From d7b1104d1d067562066881972d54093364d8a933 Mon Sep 17 00:00:00 2001
From: Baptiste Bauvin <baptiste.bauvin@lis-lab.fr>
Date: Fri, 29 Nov 2019 10:33:27 -0500
Subject: [PATCH] Examples working in the python console
---
.gitignore | 2 +-
MANIFEST.in | 3 +-
README.md | 45 ++--
multiview_platform/examples/__init__.py | 0
.../config_files/config_example_1.yml | 239 ++++++++++++++++++
multiview_platform/execute.py | 8 +-
.../exec_classif.py | 22 +-
.../monoview/analyze_result.py | 8 +-
.../monoview/exec_classif_mono_view.py | 4 +-
.../monoview_classifiers/svm_linear.py | 3 +-
.../multiview/exec_multiview.py | 12 +-
.../multiview/multiview_utils.py | 2 +-
.../result_analysis.py | 4 +-
.../utils/execution.py | 16 +-
.../utils/get_multiview_db.py | 8 +-
.../test_ExecClassifMonoView.py | 2 +-
multiview_platform/versions.py | 158 ++++++------
requirements.txt | 2 +-
setup.py | 12 +-
19 files changed, 398 insertions(+), 152 deletions(-)
create mode 100644 multiview_platform/examples/__init__.py
create mode 100644 multiview_platform/examples/config_files/config_example_1.yml
diff --git a/.gitignore b/.gitignore
index 4d1a1ab0..a071ee73 100644
--- a/.gitignore
+++ b/.gitignore
@@ -15,4 +15,4 @@ dist*
docs/build*
multiview_platform/.idea/*
.gitignore
-
+multiview_platform/examples/results*
diff --git a/MANIFEST.in b/MANIFEST.in
index 91f371be..793057f9 100644
--- a/MANIFEST.in
+++ b/MANIFEST.in
@@ -1 +1,2 @@
-include *.md
\ No newline at end of file
+include *.md
+include multiview_platform/examples*
\ No newline at end of file
diff --git a/README.md b/README.md
index 55028c1a..59714299 100644
--- a/README.md
+++ b/README.md
@@ -10,47 +10,44 @@ This project aims to be an easy-to-use solution to run a prior benchmark on a da
To be able to use this project, you'll need :
-* [Python 2.7](https://docs.python.org/2/) or [Python 3](https://docs.python.org/3/)
+* [Python 3.6](https://docs.python.org/3/)
And the following python modules :
-* [pyscm](https://github.com/aldro61/pyscm) - Set Covering Machine, Marchand, M., & Taylor, J. S. (2003) by A.Drouin, F.Brochu, G.Letarte St-Pierre, M.Osseni, P-L.Plante
-* [numpy](http://www.numpy.org/), [scipy](https://scipy.org/)
-* [matplotlib](http://matplotlib.org/) - Used to plot results
-* [sklearn](http://scikit-learn.org/stable/) - Used for the monoview classifiers
-* [joblib](https://pypi.python.org/pypi/joblib) - Used to compute on multiple threads
-* [h5py](https://www.h5py.org) - Used to generate HDF5 datasets on hard drive and use them to spare RAM
-* [pickle](https://docs.python.org/3/library/pickle.html) - Used to store some results
-* ([graphviz](https://pypi.python.org/pypi/graphviz) - Used for decision tree interpretation)
-* [pandas](https://pandas.pydata.org/) -
+
+* [numpy](http://www.numpy.org/), [scipy](https://scipy.org/),
+* [matplotlib](http://matplotlib.org/) - Used to plot results,
+* [sklearn](http://scikit-learn.org/stable/) - Used for the monoview classifiers,
+* [joblib](https://pypi.python.org/pypi/joblib) - Used to compute on multiple threads,
+* [h5py](https://www.h5py.org) - Used to generate HDF5 datasets on hard drive and use them to spare RAM,
+* [pickle](https://docs.python.org/3/library/pickle.html) - Used to store some results,
+* [pandas](https://pandas.pydata.org/) - Used to manipulate data efficiently,
+* [six](https://pypi.org/project/six/) -
+* [m2r](https://pypi.org/project/m2r/) - Used to generate documentation from the readme,
+* [docutils](https://pypi.org/project/docutils/) - Used to generate documentation,
+* [pyyaml](https://pypi.org/project/PyYAML/) - Used to read the config files,
+* [plotly](https://plot.ly/) - Used to generate interactive HTML visuals.
They are all tested in `multiview-machine-mearning-omis/multiview_platform/MonoMutliViewClassifiers/Versions.py` which is automatically checked each time you run the `execute` script
### Installing
-cd in the project directory
-and install the project
+Once you cloned the project from this repository, you just have to use :
```
-cd multiview-machine-learning-omis
pip install -e .
