+295,130.0,0.0,0.0
+300,129.8,0.0,0.0
+305,129.7,0.0,0.0
+310,129.5,0.0,0.0
+315,129.4,0.0,0.0
+320,129.2,0.0,0.0
+325,129.1,0.0,0.0
+330,129.0,0.0,0.0
+335,128.8,0.0,0.0
+340,128.7,0.0,0.0
+345,128.5,0.0,0.0
+350,128.4,0.0,0.0
+355,128.2,0.0,0.0
+360,164.1,60.0,0.0
+365,163.0,0.0,0.0
+370,161.9,0.0,0.0
+375,160.8,0.0,0.0
+380,159.7,0.0,0.0
+385,158.7,0.0,0.0
+390,157.7,0.0,0.0
+395,156.7,0.0,0.0
+400,155.8,0.0,0.0
+405,154.9,0.0,0.0
+410,153.9,0.0,0.0
+415,153.0,0.0,0.0
+420,152.2,0.0,0.0
+425,151.3,0.0,0.0
+430,150.5,0.0,0.0
+435,149.7,0.0,0.0
+440,148.9,0.0,0.0
+445,148.1,0.0,0.0
+450,147.3,0.0,0.0
+455,146.6,0.0,0.0
+460,145.8,0.0,0.0
+465,145.1,0.0,0.0
+470,144.4,0.0,0.0
+475,143.7,0.0,0.0
+480,143.0,0.0,0.0
+485,142.4,0.0,0.0
+490,141.7,0.0,0.0
+495,141.1,0.0,0.0
+500,140.4,0.0,0.0
+505,139.8,0.0,0.0
+510,139.2,0.0,0.0
+515,138.6,0.0,0.0
+520,138.0,0.0,0.0
+525,137.4,0.0,0.0
+530,136.9,0.0,0.0
+535,136.3,0.0,0.0
+540,135.8,0.0,0.0
+545,135.2,0.0,0.0
+550,134.7,0.0,0.0
+555,134.2,0.0,0.0
+560,133.7,0.0,0.0
+565,133.2,0.0,0.0
+570,132.7,0.0,0.0
+575,132.2,0.0,0.0
+580,131.7,0.0,0.0
+585,131.2,0.0,0.0
+590,130.8,0.0,0.0
+595,130.3,0.0,0.0
+600,129.8,0.0,0.0
+605,129.4,0.0,0.0
+610,128.9,0.0,0.0
+615,128.5,0.0,0.0
+620,128.1,0.0,0.0
+625,127.7,0.0,0.0
+630,127.2,0.0,0.0
+635,126.8,0.0,0.0
+640,126.4,0.0,0.0
+645,126.0,0.0,0.0
+650,125.6,0.0,0.0
+655,125.2,0.0,0.0
+660,124.8,0.0,0.0
+665,124.5,0.0,0.0
+670,124.1,0.0,0.0
+675,123.7,0.0,0.0
+680,123.3,0.0,0.0
+685,123.0,0.0,0.0
+690,122.6,0.0,0.0
+695,122.3,0.0,0.0
+700,121.9,0.0,0.0
+705,121.6,0.0,0.0
+710,121.2,0.0,0.0
+715,120.9,0.0,0.0
+720,162.6,70.0,0.0
+725,161.1,0.0,0.0
+730,159.6,0.0,0.0
+735,158.2,0.0,0.0
+740,156.9,0.0,0.0
+745,155.5,0.0,0.0
+750,154.2,0.0,0.0
+755,152.9,0.0,0.0
+760,151.7,0.0,0.0
+765,150.5,0.0,0.0
+770,149.3,0.0,0.0
+775,148.1,0.0,0.0
+780,147.0,0.0,0.0
+785,145.9,0.0,0.0
+790,144.8,0.0,0.0
+795,143.8,0.0,0.0
+800,142.8,0.0,0.0
+805,141.8,0.0,0.0
+810,140.8,0.0,0.0
+815,139.8,0.0,0.0
+820,138.9,0.0,0.0
+825,138.0,0.0,0.0
+830,137.1,0.0,0.0
+835,136.3,0.0,0.0
+840,135.4,0.0,0.0
+845,134.6,0.0,0.0
+850,133.8,0.0,0.0
+855,133.0,0.0,0.0
+860,132.3,0.0,0.0
+865,131.5,0.0,0.0
+870,130.8,0.0,0.0
+875,130.1,0.0,0.0
+880,129.4,0.0,0.0
+885,128.7,0.0,0.0
+890,128.1,0.0,0.0
+895,127.5,0.0,0.0
+900,126.8,0.0,0.0
+905,126.2,0.0,0.0
+910,125.7,0.0,0.0
+915,125.1,0.0,0.0
+920,124.5,0.0,0.0
+925,124.0,0.0,0.0
+930,123.5,0.0,0.0
+935,123.0,0.0,0.0
+940,122.5,0.0,0.0
+945,122.0,0.0,0.0
+950,121.5,0.0,0.0
+955,121.1,0.0,0.0
+960,120.6,0.0,0.0
+965,120.2,0.0,0.0
+970,119.8,0.0,0.0
+975,119.4,0.0,0.0
+980,119.0,0.0,0.0
+985,118.6,0.0,0.0
+990,118.2,0.0,0.0
+995,117.9,0.0,0.0
+1000,117.5,0.0,0.0
+1005,117.2,0.0,0.0
+1010,116.9,0.0,0.0
+1015,116.6,0.0,0.0
