Merge pull request #99 from petrobras/other_improvements

Other improvements

README.md

@@ -153,7 +153,7 @@ $ conda env create -f environment.yml
 ```
 * To activate the created virtual environment:
 ```
-$ conda activate 3w
+$ conda activate 3W
 ```
 * To use the 3W toolkit resources interactively:
 ```

environment.yml

@@ -3,205 +3,19 @@ channels:
   - conda-forge
   - defaults
 dependencies:
-  - argon2-cffi=21.3.0=pyhd8ed1ab_0
-  - argon2-cffi-bindings=21.2.0=py310he2412df_2
-  - asttokens=2.0.8=pyhd8ed1ab_0
-  - attrs=22.1.0=pyh71513ae_1
-  - backcall=0.2.0=pyh9f0ad1d_0
-  - backports=1.0=py_2
-  - backports.functools_lru_cache=1.6.4=pyhd8ed1ab_0
-  - beautifulsoup4=4.11.1=pyha770c72_0
-  - bleach=5.0.1=pyhd8ed1ab_0
-  - brotli=1.0.9=h8ffe710_7
-  - brotli-bin=1.0.9=h8ffe710_7
-  - bzip2=1.0.8=h8ffe710_4
-  - ca-certificates=2022.12.7=h5b45459_0
-  - certifi=2022.12.7=pyhd8ed1ab_0
-  - cffi=1.15.1=py310hcbf9ad4_0
-  - colorama=0.4.5=pyhd8ed1ab_0
-  - contourpy=1.0.5=py310h232114e_0
-  - cycler=0.11.0=pyhd8ed1ab_0
-  - debugpy=1.6.3=py310h8a704f9_0
-  - decorator=5.1.1=pyhd8ed1ab_0
-  - defusedxml=0.7.1=pyhd8ed1ab_0
-  - entrypoints=0.4=pyhd8ed1ab_0
-  - executing=1.1.0=pyhd8ed1ab_0
-  - flit-core=3.7.1=pyhd8ed1ab_0
-  - fonttools=4.37.3=py310h8d17308_0
-  - freetype=2.12.1=h546665d_0
-  - gettext=0.19.8.1=h5728263_1009
-  - glib=2.74.0=h12be248_0
-  - glib-tools=2.74.0=h12be248_0
-  - gst-plugins-base=1.20.3=h001b923_2
-  - gstreamer=1.20.3=h6b5321d_2
-  - icu=70.1=h0e60522_0
-  - importlib-metadata=4.11.4=py310h5588dad_0
-  - importlib_resources=5.9.0=pyhd8ed1ab_0
-  - intel-openmp=2022.1.0=h57928b3_3787
-  - ipykernel=6.16.0=pyh025b116_0
-  - ipython=8.12.0=pyh08f2357_0
-  - ipython_genutils=0.2.0=py_1
-  - ipywidgets=8.0.2=pyhd8ed1ab_1
-  - jedi=0.18.1=pyhd8ed1ab_2
-  - jinja2=3.1.2=pyhd8ed1ab_1
-  - joblib=1.2.0=pyhd8ed1ab_0
-  - jpeg=9e=h8ffe710_2
-  - jsonschema=4.16.0=pyhd8ed1ab_0
-  - jupyter=1.0.0=py310h5588dad_7
-  - jupyter_client=7.3.5=pyhd8ed1ab_0
-  - jupyter_console=6.4.4=pyhd8ed1ab_0
-  - jupyterlab_pygments=0.2.2=pyhd8ed1ab_0
-  - jupyterlab_widgets=3.0.3=pyhd8ed1ab_0
-  - kiwisolver=1.4.4=py310h476a331_0
-  - krb5=1.19.3=h1176d77_0
-  - lcms2=2.12=h2a16943_0
-  - lerc=4.0.0=h63175ca_0
-  - libblas=3.9.0=16_win64_mkl
-  - libbrotlicommon=1.0.9=h8ffe710_7
-  - libbrotlidec=1.0.9=h8ffe710_7
-  - libbrotlienc=1.0.9=h8ffe710_7
-  - libcblas=3.9.0=16_win64_mkl
-  - libclang=14.0.6=default_hf4acfee_0
