slight update

.dockerignore

+.gitignore
+.idea
+.pytest_cache
+.venv
+.git/
+__pycache__/
+**/__pycache__/
+DockerfileConda
+README.md
\ No newline at end of file

.streamlit/config.toml

 [server]
 maxUploadSize = 4096
+[browser]
+gatherUsageStats = false
\ No newline at end of file

Dockerfile

-FROM continuumio/miniconda3:latest as conda
+ARG WORKDIR="/app"
 
-ENV PYTHONUNBUFFERED=1
-WORKDIR /app
+FROM python:3.11 as builder
 
-# RUN git clone https://git-ce.rwth-aachen.de/leah.tgu/mdata_app.git .
-COPY .streamlit/ .streamlit/
-COPY logic/ logic/
-COPY pages/ pages/
-COPY resources/ resources/
-COPY environment.yml streamlit_app.py ./
+ARG WORKDIR
 
-FROM conda as builder
+ENV PYTHONFAULTHANDLER=1 \
+    PYTHONHASHSEED=random \
+    PYTHONUNBUFFERED=1 \
+    PYTHONDONTWRITEBYTECODE=1
 
-RUN conda env create -f "environment.yml"
+ENV PIP_DEFAULT_TIMEOUT=100 \
+    PIP_DISABLE_PIP_VERSION_CHECK=1 \
+    PIP_NO_CACHE_DIR=1 \
+    POETRY_VERSION=1.5
 
+#RUN apk add build-base libffi-dev
 
-FROM builder as final
+RUN pip install "poetry==$POETRY_VERSION" && poetry config virtualenvs.in-project true
+
+WORKDIR ${WORKDIR}
+
+ADD pyproject.toml poetry.lock ./
+
+RUN poetry install --only=main --no-root
+
+#RUN apt-get update && apt-get install -y \
+#    build-essential \
+#    curl \
+#    software-properties-common \
+#    git \
+#    python3-dev \
+#    libblas-dev \
+#    liblapack-dev \
+#    && rm -rf /var/lib/apt/lists/*
+#RUN git clone --single-branch -b release https://git-ce.rwth-aachen.de/leah.tgu/mdata_app.git .
+#COPY .streamlit/ .streamlit/
+#COPY logic/ logic/
+#COPY pages/ pages/
+#COPY resources/ resources/
+#COPY poetry.lock pyproject.toml streamlit_app.py ./
+
+FROM python:3.11-slim as final
+ARG WORKDIR
+WORKDIR ${WORKDIR}
+
+COPY --from=builder ${WORKDIR} .
+ADD .streamlit/ .streamlit/
+ADD logic/ logic/
+ADD pages/ pages/
+ADD resources/ resources/
+ADD streamlit_app.py .streamlit ./
 
 EXPOSE 8501
 
 HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
-
-SHELL ["conda", "run", "-n", "mdata-app", "/bin/bash", "-c"]
 # CMD ["./docker-entrypoint.sh"]
-ENTRYPOINT ["conda", "run", "--no-capture-output", "-n", "mdata-app", "streamlit", "run", "streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]
\ No newline at end of file
+ENTRYPOINT ["./.venv/bin/python", "-m", "streamlit", "run", "streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]

