From f1adc193ca15e6aa3a7a1a3bf18abfa5e9239c89 Mon Sep 17 00:00:00 2001
From: dmt <>
Date: Fri, 18 Oct 2019 23:10:17 +0200
Subject: [PATCH] Rename scikit_adapter to ml_adapter.
---
cml/ports/ml_adapter.py | 165 ++++++++++++++++++++++++++++++++++++
cml/ports/scikit_adapter.py | 86 -------------------
2 files changed, 165 insertions(+), 86 deletions(-)
create mode 100644 cml/ports/ml_adapter.py
delete mode 100644 cml/ports/scikit_adapter.py
diff --git a/cml/ports/ml_adapter.py b/cml/ports/ml_adapter.py
new file mode 100644
index 0000000..6aa0474
--- /dev/null
+++ b/cml/ports/ml_adapter.py
@@ -0,0 +1,165 @@
+from collections import Counter
+from abc import ABCMeta, abstractmethod
+
+from numpy import array, linspace, less, greater, std, argsort
+from scipy.signal import argrelextrema
+import sklearn.cluster
+from sklearn.neighbors.kde import KernelDensity
+from keras.layers import Input, Dense
+from keras.models import Model
+from keras.regularizers import l1
+
+
+# TODO (dmt): Handle algorithms without cluster initialization!
+SCIKIT_CLUSTERING_TABLE = {
+ sklearn.cluster.KMeans: ("n_clusters", "labels_"),
+ sklearn.cluster.birch.Birch: ("n_clusters", "labels_"),
+ sklearn.cluster.SpectralClustering: ("n_clusters", "labels_"),
+ sklearn.cluster.FeatureAgglomeration: ("n_clusters", "labels_"),
+ sklearn.cluster.AgglomerativeClustering: ("n_clusters", "labels_")
+}
+
+
+class MachineLearningModel:
+
+ @abstractmethod
+ def train(self, data, *args, **kwargs):
+ pass
+
+
+class FilterMethod(MachineLearningModel):
+ def __init__(self, model):
+ self.__model = model
+
+ def train(self, data, *args, **kwargs):
+ self.__model = self.__model.fit(data)
+ return self
+
+ def reduce(self, data):
+ feature_count = data.feature_count
+ indices = set(self.__model.get_support(indices=True))
+ return {i for i in range(feature_count)}.difference(indices)
+
+
+class EmbeddedMethod(MachineLearningModel):
+ _ONE_HUNDRET_PERCENT = 100
+
+ def __init__(self, model):
+ self.__model = model
+
+ def train(self, data, *args, **kwargs):
+ labels = data.get_column_values("Z")
+ self.__model = self.__model.fit(data, labels)
+ return self
+
+ def reduce(self):
+ importance = self.__model.feature_importances_
+ indices = argsort(importance)[::-1]
+ if (self._ONE_HUNDRET_PERCENT*std(importance))//max(importance) >= 10:
+ less_relevant = indices[-1]
+ return {less_relevant}
+ return {}
+
+
+class ConstructionClusteringMLModel(MachineLearningModel):
+ def __init__(self, model):
+ self.__model = model
+ self._cluster = 2
+
+ def get_labels(self):
+ return self.__model.__getattribute__(
+ SCIKIT_CLUSTERING_TABLE[type(self.__model)][1]
+ )
+
+ @property
+ def cluster(self):
+ return self._cluster
+
+ @cluster.setter
+ def cluster(self, value):
+ self.__model.__setattr__(
+ SCIKIT_CLUSTERING_TABLE[type(self.__model)][0], value
+ )
+ self._cluster = value
+
+ @property
+ def cluster_sizes(self):
+ labels = self.__model.__getattribute__(
+ SCIKIT_CLUSTERING_TABLE[type(self.__model)][1]
+ )
+ return Counter(labels)
+
+ def train(self, data, *args, **kwargs):
+ self.__model.fit(data)
+ return self
+
+
+class KernelDensityEstimator(MachineLearningModel):
+
+ def __init__(self, kernel="gaussian", bandwidth=3, gridsize=256):
+ self.__model = None
+ self.kernel = kernel
+ self.bandwidth = bandwidth
+ self.gridsize = gridsize
+
+ def train(self, data, *args, **kwargs):
+ reshaped_data = array(data).reshape(-1, 1)
+ if not self.__model:
+ self.__model = KernelDensity(kernel=self.kernel,
+ bandwidth=self.bandwidth)
+
+ self.__model.fit(reshaped_data)
+ return self
+
+ def density(self):
+ grid = linspace(0, self.gridsize)
+ reshaped_grid = grid.reshape(-1, 1)
+ return self.__model.score_samples(reshaped_grid)
+
+