```
+In the `multiview_machine-learning-omis` directory.
### Running on simulated data
In order to run it you'll need to try on **simulated** data with the command
+```python
+from multiview_platform.execute import execute
+execute()
```
-cd multiview-machine-learning-omis/multiview_platform
-python execute.py -log
-```
-Results will be stored in `multiview-machine-learning-omis/multiview_platform/mono_multi_view_classifiers/results/`
-
-If you want to run a multiclass (one versus one) benchmark on simulated data, use :
-```
-cd multiview-machine-learning-omis/multiview_platform
-python execute.py -log --CL_nbClass 3
-```
+Results will be stored in the results directory of the installation path : `path/to/install/multiview-machine-learning-omis/results`.
-If no path is specified, simulated hdf5 datasets are stored in `multiview-machine-learning-omis/data`
+And simulated hdf5 datasets are stored in `path/to/install/multiview-machine-learning-omis/data`
### Discovering the arguments
diff --git a/multiview_platform/examples/__init__.py b/multiview_platform/examples/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/multiview_platform/examples/config_files/config_example_1.yml b/multiview_platform/examples/config_files/config_example_1.yml
new file mode 100644
index 00000000..4604d09a
--- /dev/null
+++ b/multiview_platform/examples/config_files/config_example_1.yml
@@ -0,0 +1,239 @@
+# The base configuration of the benchmark
+Base :
+ # Enable logging
+ log: True
+ # The name of each dataset in the directory on which the benchmark should be run
+ name: ["plausible"]
+ # A label for the resul directory
+ label: "_"
+ # The type of dataset, currently supported ".hdf5", and ".csv"
+ type: ".hdf5"
+ # The views to use in the banchmark, an empty value will result in using all the views
+ views:
+ # The path to the directory where the datasets are stored
+ pathf: "examples/data/example_1/"
+ # The niceness of the processes, useful to lower their priority
+ nice: 0
+ # The random state of the benchmark, useful for reproducibility
+ random_state: 42
+ # The number of parallel computing threads
+ nb_cores: 1
+ # Used to run the benchmark on the full dataset
+ full: False
+ # Used to be able to run more than one benchmark per minute
+ debug: False
+ # To add noise to the data, will add gaussian noise with noise_std
+ add_noise: False
+ noise_std: 0.0
+ # The directory in which the results will be stored
+ res_dir: "examples/results/example_1/"
+
+# All the classification-realted configuration options
+Classification:
+ # If the dataset is multiclass, will use this multiclass-to-biclass method
+ multiclass_method: "oneVersusOne"
+ # The ratio number of test exmaples/number of train examples
+ split: 0.8
+ # The nubmer of folds in the cross validation process when hyper-paramter optimization is performed
+ nb_folds: 2
+ # The number of classes to select in the dataset
+ nb_class: 2
+ # The name of the classes to select in the dataset
+ classes:
+ # The type of algorithms to run during the benchmark (monoview and/or multiview)
+ type: ["monoview","multiview"]
+ # The name of the monoview algorithms to run, ["all"] to run all the available classifiers
+ algos_monoview: ["all"]
+ # The names of the multiview algorithms to run, ["all"] to run all the available classifiers
+ algos_multiview: ["all"]
+ # The number of times the benchamrk is repeated with different train/test
+ # split, to have more statistically significant results
+ stats_iter: 1
+ # The metrics that will be use din the result analysis
+ metrics: ["accuracy_score", "f1_score"]
+ # The metric that will be used in the hyper-parameter optimization process
+ metric_princ: "f1_score"
+ # The type of hyper-parameter optimization method
+ hps_type: "randomized_search"
+ # The number of iteration in the hyper-parameter optimization process
+ hps_iter: 2
+
+
+# The following arguments are classifier-specific, and are documented in each
+# of the corresponding modules.
+
+# In order to run multiple sets of parameters, use multiple values in the
+# following lists, and set hps_type to None.