-  - libclang13=14.0.6=default_h8992b79_0
-  - libdeflate=1.14=hcfcfb64_0
-  - libffi=3.4.2=h8ffe710_5
-  - libglib=2.74.0=h79619a9_0
-  - libiconv=1.17=h8ffe710_0
-  - liblapack=3.9.0=16_win64_mkl
-  - libogg=1.3.4=h8ffe710_1
-  - libpng=1.6.38=h19919ed_0
-  - libsodium=1.0.18=h8d14728_1
-  - libsqlite=3.39.3=hcfcfb64_0
-  - libtiff=4.4.0=h8e97e67_4
-  - libvorbis=1.3.7=h0e60522_0
-  - libwebp=1.2.4=hcfcfb64_1
-  - libwebp-base=1.2.4=h8ffe710_0
-  - libxcb=1.13=hcd874cb_1004
-  - libxml2=2.10.2=h99b13fb_1
-  - libxslt=1.1.35=h34f844d_0
-  - libzlib=1.2.12=hcfcfb64_3
-  - llvmlite=0.39.1=py310hb84602e_0
-  - lxml=4.9.1=py310he2412df_0
-  - m2w64-gcc-libgfortran=5.3.0=6
-  - m2w64-gcc-libs=5.3.0=7
-  - m2w64-gcc-libs-core=5.3.0=7
-  - m2w64-gmp=6.1.0=2
-  - m2w64-libwinpthread-git=5.0.0.4634.697f757=2
-  - markupsafe=2.1.1=py310he2412df_1
-  - matplotlib-base=3.6.0=py310h51140c5_0
-  - matplotlib-inline=0.1.6=pyhd8ed1ab_0
-  - mistune=2.0.4=pyhd8ed1ab_0
-  - mkl=2022.1.0=h6a75c08_874
-  - msys2-conda-epoch=20160418=1
-  - munkres=1.1.4=pyh9f0ad1d_0
-  - natsort=8.2.0=pyhd8ed1ab_0
-  - nbclient=0.6.8=pyhd8ed1ab_0
-  - nbconvert=7.0.0=pyhd8ed1ab_0
-  - nbconvert-core=7.0.0=pyhd8ed1ab_0
-  - nbconvert-pandoc=7.0.0=pyhd8ed1ab_0
-  - nbformat=5.6.1=pyhd8ed1ab_0
-  - nest-asyncio=1.5.5=pyhd8ed1ab_0
-  - notebook=6.4.12=pyha770c72_0
-  - numba=0.56.4=py310h19bcfe9_0
-  - numpy=1.23.3=py310h4a8f9c9_0
-  - openjpeg=2.5.0=hc9384bd_1
-  - openssl=1.1.1t=hcfcfb64_0
-  - packaging=21.3=pyhd8ed1ab_0
-  - pandas=1.5.0=py310h1c4a608_0
-  - pandoc=2.19.2=h57928b3_0
-  - pandocfilters=1.5.0=pyhd8ed1ab_0
-  - parso=0.8.3=pyhd8ed1ab_0
-  - patsy=0.5.2=pyhd8ed1ab_0
-  - pcre2=10.37=hdfff0fc_1
-  - pickleshare=0.7.5=py_1003
-  - pip=22.2.2=pyhd8ed1ab_0
-  - pkgutil-resolve-name=1.3.10=pyhd8ed1ab_0
-  - platformdirs=2.5.2=pyhd8ed1ab_1
-  - plotly=5.13.0=pyhd8ed1ab_0
-  - ply=3.11=py_1
-  - prometheus_client=0.14.1=pyhd8ed1ab_0
-  - prompt-toolkit=3.0.31=pyha770c72_0
-  - prompt_toolkit=3.0.31=hd8ed1ab_0
-  - psutil=5.9.2=py310h8d17308_0
-  - pthread-stubs=0.4=hcd874cb_1001
-  - pure_eval=0.2.2=pyhd8ed1ab_0
-  - pycparser=2.21=pyhd8ed1ab_0
-  - pygments=2.13.0=pyhd8ed1ab_0
-  - pyparsing=3.0.9=pyhd8ed1ab_0
-  - pyqt=5.15.7=py310hbabf5d4_0
-  - pyqt5-sip=12.11.0=py310h8a704f9_0
-  - pyrsistent=0.18.1=py310he2412df_1
-  - python=3.10.6=h9a09f29_0_cpython
-  - python-dateutil=2.8.2=pyhd8ed1ab_0
-  - python-fastjsonschema=2.16.2=pyhd8ed1ab_0
-  - python_abi=3.10=2_cp310
