added readme

ideas/annotation/README.md

@@ -0,0 +1,20 @@
+# Idea: Integrated Annotation Tool For Images
+
+
+## Quickstart
+From the repositories base directory execute
+```
+python ideas/annotation/images.py
+```
+
+The data will be loaded from Azure. You have the option to either load sparse (in time) high-resolution images or low resolution images with a higher capture frequency. (This has been done to minimize transfer costs; all images are available in high-resolution upon request)
+You can also download the data (6.7 GB) yourself and use it (again executed from the base directory).
+
+```
+python utils/download_files.py -f timelapse_images_fast.zip
+python ideas/annotation/images.py --local
+```
+
+## What next?
+There are many tools available for image labeling, but what if we want to label timeseries data? How do we even label timeseries data? Can we simply draw on the plot of a time series or are there certain characteristics which are hidden and can only revealed with another view on the data?
+A way to plot annotations over time is presented in [timeseries.py](./timeseries.py)

ideas/annotation/images.py

@@ -229,6 +229,18 @@ def serve_layout():
                                 id="date_indicator",
                                 style={"width": "50%", "display": "inline-block"},
                             ),
+                            html.Div([
+                                dcc.Input(
+                                    id="userid_input",
+                                    placeholder="Your ID",
+                                    type="number",
+                                    value="",
+                                    persistence=True,
+                                ),
+                            ],
+                            style={"width": "50%", "display": "inline-block"},
+                            ),
+
                         ]
                     ),
                     html.Div(
@@ -254,7 +266,7 @@ def serve_layout():
                         options=[
                             {"label": bb_label_mapping[m], "value": m} for m in bb_label_mapping.keys()
                         ],
-                        value="red",
+                        value="#1f77b4",
                     ),
                     dcc.Dropdown(
                         id="static_label_dropdown",
@@ -270,16 +282,11 @@ def serve_layout():
                 className="six columns",
             ),
             dcc.Markdown(
-                "Annotate by selecting per picture labels or draw bounding boxes with the rectangle tool"
-                "Note: Rotating bounding boxes will result in incorrect labels."
-            ),
-            dcc.Input(
-                id="userid_input",
-                placeholder="Your user id",
-                type="number",
-                value="",
-                persistence=True,
+                """Annotate by selecting per picture labels or draw bounding boxes with the rectangle tool
+                   
+                   Note: Rotating bounding boxes will result in incorrect labels."""
             ),
+
         ],
         style={"width": "50%"},  # Div
         className="row",
@@ -308,10 +315,10 @@ def update_output(value):
 
 @app.callback(
     Output("my-date-picker-single", "date"),
-    [Input("canvas", "prev_trigger"), Input("canvas", "next_trigger")],
+    [Input("canvas", "prev_trigger"), Input("canvas", "next_trigger"), Input("userid_input","value")],
     [State("index", "data")],
 )
-def reduce_help(prev_trigger, next_trigger, index):
+def reduce_help(prev_trigger, next_trigger, userid_input_value, index):
     """ Triggers on click on the arrow buttons. Changes the date of the date selection tool,
         which triggers the loading of a new image.
     
@@ -337,13 +344,21 @@ def reduce_help(prev_trigger, next_trigger, index):
         index = 0
 
     if button_id == "canvas.prev_trigger":
-        index = index - 1
+        index = index - 2
         if index < 0:
             index = 0
     elif button_id == "canvas.next_trigger":
-        index = index + 1
+        index = index + 2
         if index >= len(data):
             index = len(data) - 1
+    elif button_id == "userid_input.value":
+        if userid_input_value is not None:
+            max_user = 90
+            index = int(len(data)/max_user * (userid_input_value-1))
+            if index < 0:
+                index = 0
+            if index >= len(data):
+                index = len(data) - 1
     else:
         raise PreventUpdate
 
@@ -465,9 +480,9 @@ def to_csv(df, session_id, file_id=None, user_id=None):
         stuett.to_csv_with_store(remote_store, filename, df, dict(index=False))
 