+
+#####################################
+# The Monoview Classifier arguments #
+#####################################
+
+
+random_forest:
+ n_estimators: [25]
+ max_depth: [3]
+ criterion: ["entropy"]
+
+svm_linear:
+ C: [1]
+
+svm_rbf:
+ C: [1]
+
+svm_poly:
+ C: [1]
+ degree: [2]
+
+adaboost:
+ n_estimators: [50]
+ base_estimator: ["DecisionTreeClassifier"]
+
+adaboost_pregen:
+ n_estimators: [50]
+ base_estimator: ["DecisionTreeClassifier"]
+ n_stumps: [1]
+
+adaboost_graalpy:
+ n_iterations: [50]
+ n_stumps: [1]
+
+decision_tree:
+ max_depth: [10]
+ criterion: ["gini"]
+ splitter: ["best"]
+
+decision_tree_pregen:
+ max_depth: [10]
+ criterion: ["gini"]
+ splitter: ["best"]
+ n_stumps: [1]
+
+sgd:
+ loss: ["hinge"]
+ penalty: [l2]
+ alpha: [0.0001]
+
+knn:
+ n_neighbors: [5]
+ weights: ["uniform"]
+ algorithm: ["auto"]
+
+scm:
+ model_type: ["conjunction"]
+ max_rules: [10]
+ p: [0.1]
+
+scm_pregen:
+ model_type: ["conjunction"]
+ max_rules: [10]
+ p: [0.1]
+ n_stumps: [1]
+
+cq_boost:
+ mu: [0.01]
+ epsilon: [1e-06]
+ n_max_iterations: [5]
+ n_stumps: [1]
+
+cg_desc:
+ n_max_iterations: [10]
+ n_stumps: [1]
+
+cb_boost:
+ n_max_iterations: [10]
+ n_stumps: [1]
+
+lasso:
+ alpha: [1]
+ max_iter: [2]
+
+gradient_boosting:
+ n_estimators: [2]
+
+
+######################################
+# The Multiview Classifier arguments #
+######################################
+
+weighted_linear_early_fusion:
+ view_weights: [null]
+ monoview_classifier_name: ["decision_tree"]
+ monoview_classifier_config:
+ decision_tree:
+ max_depth: [1]
+ criterion: ["gini"]
+ splitter: ["best"]
+
+entropy_fusion:
+ classifier_names: [["decision_tree"]]
+ classifier_configs:
+ decision_tree:
+ max_depth: [1]
+ criterion: ["gini"]
+ splitter: ["best"]
+
+disagree_fusion:
+ classifier_names: [["decision_tree"]]
+ classifier_configs:
+ decision_tree:
+ max_depth: [1]
+ criterion: ["gini"]
+ splitter: ["best"]
+
+
+double_fault_fusion:
+ classifier_names: [["decision_tree"]]
+ classifier_configs:
+ decision_tree:
+ max_depth: [1]
+ criterion: ["gini"]
+ splitter: ["best"]
+
+difficulty_fusion:
+ classifier_names: [["decision_tree"]]
+ classifier_configs:
+ decision_tree:
+ max_depth: [1]
+ criterion: ["gini"]
+ splitter: ["best"]
+
+scm_late_fusion:
+ classifier_names: [["decision_tree"]]
+ p: 0.1
+ max_rules: 10
+ model_type: 'conjunction'
+ classifier_configs:
+ decision_tree:
+ max_depth: [1]
+ criterion: ["gini"]
+ splitter: ["best"]
+
+majority_voting_fusion:
+ classifier_names: [["decision_tree", "decision_tree", "decision_tree", ]]
+ classifier_configs:
+ decision_tree:
+ max_depth: [1]
+ criterion: ["gini"]
+ splitter: ["best"]
+
+bayesian_inference_fusion:
+ classifier_names: [["decision_tree", "decision_tree", "decision_tree", ]]
+ classifier_configs:
+ decision_tree:
+ max_depth: [1]
+ criterion: ["gini"]
+ splitter: ["best"]
+
+weighted_linear_late_fusion:
+ classifier_names: [["decision_tree", "decision_tree", "decision_tree", ]]
+ classifier_configs:
+ decision_tree:
+ max_depth: [1]
+ criterion: ["gini"]
+ splitter: ["best"]
+
+mumbo:
+ base_estimator: [null]
+ n_estimators: [10]
+ best_view_mode: ["edge"]
\ No newline at end of file
diff --git a/multiview_platform/execute.py b/multiview_platform/execute.py
index c4afa957..a23c64f2 100644
--- a/multiview_platform/execute.py
+++ b/multiview_platform/execute.py
@@ -1,13 +1,17 @@
"""This is the execution module, used to execute the code"""
+import os
-def execute():
+def execute(config_path=os.path.join(os.path.dirname(os.path.realpath(__file__)), "examples", "config_files", "config_example_1.yml")):
from multiview_platform import versions as vs
vs.test_versions()
import sys
from multiview_platform.mono_multi_view_classifiers import exec_classif
- exec_classif.exec_classif(sys.argv[1:])
+ if sys.argv[1:]:
+ exec_classif.exec_classif(sys.argv[1:])
+ else:
+ exec_classif.exec_classif(["--config_path", config_path])
if __name__ == "__main__":
diff --git a/multiview_platform/mono_multi_view_classifiers/exec_classif.py b/multiview_platform/mono_multi_view_classifiers/exec_classif.py
index e5a66352..3eb92a7f 100644
--- a/multiview_platform/mono_multi_view_classifiers/exec_classif.py