DockerfileConda

 FROM continuumio/miniconda3:latest as conda
 
-ENV PYTHONFAULTHANDLER=1 \
-    PYTHONHASHSEED=random \
-    PYTHONUNBUFFERED=1
-
+ENV PYTHONUNBUFFERED=1
 WORKDIR /app
 
-FROM conda as builder
-
-ENV PIP_DEFAULT_TIMEOUT=100 \
-    PIP_DISABLE_PIP_VERSION_CHECK=1 \
-    PIP_NO_CACHE_DIR=1
-
-
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    software-properties-common \
-    git \
-    python3-dev \
-    libblas-dev \
-    liblapack-dev \
-    && rm -rf /var/lib/apt/lists/*
-
-# RUN git clone https://git-ce.rwth-aachen.de/leah.tgu/mdata_app.git .
+#RUN apt-get update && apt-get install -y \
+#    build-essential \
+#    curl \
+#    software-properties-common \
+#    git \
+#    python3-dev \
+#    libblas-dev \
+#    liblapack-dev \
+#    && rm -rf /var/lib/apt/lists/*
+
+#RUN git clone --single-branch -b release https://git-ce.rwth-aachen.de/leah.tgu/mdata_app.git .
+COPY .streamlit/ .streamlit/
 COPY logic/ logic/
 COPY pages/ pages/
 COPY resources/ resources/
-COPY poetry.lock pyproject.toml environment.yml streamlit_app.py ./
+COPY environment.yml streamlit_app.py ./
 
-RUN conda env create -f "environment.yml"
+FROM conda as builder
 
+RUN conda env create -f "environment.yml"
 
 FROM builder as final
 
+COPY --from=builder /opt/venv venv
+
 EXPOSE 8501
 
 HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health

DockerfilePoetry

-FROM python:3.9-slim as base
-
-ENV PYTHONFAULTHANDLER=1 \
-    PYTHONHASHSEED=random \
-    PYTHONUNBUFFERED=1
-
-WORKDIR /app
-
-FROM base as builder
-
-ENV PIP_DEFAULT_TIMEOUT=100 \
-    PIP_DISABLE_PIP_VERSION_CHECK=1 \
-    PIP_NO_CACHE_DIR=1 \
-    POETRY_VERSION=1.4
-
-RUN pip install "poetry==$POETRY_VERSION"
-
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    software-properties-common \
-    git \
-    python3-dev \
-    libblas-dev \
-    liblapack-dev \
-    && rm -rf /var/lib/apt/lists/*
-
-# RUN git clone https://git-ce.rwth-aachen.de/leah.tgu/mdata_app.git .
-COPY .streamlit/ .streamlit/
-COPY logic/ logic/
-COPY pages/ pages/
-COPY resources/ resources/
-COPY poetry.lock pyproject.toml streamlit_app.py ./
-
-RUN poetry config virtualenvs.in-project true && \
-    poetry install --only=main --no-root && \
-    poetry build
-
-FROM base as final
-
-COPY --from=builder /app/.venv ./.venv
-COPY --from=builder /app/dist .
-COPY docker-entrypoint.sh .
-
-RUN ./.venv/bin/pip install *.whl
-
-EXPOSE 8501
-
-HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
-
-# CMD ["./docker-entrypoint.sh"]
-ENTRYPOINT ["streamlit", "run", "streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]
\ No newline at end of file

environment.yml

 name: mdata-app
 
 dependencies:
-  - python=3.10
+  - python=3.11
   - numpy
   - matplotlib
   - seaborn
@@ -11,4 +11,4 @@ dependencies:
   - pip:
       - tsdownsample
       - streamlit
-      - git+https://git-ce.rwth-aachen.de/leah.tgu/mdata@develop
\ No newline at end of file
+      - git+https://git-ce.rwth-aachen.de/leah.tgu/mdata@master
\ No newline at end of file

logic/page_logic.py

+from collections.abc import Mapping
 from enum import Enum
 
 import pandas as pd
 import streamlit as st
-from mdata.core import mdd
+from mdata.core import MDConcepts, MachineData, ObservationTypes
+from mdata.core.factory import as_base
+from mdata.core.protocols import TSSpec
 from mdata.visualization import plotting, matplot
 
+
 class Widgets(Enum):
     Specifications = 'Specifications'
     RawData = 'Raw Data'
@@ -12,13 +16,17 @@ class Widgets(Enum):
     Inspector = 'Inspector'
     Dummy = 'Dummy'
 
+
 available_widgets = [w for w in Widgets]
 
