From d50a86daf4601f59c727276a89526364476cb519 Mon Sep 17 00:00:00 2001
From: Alex Moreo <alejandro.moreo@isti.cnr.it>
Date: Fri, 16 Feb 2024 17:34:10 +0100
Subject: [PATCH] sketching readme system by Lu and King, Hopings and King

---
 CHANGE_LOG.txt                  |  6 +++++
 quapy/__init__.py               |  2 +-
 quapy/method/non_aggregative.py | 48 +++++++++++++++++++++++++++++++++
 3 files changed, 55 insertions(+), 1 deletion(-)

diff --git a/CHANGE_LOG.txt b/CHANGE_LOG.txt
index 5bf2643..7af3340 100644
--- a/CHANGE_LOG.txt
+++ b/CHANGE_LOG.txt
@@ -1,3 +1,9 @@
+Change Log 0.1.9
+----------------
+
+<...>
+
+
 Change Log 0.1.8
 ----------------
 
diff --git a/quapy/__init__.py b/quapy/__init__.py
index da534df..8e4ceb2 100644
--- a/quapy/__init__.py
+++ b/quapy/__init__.py
@@ -11,7 +11,7 @@ from . import util
 from . import model_selection
 from . import classification
 
-__version__ = '0.1.8'
+__version__ = '0.1.9'
 
 environ = {
     'SAMPLE_SIZE': None,
diff --git a/quapy/method/non_aggregative.py b/quapy/method/non_aggregative.py
index 6048bf6..02f133b 100644
--- a/quapy/method/non_aggregative.py
+++ b/quapy/method/non_aggregative.py
@@ -1,5 +1,6 @@
 from typing import Union, Callable
 import numpy as np
+from sklearn.feature_extraction.text import CountVectorizer
 
 from quapy.functional import get_divergence
 from quapy.data import LabelledCollection
@@ -146,6 +147,53 @@ class DMx(BaseQuantifier):
         return F.argmin_prevalence(loss, n_classes, method=self.search)
 
 
+class ReadMe(BaseQuantifier):
+
+    def __init__(self, bootstrap_trials=100, bootstrap_range=100, bagging_trials=100, bagging_range=25, **vectorizer_kwargs):
+        self.bootstrap_trials = bootstrap_trials
+        self.bootstrap_range = bootstrap_range
+        self.bagging_trials = bagging_trials
+        self.bagging_range = bagging_range
+        self.vectorizer_kwargs = vectorizer_kwargs
+
+    def fit(self, data: LabelledCollection):
+        X, y = data.Xy
+        self.vectorizer = CountVectorizer(binary=True, **self.vectorizer_kwargs)
+        X = self.vectorizer.fit_transform(X)
+        self.class_conditional_X = {i: X[y==i] for i in range(data.classes_)}
+
+    def quantify(self, instances):
+        X = self.vectorizer.transform(instances)
+
+        # number of features
+        num_docs, num_feats = X.shape
+
+        # bootstrap
+        p_boots = []
+        for _ in range(self.bootstrap_trials):
+            docs_idx = np.random.choice(num_docs, size=self.bootstra_range, replace=False)
+            class_conditional_X = {i: X[docs_idx] for i, X in self.class_conditional_X.items()}
+            Xboot = X[docs_idx]
+
+            # bagging
+            p_bags = []
+            for _ in range(self.bagging_trials):
+                feat_idx = np.random.choice(num_feats, size=self.bagging_range, replace=False)
+                class_conditional_Xbag = {i: X[:, feat_idx] for i, X in class_conditional_X.items()}
+                Xbag = Xboot[:,feat_idx]
+                p = self.std_constrained_linear_ls(Xbag, class_conditional_Xbag)
+                p_bags.append(p)
+            p_boots.append(np.mean(p_bags, axis=0))
+
+        p_mean = np.mean(p_boots, axis=0)
+        p_std  = np.std(p_bags, axis=0)
+
+        return p_mean
+
+
+    def std_constrained_linear_ls(self, X, class_cond_X: dict):
+        pass
+
 
 def _get_features_range(X):
     feat_ranges = []