+++ b/multiview_platform/mono_multi_view_classifiers/exec_classif.py
@@ -62,8 +62,7 @@ def init_benchmark(cl_type, monoview_algos, multiview_algos, args):
if "monoview" in cl_type:
if monoview_algos == ['all']:
benchmark["monoview"] = [name for _, name, isPackage in
- pkgutil.iter_modules([
- "./mono_multi_view_classifiers/monoview_classifiers"])
+ pkgutil.iter_modules(monoview_classifiers.__path__)
if not isPackage]
else:
@@ -72,8 +71,7 @@ def init_benchmark(cl_type, monoview_algos, multiview_algos, args):
if "multiview" in cl_type:
if multiview_algos==["all"]:
benchmark["multiview"] = [name for _, name, isPackage in
- pkgutil.iter_modules([
- "./mono_multi_view_classifiers/multiview_classifiers"])
+ pkgutil.iter_modules(multiview_classifiers.__path__)
if not isPackage]
else:
benchmark["multiview"] = multiview_algos
@@ -500,23 +498,23 @@ def benchmark_init(directory, classification_indices, labels, labels_dictionary,
"""
logging.debug("Start:\t Benchmark initialization")
- if not os.path.exists(os.path.dirname(directory + "train_labels.csv")):
+ if not os.path.exists(os.path.dirname(os.path.join(directory, "train_labels.csv"))):
try:
- os.makedirs(os.path.dirname(directory + "train_labels.csv"))
+ os.makedirs(os.path.dirname(os.path.join(directory, "train_labels.csv")))
except OSError as exc:
if exc.errno != errno.EEXIST:
raise
train_indices = classification_indices[0]
train_labels = labels[train_indices]
- np.savetxt(directory + "train_labels.csv", train_labels, delimiter=",")
- np.savetxt(directory + "train_indices.csv", classification_indices[0],
+ np.savetxt(os.path.join(directory, "train_labels.csv"), train_labels, delimiter=",")
+ np.savetxt(os.path.join(directory, "train_indices.csv"), classification_indices[0],
delimiter=",")
results_monoview = []
folds = k_folds.split(np.arange(len(train_labels)), train_labels)
min_fold_len = int(len(train_labels) / k_folds.n_splits)
for fold_index, (train_cv_indices, test_cv_indices) in enumerate(folds):
- file_name = directory + "/folds/test_labels_fold_" + str(
- fold_index) + ".csv"
+ file_name = os.path.join(directory, "folds", "test_labels_fold_" + str(
+ fold_index) + ".csv")
if not os.path.exists(os.path.dirname(file_name)):
try:
os.makedirs(os.path.dirname(file_name))
@@ -784,7 +782,7 @@ def exec_classif(arguments):
"""Main function to execute the benchmark"""
start = time.time()
args = execution.parse_the_args(arguments)
- args = configuration.get_the_args(args.path_config)
+ args = configuration.get_the_args(args.config_path)
os.nice(args["Base"]["nice"])
nb_cores = args["Base"]["nb_cores"]
if nb_cores == 1:
@@ -845,7 +843,7 @@ def exec_classif(arguments):
if metrics == [["all"]]:
metrics_names = [name for _, name, isPackage
in pkgutil.iter_modules(
- ['./mono_multi_view_classifiers/metrics']) if
+ [os.path.join(os.path.dirname(os.path.dirname(os.path.realpath(__file__))), 'metrics')]) if
not isPackage and name not in ["framework", "log_loss",
"matthews_corrcoef",
"roc_auc_score"]]
diff --git a/multiview_platform/mono_multi_view_classifiers/monoview/analyze_result.py b/multiview_platform/mono_multi_view_classifiers/monoview/analyze_result.py
index faecdbc2..e5d00b67 100644
--- a/multiview_platform/mono_multi_view_classifiers/monoview/analyze_result.py
+++ b/multiview_platform/mono_multi_view_classifiers/monoview/analyze_result.py
@@ -34,7 +34,7 @@ def getDBConfigString(name, feat, classification_indices, shape,
def getClassifierConfigString(gridSearch, nbCores, nIter, clKWARGS, classifier,
- directory, y_test):
+ output_file_name, y_test):
classifierConfigString = "Classifier configuration : \n"
classifierConfigString += "\t- " + classifier.getConfig()[5:] + "\n"
classifierConfigString += "\t- Executed on " + str(nbCores) + " core(s) \n"
@@ -42,7 +42,7 @@ def getClassifierConfigString(gridSearch, nbCores, nIter, clKWARGS, classifier,
classifierConfigString += "\t- Got configuration using randomized search with " + str(
nIter) + " iterations \n"
classifierConfigString += "\n\n"
- classifierInterpretString = classifier.getInterpret(directory, y_test)
+ classifierInterpretString = classifier.getInterpret(output_file_name, y_test)
return classifierConfigString, classifierInterpretString
