started graph embedding module

embeddings/db_handler.py

+import sqlite3
+
+import pandas as pd
+
+
+class DBHandler:
+    def __init__(self, file_name: str):
+        self._db = sqlite3.connect(file_name)
+
+    def fetch_questions_by_user_id(self, user_id: int):
+        questions = pd.read_sql_query(f"""
+                SELECT *
+                FROM Post
+                WHERE Tags LIKE '%python%' AND (PostTypeId = 1) AND ((LastEditorUserId = {user_id}) OR (OwnerUserId = {user_id}))
+        """, self._db)
+        questions.set_index('PostId', inplace=True)
+
+    def fetch_answers_by_user_id(self, user_id: int):
+        answers = pd.read_sql_query(f"""
+                SELECT A.Tags, B.*
+                FROM Post A
+                    INNER JOIN Post B ON (B.ParentId = A.PostId) AND (B.ParentId IS NOT NULL)
+                WHERE A.Tags LIKE '%python%' AND (B.PostTypeId = 2) AND ((B.LastEditorUserId = {user_id}) OR (B.OwnerUserId = {user_id}))
+        """, self._db)
+        # Only use the first of the two 'Tags' columns
+        answers = answers.loc[:, ~answers.columns.duplicated()].copy()
+        answers.set_index('PostId', inplace=True)
+        return answers
+
+    def fetch_comments_on_questions_by_user_id(self, user_id: int):
+        comments_on_questions = pd.read_sql_query(f"""
+                SELECT A.Tags, B.*
+                FROM Post A
+                    INNER JOIN Comment B ON (B.PostId = A.PostId)
+                WHERE A.Tags LIKE '%python%' AND (B.UserId = {user_id}) AND (A.PostTypeId = 1)
+        """, self._db)
+        comments_on_questions.set_index('CommentId', inplace=True)
+        return comments_on_questions
+
+    def fetch_comments_on_answers_by_user_id(self, user_id: int):
+        comments_on_answers = pd.read_sql_query(f"""
+            SELECT A.Tags, C.*
+            FROM Post A
+                INNER JOIN Post B ON (B.ParentId = A.PostId) AND (B.ParentId IS NOT NULL)
+                INNER JOIN Comment C ON (B.PostId = C.PostId)
+            WHERE A.Tags LIKE '%python%' AND (C.UserId = {user_id}) AND (B.PostTypeId = 2)
+        """, self._db)
+        comments_on_answers.set_index('CommentId', inplace=True)
+        return comments_on_answers
+

embeddings/static_user_graph_construction.py

+from abc import ABC
+
+import networkx as nx
+import pandas as pd
+from graph4nlp.pytorch.data import GraphData
+from graph4nlp.pytorch.modules.graph_construction import DependencyBasedGraphConstruction
+from graph4nlp.pytorch.modules.graph_construction.base import StaticGraphConstructionBase
+from matplotlib import pyplot as plt
+
+
+class StaticUserGraphConstruction:
+    """Class for StackOverflow user activity graph construction"""
+
+    def __init__(self):
+        super(StaticUserGraphConstruction, self).__init__()
+
+
+    def static_topology(cls, questions: pd.DataFrame, answers: pd.DataFrame, comments: pd.DataFrame) -> GraphData:
+        cls._construct_static_graph()
+
+    @classmethod
+    def _construct_static_graph(cls, questions: pd.DataFrame, answers: pd.DataFrame, comments: pd.DataFrame):
+        user_graph = GraphData()
+        next_node = 0
+
+        color_map = []
+
+        node_features = []
+        tag_dict = {}  # tag name: node id
+        module_dict = {}
+
+        edges_src = []
+        edges_dest = []
+
+
+    @classmethod
+    def display_graph(cls, g: GraphData, color_map=None) -> None:
+        plt.figure(figsize=(40, 40))
+        dgl_ug = g.to_dgl()
+        nx_ug_graph = dgl_ug.to_networkx()
+        pos_ug = nx.spring_layout(nx_ug_graph)  # , k=0.15, iterations=20)
+        if color_map is not None:
+            nx.draw(nx_ug_graph, pos_ug, with_labels=True, node_color=color_map)
+        else:
+            nx.draw(nx_ug_graph, pos_ug, with_labels=True, node_color=[[.7, .7, .7]])
+
+
+if __name__ == '__main__':
+    t = DependencyBasedGraphConstruction(None)
+    t(None)
+
+    #graph_topology = StaticUserGraphConstruction()
+    #graph_topology(GraphData())