Merge pull request #38 from sdevenes/issue_29/deployment

Issue 29/deployment

.gitignore

@@ -5,7 +5,36 @@ data/
 docs/build/*
 docs/source/api/
 
-### Python execution ###
-scripts/__pycache__/
-tests/output/
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# test results
+rr/tests/output/
 

.travis.yml

@@ -6,27 +6,19 @@ python:
   - "3.8"
 install:
   # Install phase of our CI pipeline
-  - wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda.sh
-  - bash miniconda.sh -b -p $HOME/miniconda
-  - source "$HOME/miniconda/etc/profile.d/conda.sh"
-  - hash -r
-  - conda config --set always_yes yes --set changeps1 no
-  - conda update -q conda
-  - conda info -a
-  - conda create -q -n project python=$TRAVIS_PYTHON_VERSION -c plotly --file requirements.txt --file build-requirements.txt
-  - conda activate project
+  - pip install .
+  - pip install -r build-requirements.txt
 
 script:
-  # Run phase of our CI pipeline
   # Run unitTests
-  - nosetests --nocapture -v tests/test.py --with-coverage --cover-package=scripts
+  - nosetests --nocapture -v rr --with-coverage --cover-package=rr
   # Generate rst files from docstring
-  - sphinx-apidoc -fMeT -o docs/source/api scripts
+  - sphinx-apidoc -fMeT -o docs/source/api rr rr/tests
   # Build documentation
   - sphinx-build docs/source docs/build
   - touch docs/build/.nojekyll
   # Black lint checking
-  - black --check scripts/ tests/
+  - black --check rr/
 after_success:
   # update coveralls report
   - coveralls
@@ -39,4 +31,12 @@ deploy:
     local_dir: ./docs/build
     on:
         branch: master
-        condition: $TRAVIS_PYTHON_VERSION = 3.8
+        condition: "$TRAVIS_PYTHON_VERSION = 3.8"
+#  - provider: pypi
+#      server: https://test.pypi.org/legacy/ # Remove to deployment on pypi.org
+#      username: "__token__"
+#      password:
+#        secure: AgENdGVzdC5weXBpLm9yZwIkNDkzMjE2ZDMtYjlhYy00NTViLTg1MzYtZGU4N2YyNjA0NDY1AAIleyJwZXJtaXNzaW9ucyI6ICJ1c2VyIiwgInZlcnNpb24iOiAxfQAABiCE1UhRrnGVriZfsUQEp0YRaWTuAOLsDggCBBsOB-PbMQ
+#      on:
+#        tags: true
+#        condition: "$TRAVIS_PYTHON_VERSION = 3.8"

MANIFEST.in

@@ -0,0 +1,3 @@
+include LICENSE README.rst buildout.cfg requirements.txt
+recursive-include doc conf.py *.rst *.ico *.png
+graft tests/inputs

build-requirements.txt

@@ -4,3 +4,4 @@ nose
 coverage
 coveralls
 black
+twine

docs/source/conf.py

@@ -13,7 +13,7 @@
 import os
 import sys
 import subprocess
-sys.path.insert(0, os.path.abspath('../../scripts'))
+sys.path.insert(0, os.path.abspath('../../experiment'))
 
 
 # -- Project information -----------------------------------------------------

experiment.ini

@@ -0,0 +1,7 @@
+[nb_trees_experiment]
+nb_trees = 1, 2
+tree_depth = 10
+
+[tree_depth_experiment]
+nb_trees = 10
+tree_depth = 1, 2

rr/download_data/__main__.py

@@ -0,0 +1,22 @@
+import sys
+import argparse
+import os.path
+from rr.download_data import download_data
+
+
+def main():
+
+    parser = argparse.ArgumentParser(
+        description="M05 mini-project: Download dataset.zip online"
+    )
+    parser.add_argument("source", type=str, help="Data zip url")
+    parser.add_argument("destination", type=str, help="Destination folder")
+    args = parser.parse_args()
+
+    download_destination = os.path.join(args.destination + "/dataset.zip")
+    download_data.download_url(args.source, download_destination)
+    download_data.unzip_file(download_destination, args.destination)
+
+
+if __name__ == "__main__":
+    sys.exit(main())

scripts/download_data.py → rr/download_data/download_data.py

@@ -3,7 +3,7 @@
 import zipfile
 
 
-# Function to download a file through http.get using requests
+# Function to download_data a file through http.get using requests
 def download_url(url, save_path):
     """Download a file from the given url using http
 
@@ -16,7 +16,7 @@ def download_url(url, save_path):
         None
     """
     with open(save_path, "wb") as f:
-        print("Downloading {} from {}".format(save_path, url))
+        print("Downloading {} from {}...".format(save_path, url))
         response = requests.get(url, stream=True)
         total_length = response.headers.get("content-length")
 
@@ -31,7 +31,7 @@ def download_url(url, save_path):
                 done = int(50 * dl / total_length)
                 sys.stdout.write("\r[%s%s]" % ("=" * done, " " * (50 - done)))
                 sys.stdout.flush()
-    print()
+        print("Download succes.\n")
 