@@ -66,7 +66,7 @@ def getMetricScore(metric, y_train, y_train_pred, y_test, y_test_pred):
def execute(name, learningRate, KFolds, nbCores, gridSearch, metrics_list, nIter,
feat, CL_type, clKWARGS, classLabelsNames,
shape, y_train, y_train_pred, y_test, y_test_pred, time,
- random_state, classifier, directory):
+ random_state, classifier, output_file_name):
metricsScores = {}
metricModule = getattr(metrics, metrics_list[0][0])
trainScore = metricModule.score(y_train, y_train_pred)
@@ -78,7 +78,7 @@ def execute(name, learningRate, KFolds, nbCores, gridSearch, metrics_list, nIter
stringAnalysis += getDBConfigString(name, feat, learningRate, shape,
classLabelsNames, KFolds)
classifierConfigString, classifierIntepretString = getClassifierConfigString(
- gridSearch, nbCores, nIter, clKWARGS, classifier, directory, y_test)
+ gridSearch, nbCores, nIter, clKWARGS, classifier, output_file_name, y_test)
stringAnalysis += classifierConfigString
for metric in metrics_list:
metricString, metricScore = getMetricScore(metric, y_train,
diff --git a/multiview_platform/mono_multi_view_classifiers/monoview/exec_classif_mono_view.py b/multiview_platform/mono_multi_view_classifiers/monoview/exec_classif_mono_view.py
index 8e6584ef..9b5490f2 100644
--- a/multiview_platform/mono_multi_view_classifiers/monoview/exec_classif_mono_view.py
+++ b/multiview_platform/mono_multi_view_classifiers/monoview/exec_classif_mono_view.py
@@ -154,9 +154,9 @@ def initConstants(args, X, classificationIndices, labels_names,
labelsString = "-".join(labels_names)
CL_type_string = CL_type
timestr = time.strftime("%Y_%m_%d-%H_%M_%S")
- outputFileName = directory + CL_type_string + "/" + view_name + "/" + timestr + "-results-" + CL_type_string + "-" + labelsString + \
+ outputFileName = os.path.join(directory, CL_type_string, view_name, timestr + "-results-" + CL_type_string + "-" + labelsString + \
'-learnRate_{0:.2f}'.format(
- learningRate) + '-' + name + "-" + view_name + "-"
+ learningRate) + '-' + name + "-" + view_name + "-")
if not os.path.exists(os.path.dirname(outputFileName)):
try:
os.makedirs(os.path.dirname(outputFileName))
diff --git a/multiview_platform/mono_multi_view_classifiers/monoview_classifiers/svm_linear.py b/multiview_platform/mono_multi_view_classifiers/monoview_classifiers/svm_linear.py
index ad867f07..47c983c7 100644
--- a/multiview_platform/mono_multi_view_classifiers/monoview_classifiers/svm_linear.py
+++ b/multiview_platform/mono_multi_view_classifiers/monoview_classifiers/svm_linear.py
@@ -1,3 +1,5 @@
+import numpy as np
+
from multiview_platform.mono_multi_view_classifiers.monoview_classifiers.additions.SVCClassifier import SVCClassifier
from ..monoview.monoview_utils import CustomUniform, BaseMonoviewClassifier
@@ -36,7 +38,6 @@ class SVMLinear(SVCClassifier, BaseMonoviewClassifier):
def getInterpret(self, directory, y_test):
interpret_string = ""
- import numpy as np
self.feature_importances_ = (self.coef_/np.sum(self.coef_)).reshape((self.coef_.shape[1],))
return interpret_string
diff --git a/multiview_platform/mono_multi_view_classifiers/multiview/exec_multiview.py b/multiview_platform/mono_multi_view_classifiers/multiview/exec_multiview.py
index 761a970d..7c2d3944 100644
--- a/multiview_platform/mono_multi_view_classifiers/multiview/exec_multiview.py
+++ b/multiview_platform/mono_multi_view_classifiers/multiview/exec_multiview.py
@@ -102,9 +102,9 @@ def save_results(classifier, labels_dictionary, string_analysis, views, classifi
labels_string = "-".join(labels_set)
timestr = time.strftime("%Y_%m_%d-%H_%M_%S")
cl_type_string = classifier.short_name
- output_file_name = directory + "/" + cl_type_string + "/" + timestr + \
- "-results-" + cl_type_string + "-" + views_string + '-' + labels_string + \
- '-learnRate_{0:.2f}'.format(learning_rate) + '-' + name
+ output_file_name = os.path.join(directory, cl_type_string,
+ timestr + "-results-" + cl_type_string + "-" + views_string + '-' + labels_string + \
+ '-learnRate_{0:.2f}'.format(learning_rate) + '-' + name)
if not os.path.exists(os.path.dirname(output_file_name)):
try:
os.makedirs(os.path.dirname(output_file_name))
@@ -400,12 +400,12 @@ if __name__ == "__main__":
logfilename = "gen a good logfilename"
- logfile = directory + logfilename