+1020,116.3,0.0,0.0
+1025,116.0,0.0,0.0
+1030,115.7,0.0,0.0
+1035,115.4,0.0,0.0
+1040,115.2,0.0,0.0
+1045,114.9,0.0,0.0
+1050,114.7,0.0,0.0
+1055,114.4,0.0,0.0
+1060,114.2,0.0,0.0
+1065,114.0,0.0,0.0
+1070,113.8,0.0,0.0
+1075,113.6,0.0,0.0
+1080,113.4,0.0,0.0
+1085,113.3,0.0,0.0
+1090,113.1,0.0,0.0
+1095,112.9,0.0,0.0
+1100,112.8,0.0,0.0
+1105,112.6,0.0,0.0
+1110,112.5,0.0,0.0
+1115,112.4,0.0,0.0
+1120,112.3,0.0,0.0
+1125,112.2,0.0,0.0
+1130,112.1,0.0,0.0
+1135,112.0,0.0,0.0
+1140,111.9,0.0,0.0
+1145,111.8,0.0,0.0
+1150,111.7,0.0,0.0
+1155,111.7,0.0,0.0
+1160,111.6,0.0,0.0
+1165,111.6,0.0,0.0
+1170,111.5,0.0,0.0
+1175,111.5,0.0,0.0
+1180,111.4,0.0,0.0
+1185,111.4,0.0,0.0
+1190,111.4,0.0,0.0
+1195,111.4,0.0,0.0
+1200,96.4,0.0,0.0
+1205,96.4,0.0,0.0
+1210,96.4,0.0,0.0
+1215,96.4,0.0,0.0
+1220,96.4,0.0,0.0
+1225,96.4,0.0,0.0
+1230,96.5,0.0,0.0
+1235,96.5,0.0,0.0
+1240,96.5,0.0,0.0
+1245,96.6,0.0,0.0
+1250,96.6,0.0,0.0
+1255,96.7,0.0,0.0
+1260,96.7,0.0,0.0
+1265,96.8,0.0,0.0
+1270,96.8,0.0,0.0
+1275,96.9,0.0,0.0
+1280,97.0,0.0,0.0
+1285,97.1,0.0,0.0
+1290,97.1,0.0,0.0
+1295,97.2,0.0,0.0
+1300,97.3,0.0,0.0
+1305,97.4,0.0,0.0
+1310,97.5,0.0,0.0
+1315,97.6,0.0,0.0
+1320,97.7,0.0,0.0
+1325,112.8,0.0,0.0
+1330,112.9,0.0,0.0
+1335,113.0,0.0,0.0
+1340,113.1,0.0,0.0
+1345,113.3,0.0,0.0
+1350,113.4,0.0,0.0
+1355,113.5,0.0,0.0
+1360,113.6,0.0,0.0
+1365,113.7,0.0,0.0
+1370,113.9,0.0,0.0
+1375,114.0,0.0,0.0
+1380,114.1,0.0,0.0
+1385,114.3,0.0,0.0
+1390,114.4,0.0,0.0
+1395,114.6,0.0,0.0
+1400,114.7,0.0,0.0
+1405,114.8,0.0,0.0
+1410,115.0,0.0,0.0
+1415,115.1,0.0,0.0
+1420,115.3,0.0,0.0
+1425,115.4,0.0,0.0
+1430,115.6,0.0,0.0
+1435,115.7,0.0,0.0

iints/data/importer.py

@@ -0,0 +1,275 @@
+from __future__ import annotations
+
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Any, Dict, Iterable, List, Optional, Tuple, Union
+import io
+import re
+import sys
+
+import pandas as pd
+
+from iints.data.ingestor import DataIngestor
+
+
+def _normalize_column(name: str) -> str:
+    return re.sub(r"[^a-z0-9]+", "", name.lower())
+
+
+def _find_column(columns: Iterable[str], candidates: Iterable[str]) -> Optional[str]:
+    normalized = {col: _normalize_column(col) for col in columns}
+    candidate_set = {_normalize_column(c) for c in candidates}
+    for col, norm in normalized.items():
+        if norm in candidate_set:
+            return col
+    return None
+
+
+DEFAULT_MAPPINGS: Dict[str, Dict[str, List[str]]] = {
+    "generic": {
+        "timestamp": ["timestamp", "time", "datetime", "date", "eventtime", "device timestamp"],
+        "glucose": ["glucose", "bg", "sgv", "sensorglucose", "glucosemgdl", "glucosevalue"],
+        "carbs": ["carbs", "carb", "carbohydrates", "carbsg", "carbgrams"],