+class Autoencoder(MachineLearningModel):
+
+ def __init__(self):
+ self.io_shape = None
+ self.target_number = None
+ self.targets = None
+ self.__model = None
+ self.__hidden_outputter = None
+
+ def train(self, data, *args, **kwargs):
+ inputer = Input(shape=(self.io_shape, ))
+ hidden = Dense(units=self.target_number,
+ activation='relu',
+ activity_regularizer=l1(0.01))(inputer)
+ outputer = Dense(units=self.io_shape,
+ activation='linear')(hidden)
+
+ self.__model = Model(inputer, outputer)
+ self.__model.compile(optimizer='adadelta',
+ loss='mean_squared_error',
+ metrics=['accuracy'])
+ self.__hidden_outputter = Model(inputer, hidden)
+ self.__model.fit(data,
+ data,
+ epochs=100,
+ batch_size=2,
+ shuffle=False,
+ validation_data=(data, data),
+ verbose=0)
+ self._predict_targets(data)
+ return self
+
+ def _predict_targets(self, data):
+ predicts = self.__hidden_outputter.predict(data)
+ self.targets = [predicts[:, i]
+ for i in range(self.__model.layers[1].units)]
+
+ @property
+ def target_error(self):
+ return 1 - self.__model.history.history['accuracy'][-1]
+
+
+def find_relative_extrema(one_dim_data):
+ relative_min_values = argrelextrema(one_dim_data, less)
+ relative_max_values = argrelextrema(one_dim_data, greater)
+ return relative_min_values, relative_max_values
diff --git a/cml/ports/scikit_adapter.py b/cml/ports/scikit_adapter.py
deleted file mode 100644
index 789b6e0..0000000
--- a/cml/ports/scikit_adapter.py
+++ /dev/null
@@ -1,86 +0,0 @@
-from collections import Counter
-from abc import ABCMeta, abstractmethod
-
-import sklearn.cluster
-from numpy import array, linspace, less, greater
-from scipy.signal import argrelextrema
-from sklearn.neighbors.kde import KernelDensity
-
-
-# TODO (dmt): Handle algorithms without cluster initialization!
-SCIKIT_CLUSTERING_TABLE = {
- sklearn.cluster.KMeans: ("n_clusterss", "labels_"),
- sklearn.cluster.birch.Birch: ("n_clusters", "labels_"),
- sklearn.cluster.SpectralClustering: ("n_clusters", "labels_"),
- sklearn.cluster.FeatureAgglomeration: ("n_clusters", "labels_"),
- sklearn.cluster.AgglomerativeClustering: ("n_clusters", "labels_")
-}
-
-
-class MachineLearningModel:
-
- @abstractmethod
- def train(self, data):
- pass
-
-
-class ConstructionClusteringMLModel(MachineLearningModel):
- def __init__(self, model):
- self.__model = model
- self._cluster = 2
-
- def get_labels(self):
- return self.__model.__getattribute__(
- SCIKIT_CLUSTERING_TABLE[type(self.__model)][1]
- )
-
- @property
- def cluster(self):
- return self._cluster
-
- @cluster.setter
- def cluster(self, value):
- self.__model.__setattr__(
- SCIKIT_CLUSTERING_TABLE[type(self.__model)][0], value
- )
-
- @property
- def cluster_sizes(self):
- labels = self.__model.__getattribute__(
- SCIKIT_CLUSTERING_TABLE[type(self.__model)][1]
- )
- return Counter(labels)
-
- @abstractmethod
- def train(self, data):
- self.__model.fit(data)
- return self
-
-
-class KernelDensityEstimator(MachineLearningModel):
-
- def __init__(self, kernel="gaussian", bandwidth=3, gridsize=256):
- self.__model = None
- self.kernel = kernel
- self.bandwidth = bandwidth
- self.gridsize = gridsize
-
- def train(self, data):
- reshaped_data = array(data).reshape(-1, 1)
- if not self.__model:
- self.__model = KernelDensity(kernel=self.kernel,
- bandwidth=self.bandwidth)
-
- self.__model.fit(reshaped_data)
- return self
-
- def density(self):
- grid = linspace(0, self.gridsize)
- reshaped_grid = grid.reshape(-1, 1)
- return self.__model.score_samples(reshaped_grid)
-
-
-def find_relative_extrema(one_dim_data):
- relative_min_values = argrelextrema(one_dim_data, less)
- relative_max_values = argrelextrema(one_dim_data, greater)
- return relative_min_values, relative_max_values
--
GitLab