-  - pytz=2022.2.1=pyhd8ed1ab_0
-  - pywin32=303=py310he2412df_0
-  - pywinpty=2.0.8=py310h00ffb61_0
-  - pyzmq=24.0.1=py310hcd737a0_0
-  - qt-main=5.15.6=hf0cf448_0
-  - qtconsole=5.3.2=pyhd8ed1ab_0
-  - qtconsole-base=5.3.2=pyha770c72_0
-  - qtpy=2.2.0=pyhd8ed1ab_0
-  - scikit-learn=1.1.2=py310h3a564e9_0
-  - scipy=1.9.1=py310h578b7cb_0
-  - seaborn=0.12.0=hd8ed1ab_0
-  - seaborn-base=0.12.0=pyhd8ed1ab_0
-  - send2trash=1.8.0=pyhd8ed1ab_0
-  - setuptools=65.4.0=pyhd8ed1ab_0
-  - sip=6.6.2=py310h8a704f9_0
-  - six=1.16.0=pyh6c4a22f_0
-  - soupsieve=2.3.2.post1=pyhd8ed1ab_0
-  - stack_data=0.5.1=pyhd8ed1ab_0
-  - statsmodels=0.13.2=py310h2873277_0
-  - tbb=2021.6.0=h91493d7_0
-  - tenacity=8.1.0=pyhd8ed1ab_0
-  - terminado=0.15.0=py310h5588dad_0
-  - threadpoolctl=3.1.0=pyh8a188c0_0
-  - tinycss2=1.1.1=pyhd8ed1ab_0
-  - tk=8.6.12=h8ffe710_0
-  - toml=0.10.2=pyhd8ed1ab_0
-  - tornado=6.2=py310he2412df_0
-  - traitlets=5.4.0=pyhd8ed1ab_0
-  - tslearn=0.5.3.2=py310h9b08ddd_0
-  - typing_extensions=4.3.0=pyha770c72_0
-  - tzdata=2022d=h191b570_0
-  - ucrt=10.0.20348.0=h57928b3_0
-  - unicodedata2=14.0.0=py310he2412df_1
-  - vc=14.2=hb210afc_7
-  - vs2015_runtime=14.29.30139=h890b9b1_7
-  - wcwidth=0.2.5=pyh9f0ad1d_2
-  - webencodings=0.5.1=py_1
-  - wheel=0.37.1=pyhd8ed1ab_0
-  - widgetsnbextension=4.0.3=pyhd8ed1ab_0
-  - winpty=0.4.3=4
-  - xorg-libxau=1.0.9=hcd874cb_0
-  - xorg-libxdmcp=1.1.3=hcd874cb_0
-  - xz=5.2.6=h8d14728_0
-  - zeromq=4.3.4=h0e60522_1
-  - zipp=3.8.1=pyhd8ed1ab_0
-  - zlib=1.2.12=hcfcfb64_3
-  - zstd=1.5.2=h7755175_4
-  - pip:
-      - about-time==3.1.1
-      - alive-progress==2.4.1
-      - charset-normalizer==3.0.1
-      - grapheme==0.6.0
-      - htmlmin==0.1.12
-      - idna==3.4
-      - imagehash==4.3.1
-      - jupyter-core==4.11.2
-      - multimethod==1.9.1
-      - networkx==3.0
-      - pandas-profiling==3.6.3
-      - phik==0.12.3
-      - pillow==9.3.0
-      - pydantic==1.10.4
-      - pywavelets==1.4.1
-      - pyyaml==6.0
-      - requests==2.28.2
-      - tangled-up-in-unicode==0.2.0
-      - tqdm==4.64.1
-      - typeguard==2.13.3
-      - urllib3==1.26.14
-      - visions==0.7.5
+  - python=3.10.6
+  - notebook=6.4.12
+  - alive-progress=2.4.1
+  - h5py=3.11.0
+  - matplotlib=3.6.0
+  - natsort=8.2.0
+  - pandas=1.5.0
+  - plotly=5.13.0
+  - pydantic=1.10.4
+  - scikit-learn=1.1.2
+  - seaborn=0.12.0
+  - tslearn=0.5.3.2
+  - pandas-profiling=3.6.3
+  - numba=0.56.4
+  - missingno=0.5.2
+