 
-def read_csv(session_id, file_id):
+def read_csv(session_id, file_id, user_id=None):
     global local_store
-    filename = session_id + f"/{file_id}.csv"
+    filename = session_id + "-" + str(user_id) + f"/{file_id}.csv"
     return stuett.read_csv_with_store(local_store, filename)
 
 
@@ -478,9 +493,9 @@ def read_csv(session_id, file_id):
         Output("date_indicator", "children"),
         Output("static_label_dropdown", "value"),
     ],
-    [Input("my-date-picker-single", "date"), Input("session-id", "children")],
+    [Input("my-date-picker-single", "date"), Input("session-id", "children"), Input("userid_input", "value")],
 )
-def update_output(date, session_id):
+def update_output(date, session_id, user_id):
     """ The callback is used to load a new image when the date has changed.
         Date change can be triggered by the date selector box or indirectly by the arrow buttons,
         which change the date selector box.
@@ -529,10 +544,10 @@ def update_output(date, session_id):
         datetime = data.index[index]
         file_id = datetime.strftime("%Y%m%d_%H%M%S")
         try:
-            df = read_csv(session_id, file_id)
-        except:
+            df = read_csv(session_id, file_id, user_id)
+        except Exception as e:
+            print('Could not read annotation file',e)
             df = None
-            pass
 
         # Load the annotations from the server
         try:

ideas/annotation/timeseries.py

@@ -0,0 +1,109 @@
+"""MIT License
+
+Copyright (c) 2019, Swiss Federal Institute of Technology (ETH Zurich), Matthias Meyer, Romain Jacob
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE."""
+
+import stuett
+from stuett.global_config import get_setting, setting_exists
+import argparse
+from pathlib import Path
+
+import pandas as pd
+from plotly.subplots import make_subplots
+import plotly.graph_objects as go
+import pandas as pd 
+
+parser = argparse.ArgumentParser(description="Seismic time series and spectogram plot")
+parser.add_argument(
+    "-p",
+    "--path",
+    type=str,
+    default=str(Path(__file__).absolute().parent.joinpath("..", "data/")),
+    help="The path to the folder containing the permafrost hackathon data",
+)
+parser.add_argument("-l", "--local", action="store_true", help="Load data from local storage")
+args = parser.parse_args()
+
+data_path = Path(args.path)
+annotations_path = data_path.joinpath("annotations")
+
+if not args.local:
+    account_name = (
+        get_setting("azure")["account_name"]
+        if setting_exists("azure")
+        else "storageaccountperma8980"
+    )
+    account_key = (
+        get_setting("azure")["account_key"] if setting_exists("azure") else None
+    )
+    annotation_store = stuett.ABSStore(
+        container="hackathon-on-permafrost",
+        prefix="annotations",
+        account_name=account_name,
+        account_key=account_key,
+        blob_service_kwargs={},
+    )
+else:
+    annotation_store = stuett.DirectoryStore(annotations_path)
+
+
+df = stuett.read_csv_with_store(annotation_store, "automatic_labels_mountaineers.csv")
+df['start_time'] = pd.to_datetime(df['start_time'] )
+df['end_time'] = pd.to_datetime(df['end_time'] )
+df.index = df['start_time']
+df = df['2017-08-01':'2017-08-02']
+
+
+fig = go.Figure(
+    layout=dict(
+        xaxis={"type": "date"},
+        xaxis_range=[
+            pd.to_datetime("2017-08-01"),
+            pd.to_datetime("2017-08-02"),
+        ],
+    )
+)
+
+for i,row in df.iterrows():
+    if(pd.isnull(row['__target'])):
+        continue
+    fig.add_trace(
+        go.Scatter(
+            x=[
+                row['start_time'],
+                row['end_time'],
+                row['end_time'],
+                row['start_time'],
+            ],
+            y=[0, 0, 1, 1],
+            fill="toself",
+            fillcolor="darkviolet",
+            # marker={'size':0},
+            mode="lines",
+            hoveron="points+fills",  # select where hover is active
+            line_color="darkviolet",
+            showlegend=False,
+            # line_width=0,
+            opacity=0.5,
+            text=str(row['__target']),
+            hoverinfo="text+x+y",
+        )
+    )
+fig.show()

ideas/machine_learning/datasets.py

@@ -181,13 +181,13 @@ def __getitem__(self, idx):
         if self.transform is not None:
             data = self.transform(data)
 