-def generate_page(md: mdd.MachineData, widget):
+
+def generate_page(md: MachineData, widget):
+    md = as_base(md)
+
     c = st.columns(3)
-    c[0].metric('#Observations', len(md.index_frame))
-    c[1].metric('#Event Types', len(md.event_series_types))
-    c[2].metric('#Measurement Types', len(md.measurement_series_types))
+    c[0].metric('#Observations', md.observation_count)
+    c[1].metric('#Event Types', len(md.event_specs))
+    c[2].metric('#Measurement Types', len(md.measurement_specs))
 
     c = st.columns(2)
     cont = c[0].container()
@@ -30,11 +38,11 @@ def generate_page(md: mdd.MachineData, widget):
 
     if widget == Widgets.Specifications:
         st.markdown('## Events')
-        st.table(make_spec_df(md.event_series_types))
+        st.table(make_spec_df(md.event_specs))
         st.markdown('## Measurements')
-        st.table(make_spec_df(md.measurement_series_types))
-        fig = plotting.create_measurement_frequency_plot(md)
-        st.plotly_chart(fig)
+        st.table(make_spec_df(md.measurement_specs))
+        #fig = plotting.create_measurement_frequency_plot(md)
+        #st.plotly_chart(fig)
 
     elif widget == Widgets.RawData:
 
@@ -43,13 +51,15 @@ def generate_page(md: mdd.MachineData, widget):
             st.markdown('## Index')
             st.write(md.index_frame)
         with c2:
-            selection = st.selectbox('Observation Type', [tsc.timeseries_type.type + ':' + tsc.timeseries_type.label for tsc in md.iter_all_timeseries()])
+            selection = st.selectbox('Observation Spec',
+                                     [tsc.timeseries_spec.type + ':' + tsc.timeseries_spec.label for tsc in
+                                      md.series_containers])
             if selection is not None:
                 label = selection[2:]
-                if selection[0] == 'E':
-                    st.write(md.get_event_series_collection(label).df)
-                if selection[0] == 'M':
-                    st.write(md.get_measurement_series_collection(label).df)
+                if selection[0] == ObservationTypes.E:
+                    st.write(md.get_events(label).df)
+                if selection[0] == ObservationTypes.M:
+                    st.write(md.get_measurements(label).df)
 
     elif widget == Widgets.Overview:
         f = plotting.create_overview_plot(md, downsample_to=5_000)
@@ -57,35 +67,39 @@ def generate_page(md: mdd.MachineData, widget):
 
     elif widget == Widgets.Inspector:
         c1, c2, c3 = st.columns(3)
-        event_type_list = list(md.event_series_types.keys())
-        measurement_type_list = list(md.measurement_series_types.keys())
-        selected_measurement_type = c1.selectbox('Measurement Type', measurement_type_list)
-        fs = list(md.measurement_series_types[selected_measurement_type].features)
-        object_list = list(md.measurement_series[selected_measurement_type].occurring_objects)
+        event_specs_list = list(md.event_series.keys())
+        measurement_spec_list = list(md.measurement_series.keys())
+        selected_measurement_spec = c1.selectbox('Measurement Spec', measurement_spec_list)
+        fs, object_list = [], []
+        if selected_measurement_spec is not None:
+            fs = list(md.measurement_specs[selected_measurement_spec].features)
+            object_list = list(md.measurement_series[selected_measurement_spec].objects)
         measurement_feature_selection = c1.multiselect('Feature Selection', fs)
 
-        event_selection = c2.multiselect('Event Type Selection', event_type_list)
+        event_selection = c2.multiselect('Event Spec Selection', event_specs_list)
         plot_separately = c2.checkbox('plot separately', False)
 
         object_selection = c3.selectbox('Object Selection', object_list)
 
-        f = plotting.create_timeseries_plot(md, measurement_type=selected_measurement_type, object=object_selection,
+        f = plotting.create_timeseries_plot(md, measurement_spec=selected_measurement_spec, obj=object_selection,
                                             events=event_selection, features=measurement_feature_selection,
                                             split_into_subplots=plot_separately)
 
         st.plotly_chart(f, use_container_width=True)
 
     elif widget == Widgets.Dummy:
-        measurement_type_list = list(md.measurement_series_types.keys())
-        selected_measurement_type = st.selectbox('Measurement Type', measurement_type_list)
-        f = matplot.create_basic_stacked_subplots(md, measurement_type=selected_measurement_type)
+        measurement_spec_list = list(md.measurement_specs)
+        selected_measurement_spec = st.selectbox('Measurement Spec', measurement_spec_list)
+        if selected_measurement_spec is not None:
+            f = matplot.create_basic_stacked_subplots(md, measurement_type=selected_measurement_spec)
             st.write(f)
 
     else:
         st.write('Invalid Widget')
 
