python-clired 6.0.7__tar.gz → 6.0.9__tar.gz

{python-clired-6.0.7 → python_clired-6.0.9}/CHANGELOG

@@ -1,6 +1,15 @@
 CHANGELOG for Clired/Siren
 =============================
 
+v6.0.9
+------
+* Fixed command-line `exec_clired` entry point
+* Pushing edits to pypi release
+
+v6.0.8
+------
+* Renamed folders
+
 v6.0.7
 ------
 * Adding a command-line client

{python-clired-6.0.7 → python_clired-6.0.9}/MANIFEST.in

@@ -1,7 +1,6 @@
 include blocks/mine/*.py 
 include blocks/mine/*.xml
 include blocks/mine/*.xsl
-include blocks/mine/*.txt
 include blocks/mine/grako/*.py
 include blocks/work/*.py 
 include CHANGELOG

python_clired-6.0.9/PKG-INFO

@@ -0,0 +1,33 @@
+Metadata-Version: 2.2
+Name: python-clired
+Version: 6.0.9
+Summary: Command-line Redescription Mining
+Home-page: http://cs.uef.fi/siren/
+Author: Esther Galbrun and Pauli Miettinen
+Author-email: esther.galbrun@inria.fr
+License: Apache_2.0
+Classifier: Development Status :: 4 - Beta
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Scientific/Engineering
+Requires-Python: >=3
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: python-dateutil>=2.7.3
+Requires-Dist: shapely>=1.7.0
+Requires-Dist: numpy>=1.13.0
+Requires-Dist: scipy>=0.19.0
+Requires-Dist: scikit-learn>=0.19.0
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+This provides the Clired command-line tool for redescription mining including, in particular, the greedy ReReMi algorithm and tree-based algorithms. Once installed, Clired can be run by calling the command 'exec_clired'.

{python-clired-6.0.7 → python_clired-6.0.9}/README.md

@@ -8,7 +8,7 @@ Clired is a command-line tool for redescription mining.
 #### Dependencies
 `python-clired` requires several other Python utilities, including Numpy, Scipy and Scikit-learn.
 
-* python-dateutil (>= 2.8.1)
+* python-dateutil (>= 2.7.3)
 * shapely (>= 1.7.0)
 * numpy (>= 1.13.0)
 * scipy (>= 0.19.0)

{python-clired-6.0.7 → python_clired-6.0.9}/blocks/common_details.py

@@ -9,14 +9,14 @@ def getVersion():
         ctime = time.strftime("%a, %d %b %Y %T", time.localtime(os.path.getmtime(CHANGELOG_FILE)))
         with open(CHANGELOG_FILE) as fp:        
             for line in fp:
-                tmp = re.match("^v(?P<version>[0-9\.]*)$", line)
+                tmp = re.match(r"^v(?P<version>[0-9\.]*)$", line)
                 if tmp is not None:
                     if version is None:
                         version = tmp.group("version")
                     else:
                         return version, changes, ctime
-                elif version is not None and len(line.strip("[\n\*\- ]")) > 0:
-                    changes.append(line.strip("[\n\*\- ]"))
+                elif version is not None and len(line.strip("\n*- ")) > 0:
+                    changes.append(line.strip("\n*- "))
                     
     return "", [], time.strftime("%a, %d %b %Y %T", time.localtime())
 
@@ -38,7 +38,7 @@ home_eg = "https://members.loria.fr/EGalbrun/"
 web_siren = "http://cs.uef.fi/siren/"
 gitlab_siren = "https://gitlab.inria.fr/egalbrun/siren"
 
-dependencies_clired = [("python-dateutil", "python3-dateutil", "(>= 2.8.1)"),
+dependencies_clired = [("python-dateutil", "python3-dateutil", "(>= 2.7.3)"),
                 ("shapely", "python3-shapely", "(>= 1.7.0)"),
                 ("numpy", "python3-numpy", "(>= 1.13.0)"),
                 ("scipy", "python3-scipy", "(>= 0.19.0)"),

