From b10fcac016955d5d67bbc76d142ad6d7ca855403 Mon Sep 17 00:00:00 2001
From: Dominik Roth <dominik.roth.dev@gmail.com>
Date: Thu, 24 Feb 2022 20:12:08 +0100
Subject: [PATCH] WIP

---
 caliGraph.py |  9 ++++++--
 py/gp.py     | 62 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 69 insertions(+), 2 deletions(-)
 create mode 100644 py/gp.py

diff --git a/caliGraph.py b/caliGraph.py
index b585cce..957fee7 100755
--- a/caliGraph.py
+++ b/caliGraph.py
@@ -20,6 +20,8 @@ import plotly.graph_objects as go
 
 import wikipedia
 
+from py import *
+
 def getAllAuthors(books):
     authors = set()
     for book in books:
@@ -390,7 +392,7 @@ def scoreOpinions(G, globMu, globStd):
     for n in list(G.nodes):
         node = G.nodes[n]
         feedbacks = []
-        if node['t'] not in ['book']:
+        if node['t'] not in ['book', 'newBooks']:
             adjacens = list(G.adj[n].keys())
             for adj in adjacens:
                 adjNode = G.nodes[adj]
@@ -403,7 +405,8 @@ def scoreOpinions(G, globMu, globStd):
                 node['score'] = node['mean']
                 node['feedbacks'] = feedbacks
             else:
-                node['score'] = None
+                node['score'] = globMu - globStd
+            node['score'] = node['score'] / 2 + node['gpr_score']
 
 def scoreUnread(G, globMu, globStd):
     neuralBins = defaultdict(list)
@@ -428,6 +431,7 @@ def scoreUnread(G, globMu, globStd):
                 neuralBins['median'] = [node['median']]
                 neuralBins['se'] = [node['se']]
                 neuralBins['pagerank'] = [node['pagerank_score']]
+                neuralBins['gpr_score'] = [node['gpr_score']]
                 if 'tgb_rank' in node:
                     neuralBins['tgbrank'] = [10/math.ln10(10+node['tgb_rank'])]
                 neuralBins['bias'] = [globMu]
@@ -815,6 +819,7 @@ def genScores(G, books, calcPagerank=True):
     globMu, globStd = calcRecDist(G, books)
     if calcPagerank:
         runPagerank(G)
+    genGprScores(G, globMu, globStd)
     scoreOpinions(G, globMu, globStd)
     scoreUnread(G, globMu, globStd)
     return globMu, globStd
diff --git a/py/gp.py b/py/gp.py
new file mode 100644
index 0000000..a98c6b4
--- /dev/null
+++ b/py/gp.py
@@ -0,0 +1,62 @@
+import numpy as np
+from sklearn.gaussian_process.kernels import Kernel, Hyperparameter
+from sklearn.gaussian_process.kernels import GenericKernelMixin
+from sklearn.gaussian_process import GaussianProcessRegressor
+#from sklearn.gaussian_process import GaussianProcessClassifier
+from sklearn.base import clone
+
+class BookKernel(GenericKernelMixin, Kernel):
+    def __init__(self, G):
+        self.baseline_similarity = 0.5
+        self.baseline_similarity_bounds = (1e-5, 1)
+
+        self.G = G
+        self.node2vec = Node2Vec(self.G, dimensions=32, walk_length=16, num_walks=256, workers=8)
+        self.model = node2vec.fit(window=10, min_count=1, batch_words=4)
+        self.wv = self.model.wv
+
+    def _f(self, s1, s2):
+        return self.wv.similarity(s1, s2)
+
+    def __call__(self, X, Y=None, eval_gradient=False):
+        if Y is None:
+            Y = X
+
+        if eval_gradient:
+            return (
+                np.array([[self._f(x, y) for y in Y] for x in X]),
+            )
+        else:
+            return np.array([[self._f(x, y) for y in Y] for x in X])
+
+    def diag(self, X):
+        return self(X)
+
+    def is_stationary(self):
+        return False
+
+    def clone_with_theta(self, theta):
+        cloned = clone(self)
+        cloned.theta = theta
+        return cloned
+
+def genGprScores(G, globMu, globStd, scoreName='gpr_score', stdName='gpr_std'):
+    gpr = GaussianProcessRegressor(kernel=BookKernel(G), random_state=3141)
+    X, y = [], []
+    for n in G.nodes:
+        node = G.nodes[n]
+        if node['rating']!=None:
+            X.append(n)
+            y.append(node['rating'])
+    gpr.fit(X, y)
+    X = []
+    for n in G.nodes:
+        node = G.nodes[n]
+        if node['rating']==None:
+            X.append(n)
+    y,stds = gpr.predict(X, return_std=True)
+    for n in G.nodes:
+        node = G.nodes[n]
+        if node['rating']==None:
+            y, std = y.pop(0), stds.pop(0)
+            node[scoreName], node[stdName] = y, std