+ logfile = os.path.join(directory, logfilename)
if os.path.isfile(logfile + ".log"):
for i in range(1, 20):
testFileName = logfilename + "-" + str(i) + ".log"
- if not os.path.isfile(directory + testFileName):
- logfile = directory + testFileName
+ if not os.path.isfile(os.path.join(directory, testFileName)):
+ logfile = os.path.join(directory, testFileName)
break
else:
logfile += ".log"
diff --git a/multiview_platform/mono_multi_view_classifiers/multiview/multiview_utils.py b/multiview_platform/mono_multi_view_classifiers/multiview/multiview_utils.py
index fcc0ec1a..5fe42d49 100644
--- a/multiview_platform/mono_multi_view_classifiers/multiview/multiview_utils.py
+++ b/multiview_platform/mono_multi_view_classifiers/multiview/multiview_utils.py
@@ -44,7 +44,7 @@ class BaseMultiviewClassifier(BaseEstimator, ClassifierMixin):
def __init__(self, random_state):
self.random_state = random_state
- self.short_name = self.__class__.__name__
+ self.short_name = self.__module__.split(".")[-1]
self.weird_strings = {}
def gen_best_params(self, detector):
diff --git a/multiview_platform/mono_multi_view_classifiers/result_analysis.py b/multiview_platform/mono_multi_view_classifiers/result_analysis.py
index 02514a8a..1dfd5460 100644
--- a/multiview_platform/mono_multi_view_classifiers/result_analysis.py
+++ b/multiview_platform/mono_multi_view_classifiers/result_analysis.py
@@ -58,9 +58,9 @@ def plot_results_noise(directory, noise_results, metric_to_plot, name, width=0.1
plt.title(name)
plt.xticks(noise_levels)
plt.xlabel("Noise level")
- plt.savefig(directory+name+"_noise_analysis.png")
+ plt.savefig(os.path.join(directory, name+"_noise_analysis.png"))
plt.close()
- df.to_csv(directory+name+"_noise_analysis.csv")
+ df.to_csv(os.path.join(directory, name+"_noise_analysis.csv"))
def plot_metric_scores(train_scores, test_scores, names, nb_results, metric_name,
diff --git a/multiview_platform/mono_multi_view_classifiers/utils/execution.py b/multiview_platform/mono_multi_view_classifiers/utils/execution.py
index 8bec9645..649dfd29 100644
--- a/multiview_platform/mono_multi_view_classifiers/utils/execution.py
+++ b/multiview_platform/mono_multi_view_classifiers/utils/execution.py
@@ -21,7 +21,7 @@ def parse_the_args(arguments):
fromfile_prefix_chars='@')
groupStandard = parser.add_argument_group('Standard arguments')
- groupStandard.add_argument('--path_config', metavar='STRING', action='store',
+ groupStandard.add_argument('--config_path', metavar='STRING', action='store',
help='Path to the hdf5 dataset or database '
'folder (default: %(default)s)',
default='../config_files/config.yml')
@@ -53,6 +53,7 @@ def init_random_state(random_state_arg, directory):
random_state : numpy.random.RandomState object
This random state will be used all along the benchmark .
"""
+
if random_state_arg is None:
random_state = np.random.RandomState(random_state_arg)
else:
@@ -63,7 +64,7 @@ def init_random_state(random_state_arg, directory):
file_name = random_state_arg
with open(file_name, 'rb') as handle:
random_state = pickle.load(handle)
- with open(directory + "random_state.pickle", "wb") as handle:
+ with open(os.path.join(directory, "random_state.pickle"), "wb") as handle:
pickle.dump(random_state, handle)
return random_state
@@ -152,6 +153,7 @@ def init_log_file(name, views, cl_type, log, debug, label,
if views is None:
views=[]
noise_string = "n_"+str(int(noise_std*100))
+ result_directory = os.path.join(os.path.dirname(os.path.dirname(os.path.dirname(os.path.realpath(__file__)))), result_directory)
if debug:
result_directory = os.path.join(result_directory, name, noise_string,
"debug_started_" + time.strftime("%Y_%m_%d-%H_%M_%S") + "_" + label)
@@ -299,7 +301,7 @@ def gen_direcorties_names(directory, stats_iter):
if stats_iter > 1:
directories = []
for i in range(stats_iter):
- directories.append(directory + "iter_" + str(i + 1) + "/")
+ directories.append(os.path.join(directory, "iter_" + str(i + 1)))
else:
directories = [directory]
return directories
@@ -308,9 +310,9 @@ def gen_direcorties_names(directory, stats_iter):
def find_dataset_names(path, type, names):
"""This function goal is to browse the dataset directory and extrats all
the needed dataset names."""