-        # if "shape" in self.__dict__:
+        # if "shape" not in self.__dict__:
         #     self.shape = data.shape
         # elif data.shape != self.shape:
-        #     warnings.warn(f"Inconsistency in the data for item {indexers['time']}, its shape {data.shape} does not match shape {shape}")
+        #     warnings.warn(f"Inconsistency in the data for item {indexers['time']}, its shape {data.shape} does not match shape {self.shape}")
         #     padded_data = torch.zeros(self.shape)
         #     pad = data.shape - self.shape
-        #     padded_data = torch.nn.functional.pad(data)
+        #     padded_data = torch.nn.functional.pad(data,pad)
 
         return data, target
 

tutorial/azure_integration.py

@@ -29,11 +29,12 @@
 import zarr
 
 
-account_name = (
-    get_setting("azure")["account_name"]
-    if setting_exists("azure")
-    else "storageaccountperma8980"
-)
+# Get the account name which is "storageaccountperma8980" for the hackathon
+# If you stored it in a config file you it will beloaded
+if setting_exists("azure"):
+    account_name = get_setting("azure")["account_name"]
+else:
+    account_name = "storageaccountperma8980"
 account_key = get_setting("azure")["account_key"] if setting_exists("azure") else None
 
 if account_key is not None:
@@ -42,22 +43,32 @@
 
 # Create a blob service and list all data available
 block_blob_service = BlockBlobService(
-    account_name="storageaccountperma8980", account_key=account_key
+    account_name=account_name, account_key=account_key
 )
 print("\nList blobs in the container")
 generator = block_blob_service.list_blobs("hackathon-on-permafrost")
-for blob in generator:
+for i, blob in enumerate(generator):
     print("\t Blob name: " + blob.name)
+    if i == 5:
+        break
 
-# Create a zarr store and load the data from the 
+print("List some documents")
+# In stuett we can use a a zarr store and load the data from there 
 store = stuett.ABSStore(
     container="hackathon-on-permafrost",
-    prefix="dataset/",
+    prefix="docs/",
     account_name=account_name,
     account_key=account_key,
     blob_service_kwargs={},
 )
 
+for i, key in enumerate(store.keys()):
+    print(key)
+    if i == 5:
+        break
+
+# # Currently, stuett (or zarr in the backend) only support azure-storage-blob==2.1.0`
+# # But a newer version is available which you can use independently
 # # using azure-storage-blob==12.0.0
 # # untested
 # from azure.storage.blob import BlobServiceClient

tutorial/howto_stuett.py

@@ -21,6 +21,10 @@
 SOFTWARE."""
 
 import stuett
+# What is stuett?
+# A data management package developed for analysing and visualizing outdoor sensor deployments
+# The name originates from the lower german word "stütt" which means "support"
+# The tool revolves around a feedback workflow where analysis is tighly integrated with multi-modal input
 
 import argparse
 from pathlib import Path
@@ -106,13 +110,3 @@
 # Note: The timezone used within stuett is UTC, but the datetime objects you receive are not timezone aware.
 #       Timezone issues are a recurring problem so be careful when working with the data.
 
-# TODO: Seismic (as xarray and obspy)
-# TODO: Images
-# TODO: Rock temperature
-# TODO: Wind
-# TODO: Precipitation
-# TODO: Radiation
-# TODO: Mountaineer Annotations
-# TODO: Annotations
-
-#### Graph ####