Added script to get all B and C survey data availible. Search by location ID

get_loc_survey_results.py

@@ -0,0 +1,150 @@
+import requests
+import pandas as pd
+import numpy as np
+
+
+def main(loc_id):
+    """
+    Fetch survey history for a fish farm location ID and expand with measurement data
+    for report_type 'b' (b-undersøkelser).
+
+    Adds columns:
+        - lat (list)
+        - lon (list)
+        - b_float_value (list)
+        - tilstand_final (list)
+        - depth (list)
+        - measurement number (list)
+
+    For reports without measurement data (including type 'c'),
+    these columns contain empty lists.
+    """
+
+    loc_id = str(loc_id)
+
+    base_url = "https://api.fiskeridir.no/envreportreg-public/api/v2/report/search"
+    params = {"siteNumber": loc_id}
+
+    response = requests.get(base_url, params=params)
+    response.raise_for_status()
+
+    data = response.json()
+    items = data.get("content", [])
+
+    if not items:
+        return pd.DataFrame(columns=[
+            "report_type", "report_date", "report_id", "download_link",
+            "lat", "lon", "b_float_value", "tilstand_final"
+        ])
+    dl_link = "https://api.fiskeridir.no/envreportreg-public/api/v2/report/"
+
+    # Build base dataframe
+    df = pd.DataFrame({
+        "report_type": [item.get("envExaminationType") for item in items],
+        "report_date": [item.get("reportCreated") for item in items],
+        "report_id":   [int(item.get("reportId")) for item in items],
+        "download_link" : [dl_link + str(item.get("reportId")) +  '/pdf' for item in items],
+    })
+
+    # Convert and sort
+    df["report_date"] = pd.to_datetime(df["report_date"], utc=True)
+
+    df = df.sort_values(
+        by=["report_type", "report_date"],
+        ascending=[True, False]
+    ).reset_index(drop=True)
+
+    # Prepare empty columns (lists per row)
+    df["lat"] = [[] for _ in range(len(df))]
+    df["lon"] = [[] for _ in range(len(df))]
+    df["b_float_value"] = [[] for _ in range(len(df))]
+    df["tilstand_final"] = [[] for _ in range(len(df))]
+    df["depth"] = [[] for _ in range(len(df))]
+    df["measurement_nr"] = [[] for _ in range(len(df))]
+
+    # Process only report_type 'b'
+    for idx, row in df.iterrows():
+
+        if row["report_type"] != "b":
+            continue
+
+        report_id = str(row["report_id"])
+        detail_url = f"https://api.fiskeridir.no/envreportreg-public/api/v2/report/{report_id}"
+
+        response = requests.get(detail_url)
+        response.raise_for_status()
+
+        detail_data = response.json()
+        measurements = detail_data.get("measurements", [])
+
+        if not measurements:
+            continue  # leave empty lists
+
+        # Extract values
+        lat = np.array([m.get("latitudeDecimal") for m in measurements])
+        lon = np.array([m.get("longitudeDecimal") for m in measurements])
+        b_float_value = np.array([m.get("medianGroupIIAndIIIValue") for m in measurements])
+        depth = np.array([m.get("depthMeters") for m in measurements])
+        measurement_nr = np.array([m.get("stationMeasurementNumber") for m in measurements])
+
+        # Keep only valid coordinates
+        valid_idx = np.where(lat > 0)[0]
+
+        lat = lat[valid_idx]
+        lon = lon[valid_idx]
+        b_float_value = b_float_value[valid_idx]
+        depth = depth[valid_idx]
+        measurement_nr = measurement_nr[valid_idx]
+
+        # Compute tilstand_final (vectorized)
+        tilstand_final = np.select(
+            [
+                b_float_value < 1.1,
+                (b_float_value >= 1.1) & (b_float_value < 2.1),
+                (b_float_value >= 2.1) & (b_float_value < 3.1),
+            ],
+            [1, 2, 3],
+            default=4
+        )
+
+        # Store as lists in dataframe
+        df.at[idx, "lat"] = lat.tolist()
+        df.at[idx, "lon"] = lon.tolist()
+        df.at[idx, "b_float_value"] = b_float_value.tolist()
+        df.at[idx, "tilstand_final"] = tilstand_final.tolist()
+        df.at[idx, "depth"] = depth.tolist()
+        df.at[idx, "measurement_nr"] = measurement_nr.tolist()
+
+    # Convert date back to string if desired
+    df["report_date"] = df["report_date"].dt.strftime("%Y-%m-%dT%H:%M:%SZ")
+
+
+    '''Example for plotting b_survey results:
+import matplotlib.pyplot as plt
+survey = 2
+color_map = {
+    1: 'blue',
+    2: 'green',
+    3: 'yellow',
+    4: 'red'
+}
+
+#colors = pd['tilstand_final'][0].map(color_map)
+colors = pd.Series(df2['tilstand_final'][survey]).map(color_map).tolist()
+
+plt.figure()
+
+plt.scatter(
+    df2['lon'][survey],
+    df2['lat'][survey],
+    c=colors,
+    marker='s'  # square
+)
+
+plt.xlabel('Longitude')
+plt.ylabel('Latitude')
+plt.title('Tilstand Plot B rapport '+ df2['report_date'][survey])
+
+plt.show()'''
+
+    return df