overviews/AndreMachado/main.ipynb

@@ -63528,7 +63528,7 @@
    "source": [
     "class_number = 2\n",
     "resample_factor = 100\n",
-    "df_all_instances_class = pd.concat([tk.resample(pd.read_csv(f, sep=',',header=0),resample_factor,class_number)for f in glob.glob(tk.PATH_DATASET + '\\\\'+str(class_number)+'\\\\*.csv')],ignore_index=True)"
+    "df_all_instances_class = pd.concat([tk.resample(pd.read_csv(f, sep=',',header=0),resample_factor,class_number)for f in glob.glob(os.path.join(tk.PATH_DATASET, str(class_number), \"*.csv\"))],ignore_index=True)"
    ]
   },
   {

toolkit/misc.py

@@ -8,6 +8,7 @@
 import matplotlib.pyplot as plt
 import matplotlib.dates as mdates
 import matplotlib.colors as mcolors
+import os
 
 from matplotlib.patches import Patch
 from pathlib import Path
@@ -538,7 +539,7 @@ def resample(data, n, class_number):
     # Back with transient label value
     resampleClass.replace(0.5, class_number + 100, inplace=True)
     # Non overlap group and get the average value from the data
-    dfResample = data.groupby(data.index // n).mean()
+    dfResample = data.groupby(data.index // n).mean(numeric_only=True)
     # Drop class column
     dfResample.drop(["class"], axis=1, inplace=True)
     # Insert new class label values group by non overlap
@@ -557,7 +558,7 @@ def plot_instance(class_number, instance_index, resample_factor):
         class_number (integer): integer that represents the event class [0-8]
         instance_index (integer): input the instance file index
     """
-    instances_path = PATH_DATASET + "\\" + str(class_number) + "\\*.csv"
+    instances_path = os.path.join(PATH_DATASET, str(class_number), "*.csv")
     instances_path_list = glob.glob(instances_path)
     if class_number > 8 or class_number < 0:
         print(
@@ -571,7 +572,9 @@ def plot_instance(class_number, instance_index, resample_factor):
         df_instance = pd.read_csv(
             instances_path_list[instance_index], sep=",", header=0
         )
+
         df_instance_resampled = resample(df_instance, resample_factor, class_number)
+
         df_drop_resampled = df_instance_resampled.drop(["timestamp", "class"], axis=1)
         df_drop_resampled.interpolate(
             method="linear", limit_direction="both", axis=0, inplace=True
@@ -708,7 +711,7 @@ def plot_instance(class_number, instance_index, resample_factor):
                 line_color=colors_traces[8],
             )
         ),
-        fileName = instances_path_list[instance_index].split("\\")
+        fileName = instances_path_list[instance_index].split(os.sep)
         fig.update_layout(
             title=EVENT_NAMES[class_number] + " - " + fileName[-1],
             xaxis_title="Time(s)",