-
+ module_path = os.path.dirname(os.path.dirname(os.path.dirname(os.path.realpath(__file__))))
available_file_names = [file_name.strip().split(".")[0]
- for file_name in os.listdir(path)
+ for file_name in os.listdir(os.path.join(module_path, path))
if file_name.endswith(type)]
if names == ["all"]:
return available_file_names
@@ -379,10 +381,10 @@ def gen_argument_dictionaries(labels_dictionary, directories, multiclass_labels,
"labels_dictionary": {0: labels_dictionary[labels_combination[0]],
1: labels_dictionary[
labels_combination[1]]},
- "directory": directories[iter_index] +
+ "directory": os.path.join(directories[iter_index],
labels_dictionary[labels_combination[0]] +
"-vs-" +
- labels_dictionary[labels_combination[1]] + "/",
+ labels_dictionary[labels_combination[1]]),
"classification_indices": [
indices_multiclass[combination_index][0][iter_index],
indices_multiclass[combination_index][1][iter_index],
diff --git a/multiview_platform/mono_multi_view_classifiers/utils/get_multiview_db.py b/multiview_platform/mono_multi_view_classifiers/utils/get_multiview_db.py
index 11e7bd3b..5d9c9602 100644
--- a/multiview_platform/mono_multi_view_classifiers/utils/get_multiview_db.py
+++ b/multiview_platform/mono_multi_view_classifiers/utils/get_multiview_db.py
@@ -38,9 +38,9 @@ def get_plausible_db_hdf5(features, path, file_name, nb_class=3,
nb_features=10):
"""Used to generate a plausible dataset to test the algorithms"""
- if not os.path.exists(os.path.dirname(path + "plausible.hdf5")):
+ if not os.path.exists(os.path.dirname(os.path.join(path, "plausible.hdf5"))):
try:
- os.makedirs(os.path.dirname(path + "plausible.hdf5"))
+ os.makedirs(os.path.dirname(os.path.join(path, "plausible.hdf5")))
except OSError as exc:
if exc.errno != errno.EEXIST:
raise
@@ -133,14 +133,14 @@ def get_classic_db_hdf5(views, path_f, name_DB, nb_class, asked_labels_names,
path_for_new="../data/"):
"""Used to load a hdf5 database"""
if full:
- dataset_file = h5py.File(path_f + name_DB + ".hdf5", "r")
+ dataset_file = h5py.File(os.path.join(path_f, name_DB + ".hdf5"), "r")
dataset = Dataset(hdf5_file=dataset_file)
dataset_name = name_DB
labels_dictionary = dict((label_index, label_name)
for label_index, label_name
in enumerate(dataset.get_label_names()))
else:
- dataset_file = h5py.File(path_f + name_DB + ".hdf5", "r")
+ dataset_file = h5py.File(os.path.join(path_f, name_DB + ".hdf5"), "r")
dataset = Dataset(hdf5_file=dataset_file)
labels_dictionary = dataset.select_views_and_labels(nb_labels=nb_class,
selected_label_names=asked_labels_names,
diff --git a/multiview_platform/tests/test_mono_view/test_ExecClassifMonoView.py b/multiview_platform/tests/test_mono_view/test_ExecClassifMonoView.py
index 8b245793..f540dab6 100644
--- a/multiview_platform/tests/test_mono_view/test_ExecClassifMonoView.py
+++ b/multiview_platform/tests/test_mono_view/test_ExecClassifMonoView.py
@@ -31,7 +31,7 @@ class Test_initConstants(unittest.TestCase):
np.array([1, 3, 5, 7, 9])]
cls.labels_names = ["test_true", "test_false"]
cls.name = "test"
- cls.directory = tmp_path+"test_dir/"
+ cls.directory = os.path.join(tmp_path, "test_dir/")
def test_simple(cls):
kwargs, \
diff --git a/multiview_platform/versions.py b/multiview_platform/versions.py
index 23661197..b60d9854 100644
--- a/multiview_platform/versions.py
+++ b/multiview_platform/versions.py
@@ -8,88 +8,88 @@ def test_versions():
is_up_to_date = True
to_install = []
- try:
- import sys
- except ImportError:
- raise
-
- try:
- import cvxopt
- except ImportError:
- is_up_to_date = False
- to_install.append("cvxopt")
-
- try:
- import pyscm
- except ImportError:
- is_up_to_date = False
- to_install.append("pyscm")
-
- try:
- import numpy
- except ImportError:
- is_up_to_date = False
- to_install.append("numpy")
-
- try:
- import scipy
- except ImportError:
- is_up_to_date = False
- to_install.append("scipy")
-
- try:
- import matplotlib
- except ImportError:
- is_up_to_date = False
- to_install.append("matplotlib")
-
- try:
- import sklearn
- except ImportError:
- is_up_to_date = False
- to_install.append("sklearn")
-
- try:
- import logging
- except ImportError:
- is_up_to_date = False
- to_install.append("logging")
-
- try:
- import joblib
- except ImportError:
- is_up_to_date = False
- to_install.append("joblib")
-
- try:
- import argparse
- except ImportError:
- is_up_to_date = False
- to_install.append("argparse")
-
- try:
- import h5py #
- except ImportError:
- is_up_to_date = False
- to_install.append("h5py")
-
# try:
- # import graphviz #
+ # import sys
+ # except ImportError:
+ # raise
+ #
+ # try:
+ # import cvxopt
# except ImportError:
# is_up_to_date = False
- # to_install.append("graphviz")
-
- try:
- import pickle #
- except ImportError:
- is_up_to_date = False
- to_install.append("pickle")
-
- if not is_up_to_date:
- print(
- "You can't run at the moment, please install the following modules : \n" + "\n".join(
- to_install))
- quit()
+ # to_install.append("cvxopt")
+ #
+ # try:
+ # import pyscm
+ # except ImportError:
+ # is_up_to_date = False
+ # to_install.append("pyscm")
+ #
+ # try:
+ # import numpy
+ # except ImportError:
+ # is_up_to_date = False
+ # to_install.append("numpy")
+ #
+ # try:
+ # import scipy
+ # except ImportError:
+ # is_up_to_date = False
+ # to_install.append("scipy")
+ #
+ # try:
+ # import matplotlib
+ # except ImportError:
+ # is_up_to_date = False
+ # to_install.append("matplotlib")
+ #
+ # try:
+ # import sklearn
+ # except ImportError:
+ # is_up_to_date = False
+ # to_install.append("sklearn")
+ #
+ # try:
+ # import logging
+ # except ImportError:
+ # is_up_to_date = False
+ # to_install.append("logging")
+ #
+ # try:
+ # import joblib
+ # except ImportError:
+ # is_up_to_date = False
+ # to_install.append("joblib")
+ #
+ # try:
+ # import argparse
+ # except ImportError:
+ # is_up_to_date = False
+ # to_install.append("argparse")
+ #
+ # try:
+ # import h5py #
+ # except ImportError:
+ # is_up_to_date = False
+ # to_install.append("h5py")
+ #
+ # # try:
+ # # import graphviz #
+ # # except ImportError:
+ # # is_up_to_date = False
+ # # to_install.append("graphviz")
+ #
+ # try:
+ # import pickle #
+ # except ImportError:
+ # is_up_to_date = False
+ # to_install.append("pickle")
+ #
+ # if not is_up_to_date:
+ # print(
+ # "You can't run at the moment, please install the following modules : \n" + "\n".join(
+ # to_install))
+ # quit()
if __name__ == "__main__":
diff --git a/requirements.txt b/requirements.txt
index 9802205d..940b0782 100755
--- a/requirements.txt
+++ b/requirements.txt
@@ -5,7 +5,6 @@ joblib==0.13.2
kiwisolver==1.1.0
numpy==1.16.4
pyparsing==2.4.0
--e git+https://github.com/aldro61/pyscm.git#egg=pyscm
python-dateutil==2.8.0
scikit-learn==0.19.0
scipy==1.3.0
@@ -16,3 +15,4 @@ docutils==0.12
pyyaml==3.12
cvxopt==1.2.0
plotly==4.2.1
+matplotlib==3.1.1
diff --git a/setup.py b/setup.py
index 885aa563..3a952d19 100644
--- a/setup.py
+++ b/setup.py
@@ -1,4 +1,7 @@
# -*- coding: utf-8 -*-
+#Extracting requrements from requirements.txt
+with open('requirements.txt') as f:
+ requirements = f.read().splitlines()
# from Cython.Build import cythonize
from setuptools import setup, find_packages
@@ -52,10 +55,11 @@ def setup_package():
# dependency_links=['https://github.com/aldro61/pyscm.git#egg=pyscm'],
# Une url qui pointe vers la page officielle de votre lib
url='http://github.com/babau1/multiview-machine-learning-omis/',
- install_requires=['numpy>=1.16', 'scipy>=0.16','scikit-learn==0.19',
- 'matplotlib', 'h5py', 'joblib',
- 'pandas', 'm2r', 'pyyaml', 'pyscm @ git+https://github.com/aldro61/pyscm',
- 'cvxopt', 'plotly==4.2.1'],
+ install_requires=requirements,
+ # install_requires=['numpy>=1.16', 'scipy>=0.16','scikit-learn==0.19',
+ # 'matplotlib', 'h5py', 'joblib',
+ # 'pandas', 'm2r', 'pyyaml', 'pyscm @ git+https://github.com/aldro61/pyscm',
+ # 'cvxopt', 'plotly==4.2.1'],
# Il est d'usage de mettre quelques metadata à propos de sa lib
# Pour que les robots puissent facilement la classer.
--
GitLab