+        "insulin": ["insulin", "insulinunits", "bolus", "basal", "totalinsulin"],
+    },
+    "dexcom": {
+        "timestamp": ["timestamp", "eventtime", "device timestamp"],
+        "glucose": ["glucose", "glucosevalue", "sgv", "sensorglucose"],
+        "carbs": ["carbs", "carb", "carbohydrates"],
+        "insulin": ["insulin", "insulinunits", "bolus", "basal"],
+    },
+    "libre": {
+        "timestamp": ["timestamp", "device timestamp", "datetime", "time"],
+        "glucose": ["glucose", "glucosevalue", "sensorglucose", "sgv"],
+        "carbs": ["carbs", "carb", "carbohydrates"],
+        "insulin": ["insulin", "insulinunits", "bolus", "basal"],
+    },
+}
+
+IMPORT_FORMAT_SCHEMAS: Dict[str, Dict[str, List[str]]] = {
+    "generic": {
+        "required": ["timestamp", "glucose"],
+        "optional": ["carbs", "insulin"],
+    },
+    "dexcom": {
+        "required": ["timestamp", "glucose"],
+        "optional": ["carbs", "insulin"],
+    },
+    "libre": {
+        "required": ["timestamp", "glucose"],
+        "optional": ["carbs", "insulin"],
+    },
+}
+
+
+@dataclass
+class ImportResult:
+    dataframe: pd.DataFrame
+    scenario: Dict[str, Any]
+
+
+def guess_column_mapping(columns: Iterable[str], data_format: str = "generic") -> Dict[str, Optional[str]]:
+    candidates = DEFAULT_MAPPINGS.get(data_format, DEFAULT_MAPPINGS["generic"])
+    return {
+        "timestamp": _find_column(columns, candidates.get("timestamp", [])),
+        "glucose": _find_column(columns, candidates.get("glucose", [])),
+        "carbs": _find_column(columns, candidates.get("carbs", [])),
+        "insulin": _find_column(columns, candidates.get("insulin", [])),
+    }
+
+
+def validate_import_schema(
+    columns: Iterable[str],
+    data_format: str,
+    column_map: Optional[Dict[str, str]] = None,
+) -> None:
+    schema = IMPORT_FORMAT_SCHEMAS.get(data_format, IMPORT_FORMAT_SCHEMAS["generic"])
+    candidates = DEFAULT_MAPPINGS.get(data_format, DEFAULT_MAPPINGS["generic"])
+    mapping = column_map or {}
+
+    missing: List[str] = []
+    for key in schema["required"]:
+        if key in mapping:
+            continue
+        found = _find_column(columns, candidates.get(key, []))
+        if found is None:
+            missing.append(key)
+
+    if missing:
+        raise ValueError(
+            f"Missing required columns for format '{data_format}': {', '.join(missing)}. "
+            f"Columns: {list(columns)}"
+        )
+
+
+def import_cgm_dataframe(
+    df: pd.DataFrame,
+    data_format: str = "generic",
+    column_map: Optional[Dict[str, str]] = None,
+    time_unit: str = "minutes",
+    source: Optional[str] = None,
+) -> pd.DataFrame:
+    """
+    Import CGM data from an in-memory DataFrame into the universal IINTS schema.
