Create zebris_extractor.py

zebris_extractor.py

@@ -0,0 +1,132 @@
+import io
+import numpy as np
+import pandas as pd
+
+
+STANDARD_COLUMNS = [
+    "Nom",
+    "Date",
+    "Poids (kg)",
+    "Vitesse (km/h)",
+    "Cadence (pas/min)",
+    "Contact (%)",
+    "Flight (%)",
+    "Force talon G (N)",
+    "Force talon D (N)",
+    "Force avant-pied G (N)",
+    "Force avant-pied D (N)",
+    "Pression talon G (N/cm²)",
+    "Pression talon D (N/cm²)",
+    "COP G (mm)",
+    "COP D (mm)",
+    "Rotation G (°)",
+    "Rotation D (°)",
+    "Transition G (s)",
+    "Transition D (s)",
+    "Longueur foulée (cm)",
+    "Largeur pas (cm)",
+]
+
+
+def _to_numeric(series):
+    return pd.to_numeric(
+        series.astype(str).str.replace(",", ".", regex=False),
+        errors="coerce"
+    )
+
+
+def _read_csv_flex(uploaded_file):
+    raw = uploaded_file.read()
+    uploaded_file.seek(0)
+
+    for encoding in ["utf-8-sig", "utf-8", "latin1", "cp1252"]:
+        for sep in [",", ";", "\t"]:
+            try:
+                txt = raw.decode(encoding)
+                df = pd.read_csv(io.StringIO(txt), sep=sep)
+                if df.shape[1] > 1:
+                    return df
+            except Exception:
+                pass
+
+    return pd.read_csv(uploaded_file)
+
+
+def _pick(df, candidates):
+    for c in candidates:
+        if c in df.columns:
+            return c
+    return None
+
+
+def extract_zebris_csv(uploaded_file):
+    df = _read_csv_flex(uploaded_file)
+
+    out = pd.DataFrame(index=df.index)
+    mapping = {}
+    manquantes = []
+
+    # Nom
+    first_name_col = _pick(df, ["Prénom", "First Name"])
+    last_name_col = _pick(df, ["Nom de famille", "Last Name"])
+    if first_name_col and last_name_col:
+        out["Nom"] = (
+            df[first_name_col].astype(str).str.strip() + " " +
+            df[last_name_col].astype(str).str.strip()
+        )
+        mapping["Nom"] = [first_name_col, last_name_col]
+    else:
+        out["Nom"] = "Inconnu"
+        manquantes.append("Nom")
+
+    # Mapping direct depuis ton CSV Zebris
+    direct_map = {
+        "Date": ["Measurement date", "Date"],
+        "Poids (kg)": ["Body weight [Kg]", "Weight (kg)", "Poids (kg)"],
+        "Vitesse (km/h)": ["Vitesse [km/h]", "Speed [km/h]", "Speed (km/h)"],
+        "Cadence (pas/min)": ["Cadence [pass/min]", "Cadence [pas/min]", "Cadence"],
+        "Contact (%)": ["Total contact [%]", "Contact [%]"],
+        "Flight (%)": ["Total flight [%]", "Flight [%]"],
+        "Force talon G (N)": ["Force maximale Heel (Three zones) Gauche [N]"],
+        "Force talon D (N)": ["Force maximale Heel (Three zones) Droite [N]"],
+        "Force avant-pied G (N)": ["Force maximale Forefoot (Three zones) Gauche [N]"],
+        "Force avant-pied D (N)": ["Force maximale Forefoot (Three zones) Droite [N]"],
+        "Pression talon G (N/cm²)": ["Pression maximale Heel (Three zones) Gauche [N/cm²]", "Pression maximale Heel (Three zones) Gauche [N/cm2]"],
+        "Pression talon D (N/cm²)": ["Pression maximale Heel (Three zones) Droite [N/cm²]", "Pression maximale Heel (Three zones) Droite [N/cm2]"],
+        "COP G (mm)": ["Longueur lors de la phase d'appui Gauche [mm]"],
+        "COP D (mm)": ["Longueur lors de la phase d'appui Droite [mm]"],
+        "Rotation G (°)": ["Rotation du pied Gauche [degré]"],
+        "Rotation D (°)": ["Rotation du pied Droite [degré]"],
+        "Transition G (s)": ["Instant du passage du talon vers l'avant-pied Gauche [s]"],
+        "Transition D (s)": ["Instant du passage du talon vers l'avant-pied Droite [s]"],
+        "Longueur foulée (cm)": ["Longueur de la foulée [cm]"],
+        "Largeur pas (cm)": ["Largeur du pas [cm]"],
+    }
+
+    for target, candidates in direct_map.items():
+        col = _pick(df, candidates)
+        if col is None:
+            out[target] = np.nan
+            manquantes.append(target)
+        else:
+            mapping[target] = col
+            if target == "Date":
+                out[target] = df[col]
+            else:
+                out[target] = _to_numeric(df[col])
+
+    # Garde seulement les lignes avec une vitesse
+    out = out[out["Vitesse (km/h)"].notna()].copy()
+
+    # Réordonne
+    out = out.reindex(columns=STANDARD_COLUMNS).reset_index(drop=True)
+
+    debug = {
+        "mapping": mapping,
+        "manquantes": manquantes,
+        "colonnes_csv": list(df.columns),
+        "nb_lignes_csv": len(df),
+        "nb_lignes_extractees": len(out),
+    }
+
+    return out, debug