-def make_spec_df(spec_types):
-    df = pd.DataFrame.from_dict({l: list(t.features) for l, t in spec_types.items()},
+
+def make_spec_df(spec_types: Mapping[str, TSSpec]):
+    df = pd.DataFrame.from_dict({label: list(spec.features) for label, spec in spec_types.items()},
                                 orient='index').replace(pd.NA, '')
     df.columns = [f'f_{i}' for i in range(1, len(df.columns) + 1)]
     return df

pages/export.py

@@ -3,32 +3,32 @@ import os
 import tempfile
 import zipfile
 
-import mdata.core.machine_data_def as mdd
-import mdata.file_formats.csv.shared
 import streamlit as st
+from mdata.core import MachineData, MDConcepts
+from mdata.io import read_machine_data, write_machine_data, write_machine_data_h5
+from mdata.file_formats.csv.shared import HeaderFileFormats
 from mdata.file_formats.csv.exporting import write_machine_data_custom
-from mdata.file_formats.hdf import write_machine_data_h5
 
 st.title('Machine Data File Export & Conversions')
 
 if 'uploaded_md' not in st.session_state:
     st.write('No data has been uploaded yet')
 else:
-    md: mdd.MachineData = st.session_state['uploaded_md']
+    md: MachineData = st.session_state['uploaded_md']
 
     st.header('File Format Exports')
 
     st.subheader('CSV')
 
-    header_format = st.selectbox('Header file type', mdata.file_formats.csv.shared.HeaderFileFormats)
+    header_format = st.selectbox('Header file type', HeaderFileFormats.values)
     do_csv_export = st.button('Convert to CSV')
 
     zip_download = st.empty()
     header_download = st.empty()
     csv_download = st.empty()
 
-    st.subheader('HDF')
-    do_hdf_export = st.button('Convert to HDF')
+    st.subheader('HDF 5')
+    do_hdf_export = st.button('Convert to HDF 5')
     hdf_download = st.empty()
 
     if do_csv_export:

pages/upload.py

@@ -25,6 +25,7 @@ elif import_type == 'hdf':
 
 if st.button('clear upload'):
     st.cache_data.clear()
+    if 'uploaded_md' in st.session_state:
         del st.session_state['uploaded_md']
 
 

pyproject.toml

@@ -6,20 +6,23 @@ authors = ["Leah Tacke genannt Unterberg <leah.tgu@pads.rwth-aachen.de>"]
 packages = [{ include = "mdata_app" }]
 readme = "README.md"
 license = "MIT"
-
+include = [".streamlit", "logic", "pages", "resources"]
 
 [tool.poetry.dependencies]
-python = "^3.9,!=3.9.7"
+python = "^3.11"
+streamlit = "^1.25"
 cvxopt = "^1.3"
-streamlit = "^1.23"
-# mdata = "^0.1.0"
-mdata = { path = "C:/Users/Leah/PycharmProjects/mdata", develop = true }
-# mdata = { git = "https://git-ce.rwth-aachen.de/leah.tgu/mdata.git", branch = "master" }
+# mdata = "^0.1.2"
+pyyaml = "*"
+mdata = { git = "https://git-ce.rwth-aachen.de/machine-data/mdata.git", branch = "master" }
+#mdata = [
+#    { platform = "linux", git = "https://git-ce.rwth-aachen.de/leah.tgu/mdata.git", branch = "master" },
+#    { platform = "windows", path = "C:/Users/Leah/PycharmProjects/mdata", develop = true }
+#]
 seaborn = "^0.12.2"
 plotly = "^5.15"
 tsdownsample = "^0.1.2"
 
-
 [build-system]
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"