+    """
+    columns = list(df.columns)
+    mapping = column_map or {}
+    mapping = {k: v for k, v in mapping.items() if v}
+
+    candidates = DEFAULT_MAPPINGS.get(data_format, DEFAULT_MAPPINGS["generic"])
+
+    validate_import_schema(columns, data_format=data_format, column_map=mapping)
+
+    def resolve(key: str, required: bool = True) -> Optional[str]:
+        if key in mapping:
+            return mapping[key]
+        col = _find_column(columns, candidates.get(key, []))
+        if required and col is None:
+            raise ValueError(f"Missing required column for '{key}'. Columns: {columns}")
+        return col
+
+    ts_col = resolve("timestamp", required=True)
+    glucose_col = resolve("glucose", required=True)
+    carbs_col = resolve("carbs", required=False)
+    insulin_col = resolve("insulin", required=False)
+
+    df = df.rename(
+        columns={
+            ts_col: "timestamp",
+            glucose_col: "glucose",
+            carbs_col: "carbs",
+            insulin_col: "insulin",
+        }
+    )
+
+    if "carbs" not in df.columns:
+        df["carbs"] = 0.0
+    if "insulin" not in df.columns:
+        df["insulin"] = 0.0
+
+    # Parse timestamps
+    if pd.api.types.is_numeric_dtype(df["timestamp"]):
+        # Assume numeric (minutes or seconds)
+        if time_unit == "seconds":
+            df["timestamp"] = df["timestamp"].astype(float) / 60.0
+        else:
+            df["timestamp"] = df["timestamp"].astype(float)
+    elif pd.api.types.is_datetime64_any_dtype(df["timestamp"]):
+        ts = df["timestamp"]
+        df["timestamp"] = (ts - ts.iloc[0]).dt.total_seconds() / 60.0
+    else:
+        # Try datetime parsing, fallback to numeric
+        ts = pd.to_datetime(df["timestamp"], errors="coerce")
+        if ts.isna().all():
+            if time_unit == "seconds":
+                df["timestamp"] = df["timestamp"].astype(float) / 60.0
+            else:
+                df["timestamp"] = df["timestamp"].astype(float)
+        else:
+            df["timestamp"] = (ts - ts.iloc[0]).dt.total_seconds() / 60.0
+
+    df["source"] = source or data_format
+    ingestor = DataIngestor()
+    ingestor._validate_schema(df, ingestor.UNIVERSAL_SCHEMA)
+    return df[list(ingestor.UNIVERSAL_SCHEMA.keys())]
+
+
+def import_cgm_csv(
+    path: Union[str, Path],
+    data_format: str = "generic",
+    column_map: Optional[Dict[str, str]] = None,
+    time_unit: str = "minutes",
+    source: Optional[str] = None,
+) -> pd.DataFrame:
+    """
+    Import CGM data from CSV into the universal IINTS schema.
+    """
+    df = pd.read_csv(path)
+    return import_cgm_dataframe(
+        df,
+        data_format=data_format,
+        column_map=column_map,
+        time_unit=time_unit,
+        source=source,
+    )
+
+
+def scenario_from_dataframe(
+    df: pd.DataFrame,
+    scenario_name: str,
+    scenario_version: str = "1.0",
+    description: str = "Imported CGM scenario",
+    carb_threshold: float = 0.1,
+    absorption_delay_minutes: int = 10,
+    duration_minutes: int = 60,
+) -> Dict[str, Any]:
+    stress_events = []
+    if "carbs" in df.columns:
+        for _, row in df[df["carbs"] > carb_threshold].iterrows():
+            stress_events.append(
+                {
+                    "start_time": int(row["timestamp"]),
+                    "event_type": "meal",
+                    "value": float(row["carbs"]),
+                    "absorption_delay_minutes": absorption_delay_minutes,
+                    "duration": duration_minutes,
+                }
+            )
+
+    return {
+        "scenario_name": scenario_name,
+        "scenario_version": scenario_version,
+        "description": description,
+        "stress_events": stress_events,
+    }
+
+
+def scenario_from_csv(
+    path: Union[str, Path],
+    scenario_name: str = "Imported CGM Scenario",
+    scenario_version: str = "1.0",
+    data_format: str = "generic",
+    column_map: Optional[Dict[str, str]] = None,
+    time_unit: str = "minutes",
+    carb_threshold: float = 0.1,
+) -> ImportResult:
+    df = import_cgm_csv(
+        path,
+        data_format=data_format,
+        column_map=column_map,
+        time_unit=time_unit,
+    )
+    scenario = scenario_from_dataframe(
+        df,
+        scenario_name=scenario_name,
+        scenario_version=scenario_version,
+        carb_threshold=carb_threshold,
+    )
+    return ImportResult(dataframe=df, scenario=scenario)
+
+
+def export_standard_csv(df: pd.DataFrame, output_path: Union[str, Path]) -> str:
+    output_path = Path(output_path)
+    output_path.parent.mkdir(parents=True, exist_ok=True)
+    df.to_csv(output_path, index=False)
+    return str(output_path)
+
+
+def _read_demo_csv_text() -> str:
+    if sys.version_info >= (3, 9):
+        from importlib.resources import files
+        return files("iints.data.demo").joinpath("demo_cgm.csv").read_text()
+    from importlib import resources
+    return resources.read_text("iints.data.demo", "demo_cgm.csv")
+
+
+def load_demo_dataframe() -> pd.DataFrame:
+    text = _read_demo_csv_text()
+    return pd.read_csv(io.StringIO(text))
+
+
+def export_demo_csv(output_path: Union[str, Path]) -> str:
+    output_path = Path(output_path)
+    output_path.parent.mkdir(parents=True, exist_ok=True)
+    output_path.write_text(_read_demo_csv_text())
+    return str(output_path)