python_clired-6.0.9/blocks/mine/actions_rdefs_basic.xml

@@ -0,0 +1,196 @@
+<?xml version="1.0" encoding="utf-8"?>
+<root>
+  <actionlist>
+    <name>redundant</name>
+    <action what="filterPairs">
+      <reverse><cstr>redundancy_reverse</cstr></reverse>
+      <max>0</max>
+      <comparison>
+        <value type="pair">active:<cstr>redundancy_how</cstr>:<cstr>redundancy_which</cstr></value>
+        <operator><![CDATA[>]]></operator>
+        <value><cstr>redundancy_threshold</cstr></value>
+      </comparison>
+    </action>
+  </actionlist>
+  <actionlist>
+    <name>_nextge</name>
+    <action what="filterSingle">
+      <comparison>
+        <value type="item">:nbAvC:</value>
+        <operator><![CDATA[=]]></operator>
+        <value type="int">0</value>
+      </comparison>
+    </action>
+    <action what="sort" reverse="true">
+      <value type="item">:acc:</value>
+    </action>
+    <action what="cut">
+      <max><cstr>batch_cap</cstr></max>
+      <direction>0</direction>
+      <comparison><value type="item">:acc:</value></comparison>
+    </action>
+  </actionlist>
+  <actionlist>
+    <name>_tree_rectangles</name>
+    <action what="filterPairs">
+      <max>0</max>
+      <value type="pair">:sameRectangles:</value>
+    </action>
+  </actionlist>
+  <actionlist>
+    <name>_partial</name>
+    <action what="filterSingle" reverse="true">
+      <comparison>
+        <value type="item">:len:O</value>
+        <operator><![CDATA[>=]]></operator>
+        <value><cstr>min_itm_out</cstr></value>
+      </comparison>
+      <comparison>
+        <value type="item">:len:I</value>
+        <operator><![CDATA[>=]]></operator>
+        <value><cstr>min_itm_in</cstr></value>
+      </comparison>
+      <comparison>
+        <value type="item">:pval:</value>
+        <operator><![CDATA[<=]]></operator>
+        <value><cstr>max_fin_pval</cstr></value>
+      </comparison>
+    </action>
+    <action what="sort" reverse="true">
+      <value type="item">:acc:</value>
+      <value type="item" flip="true">BOTH:len:q</value>
+      <value type="item" flip="true">:diffLengthQs:</value>
+    </action>
+    <action what="filterPairs">
+      <max>0</max>
+      <value type="pair">:superceding:</value>
+    </action>
+    <action what="cut">
+      <max><cstr>batch_out</cstr></max>
+      <direction>1</direction>
+      <comparison><value type="item">:acc:</value></comparison>
+      <comparison><value type="item" flip="true">BOTH:len:q</value></comparison>
+      <comparison><value type="item" flip="true">:diffLengthQs:</value></comparison>
+    </action>
+  </actionlist>
+  <actionlist>
+    <name>_final</name>
+    <action what="filterSingle" reverse="true">
+      <comparison>
+        <value type="item">BOTH:len:q</value>
+        <operator><![CDATA[>=]]></operator>
+        <value><cstr>min_fin_var</cstr></value>
+      </comparison>
+      <comparison>
+        <value type="item">:len:O</value>
+        <operator><![CDATA[>=]]></operator>
+        <value><cstr>min_fin_out</cstr></value>
+      </comparison>
+      <comparison>
+        <value type="item">:len:I</value>
+        <operator><![CDATA[>=]]></operator>
+        <value><cstr>min_fin_in</cstr></value>
+      </comparison>
+      <comparison>
+        <value type="item">:acc:</value>
+        <operator><![CDATA[>=]]></operator>
+        <value><cstr>min_fin_acc</cstr></value>
+      </comparison>
+      <comparison>
+        <value type="item">:pval:</value>
+        <operator><![CDATA[<=]]></operator>
+        <value><cstr>max_fin_pval</cstr></value>
+      </comparison>
+    </action>
+    <action what="sort" reverse="true">
+      <value type="item">:acc:</value>
+      <value type="item" flip="true">BOTH:len:q</value>
+      <value type="item" flip="true">:diffLengthQs:</value>
+    </action>
+    <action what="filterPairs">
+      <max>0</max>
+      <value type="pair">:superceding:</value>
+    </action>
+  </actionlist>
+  <actionlist>
+    <name>_fim</name>
+    <action what="sort" reverse="true">
+      <value type="item" flip="true">:len:O</value>
+      <value type="item" flip="true">BOTH:len:q</value>
+    </action>
+  </actionlist>
+  <actionlist>
+    <name>_fimg</name>
+    <action what="filterSingle" reverse="true">
+      <comparison>
+        <value type="item">:len:O</value>
+        <operator><![CDATA[>=]]></operator>
+        <value><cstr>min_itm_out</cstr></value>
+      </comparison>
+      <comparison>
+        <value type="item">:len:I</value>
+        <operator><![CDATA[>=]]></operator>
+        <value><cstr>min_itm_in</cstr></value>
+      </comparison>
+      <comparison>
+        <value type="item">:pval:</value>
+        <operator><![CDATA[<=]]></operator>
+        <value><cstr>max_fin_pval</cstr></value>
+      </comparison>
+      <comparison>
+        <value type="item">BOTH:len:q</value>
+        <operator><![CDATA[>=]]></operator>
+        <value><cstr>min_fin_var</cstr></value>
+      </comparison>
+      <comparison>
+        <value type="item">:len:O</value>
+        <operator><![CDATA[>=]]></operator>
+        <value><cstr>min_fin_out</cstr></value>
+      </comparison>
+      <comparison>
+        <value type="item">:len:I</value>
+        <operator><![CDATA[>=]]></operator>
+        <value><cstr>min_fin_in</cstr></value>
+      </comparison>
+      <comparison>
+        <value type="item">:acc:</value>
+        <operator><![CDATA[>=]]></operator>
+        <value><cstr>min_fin_acc</cstr></value>
+      </comparison>
+      <comparison>
+        <value type="item">:pval:</value>
+        <operator><![CDATA[<=]]></operator>
+        <value><cstr>max_fin_pval</cstr></value>
+      </comparison>
+    </action>
+    <action what="sort" reverse="true">
+      <value type="item">:acc:</value>
+      <value type="item" flip="true">BOTH:len:q</value>
+      <value type="item" flip="true">:diffLengthQs:</value>
+    </action>
+  </actionlist>
+  <actionlist>
+    <name>final_selection</name>
+    <list><name>_final</name></list>
+  </actionlist>
+  <actionlist>
+    <name>partial_selection</name>
+    <list><name>_partial</name></list>
+  </actionlist>
+  <actionlist>
+    <name>prune</name>
+    <action what="applyBulk">
+      <function>getPruned</function>
+    </action>
+  </actionlist>
+  <actionlist>
+    <name>normalize</name>
+    <action what="applyBulk">
+      <function>getNormalized</function>
+    </action>
+  </actionlist>
+  <actionlist>
+    <name>_postprocess</name>
+    <list><name>_final</name></list>
+  </actionlist>
+</root>