 
 # Function to unzip files
@@ -46,17 +46,7 @@ def unzip_file(path_to_zip_file, directory_to_extract_to):
     Raises:
         None
     """
-    print("Unzip files..")
+    print("Unzip {} to {}...".format(path_to_zip_file, directory_to_extract_to))
     with zipfile.ZipFile(path_to_zip_file, "r") as zip_ref:
         zip_ref.extractall(directory_to_extract_to)
-
-
-if __name__ == "__main__":
-    url = "https://archive.ics.uci.edu/ml/machine-learning-databases/00506/casas-dataset.zip"
-    url_test = "https://archive.ics.uci.edu/ml/machine-learning-databases/00405/Postures.zip"  # Smaller zip to test
-    save_path = "../data/casas-dataset.zip"
-    # Download zip file
-    download_url(url, save_path)
-    # Unzip it
-    unzip_file(save_path, "../data_test/")
-    print("Done")
+        print("Unzip succes.\n")

rr/experiment/__main__.py

@@ -0,0 +1,51 @@
+import sys
+import argparse
+import configparser
+from rr.experiment import experiments, database
+import os.path
+
+
+def main():
+    parser = argparse.ArgumentParser(description="M05 mini-project: experiments")
+    parser.add_argument("datapath", type=str, help="Dataset file in .csv")
+    parser.add_argument("output", type=str, help="Destination folder for the results")
+    parser.add_argument(
+        "config", type=str, help="Filepath for experiments configuration file in .ini"
+    )
+    args = parser.parse_args()
+
+    config = configparser.ConfigParser()
+    config.read(args.config)
+
+    print(
+        "M05 mini-project on Human Activity Recognition with Random Forest classifier"
+    )
+    tabnum = 1
+    experiment_results = experiments.experiment_impact_nb_trees(
+        tabnum,
+        filepath=args.datapath,
+        nb_trees=[int(n) for n in config["nb_trees_experiment"]["nb_trees"].split(",")],
+        max_depth=int(config["nb_trees_experiment"]["tree_depth"]),
+        plot_path=args.output,
+    )
+
+    tabnum += len(config["nb_trees_experiment"]["nb_trees"].split(",")) * len(
+        database.PROTOCOLS
+    )
+    experiment_results += experiments.experiment_impact_tree_depth(
+        tabnum,
+        filepath=args.datapath,
+        nb_trees=int(config["tree_depth_experiment"]["nb_trees"]),
+        max_depths=[
+            int(d) for d in config["tree_depth_experiment"]["tree_depth"].split(",")
+        ],
+        plot_path=args.output,
+    )
+
+    with open(os.path.join(args.output, "experiment_results.txt"), "w+") as fout:
+        fout.write(experiment_results)
+    print("Experiments done\n")
+
+
+if __name__ == "__main__":
+    sys.exit(main())

rr/experiment/algorithm.py

@@ -0,0 +1,51 @@
+from sklearn.ensemble import RandomForestClassifier
+
+import logging
+
+logger = logging.getLogger()
+
+
+class Model:
+    def __init__(self, nb_tree_per_forest=50, max_depth=10):
+        """Create a new ML model (Random forest classifier from scikitlearn)
+
+        Args:
+            nb_tree_per_forest (int): number of decision trees in the forest
+            max_depth (int): max depth of the trees
+        Returns:
+            None
+        Raises:
+            None
+        """
+        self.model = RandomForestClassifier(
+            n_estimators=nb_tree_per_forest, max_depth=max_depth, random_state=0
+        )
+
+    def train(self, X, y):
+        """Train the model using the given data
+
+        Args:
+            X (numpy.ndarray):A NxM 2D-array where each row corresponds to a sample and each column to a feature
+            y (numpy.ndarray): A 1D-array of length N, where each element corresponds to a sample label
+        Returns:
+            None
+        Raises:
+            None
+        """
+        self.model.fit(X, y)
+
+    def predict(self, X):
+        """Make a prediction on the data using the trained model
+
+        Args:
+            X (numpy.ndarray):A NxM 2D-array where each row corresponds to a sample and each column to a feature
+        Returns:
+            numpy.ndarray: A 1D array (with a dtype of int) containing the predicted
+            label for each sample
+
+        Raises:
+            None
+        """
+        prediction = self.model.predict(X)
+
+        return prediction

scripts/analysis.py → rr/experiment/analysis.py

@@ -1,15 +1,14 @@
 import plotly.express as px
 from sklearn.metrics import confusion_matrix
 import numpy as np
-import itertools
 
 
 def get_confusion_matrix(prediction_label, true_label):
     """Get the confusion matrix given the predicted and true labels
 
     Args:
         prediction_label (list): Estimated targets as returned by a classifier.
-        true_label (list): Ground truth (correct) target values.   
+        true_label (list): Ground truth (correct) target values.
     Returns:
         numpy.ndarray: A 2D array (with a dtype of int) containing the confusion matrix.
     Raises:
@@ -26,15 +25,14 @@ def plot_confusion_matrix(
     Args:
         cm (numpy.ndarray): A 2D array (with a dtype of int) containing the confusion matrix.
         classes (numpy.ndarray): A 1D array (with a dtype of str) containing the lable name for each class
-        normalize (boolean): Flag to normalize the data 
+        normalize (boolean): Flag to normalize the data
         title (str): The title of the plot
         file_name (str): File name to export the graph
     Returns:
         None
     Raises:
         None
     """
-    # Normalize if wanted
     if normalize:
         cm = cm / np.sum(cm)
 
@@ -47,6 +45,4 @@ def plot_confusion_matrix(
         color_continuous_scale="Blues",
         title=title,
     )
-    # fig.show()
-    # Export graph
     fig.write_html("{}.html".format(file_name))

scripts/database.py → rr/experiment/database.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python
 import numpy as np
 import csv
 from sklearn.model_selection import train_test_split