python_clired-6.0.9/blocks/mine/bellman.py

@@ -0,0 +1,60 @@
+# -*- coding: utf-8 -*-
+
+import numpy as np
+from scipy import stats
+
+
+def bin_segments(V_,max_k,criterion):
+    V = stats.zscore(V_)
+    T,I,J = np.unique(V,return_index=True,return_inverse=True)
+    occurrences = np.histogram(J,max(J+1))
+    n = len(T)
+    cumocc = np.insert(np.cumsum(occurrences[0]),0,0)
+    cs = np.insert(np.cumsum(np.multiply(T,occurrences[0])),0,0)
+    css = np.insert(np.cumsum(np.multiply(np.power(T,2),occurrences[0])),0,0)
+    sigma = np.zeros((n,n))
+    for i in range(n):
+        for j in range(i+1,n):
+            sigma[i,j] = (css[j+1] - css[i]) - (1/(cumocc[j+1]-cumocc[i]))*np.power((cs[j+1]-cs[i]),2)   
+    E = np.zeros((max_k,n))
+    E[0,:] = sigma[0,:]
+    B = np.zeros((max_k,n))
+    cost = np.inf
+    for k in range(1,max_k):
+        for cutp in range(k,n):
+            E[k,cutp] = np.min(np.add(E[k-1,0:cutp],sigma[1:cutp+1,cutp]))
+            B[k,cutp] = int(np.argmin(np.add(E[k-1,0:cutp],sigma[1:cutp+1,cutp])))
+        if criterion == "manual":
+            c = E[k,n-1]
+        elif criterion == "BIC":
+            c = E[k,n-1] + k*np.log(len(V))
+        elif criterion == "AIC":
+            c = E[k,n-1] + 2*k
+        if c < cost:
+            opt_k = k
+            cost = c
+        else:
+            opt_k = k-1
+            break
+    B = B.astype(int)
+    cuts = [B[opt_k,n-1],n-1]
+    for j in range(opt_k-1,0,-1):
+        tmp = B[j,cuts[0]]
+        cuts = np.insert(cuts,0,tmp)
+    cuts = np.insert(np.unique(cuts),0,0)
+    buckets = np.zeros(n)
+    bounds = []
+    U = np.unique(V_)
+    for i in range(len(cuts)-1):
+        buckets[cuts[i]+1:cuts[i+1]+1] = i
+        bounds.append(U[cuts[i]+1]) 
+    bounds = bounds[1:]
+    assign = buckets[J]
+        
+    return assign, bounds, cost, opt_k
+        
+
+    
+    
+    
+