Merge pull request #384 from monarch-initiative/383-duckdbduckdbparse…

…rexception-parser-error-syntax-error-at-or-near-1

383 duckdbduckdbparserexception parser error syntax error at or near 1

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "pheval"
-version = "0.4.4"
+version = "0.4.5"
 description = ""
 authors = ["Yasemin Bridges <y.bridges@qmul.ac.uk>",
   "Julius Jacobsen <j.jacobsen@qmul.ac.uk>",

src/pheval/analyse/benchmark_db_manager.py

@@ -47,9 +47,9 @@ def add_column_integer_default(self, table_name: str, column: str, default: int
         """
         try:
             self.conn.execute(
-                f'ALTER TABLE {table_name} ADD COLUMN "{column}" INTEGER DEFAULT {default}'
+                f'ALTER TABLE "{table_name}" ADD COLUMN "{column}" INTEGER DEFAULT {default}'
             )
-            self.conn.execute(f'UPDATE {table_name} SET "{column}" = ?', (default,))
+            self.conn.execute(f'UPDATE "{table_name}" SET "{column}" = ?', (default,))
             self.conn.commit()
         except duckdb.CatalogException:
             pass

src/pheval/analyse/disease_prioritisation_analysis.py

@@ -32,7 +32,7 @@ def assess_disease_prioritisation(
         """
         relevant_ranks = []
         df = self.conn.execute(
-            f"SELECT * FROM {self.table_name} WHERE phenopacket = ? ",
+            f"SELECT * FROM '{self.table_name}' WHERE phenopacket = ? ",
             (phenopacket_path.name,),
         ).fetchdf()
         for _i, row in df.iterrows():
@@ -58,7 +58,7 @@ def assess_disease_prioritisation(
                 relevant_ranks.append(disease_match)
                 primary_key = f"{phenopacket_path.name}-{row['disease_identifier']}"
                 self.conn.execute(
-                    f'UPDATE {self.table_name} SET "{self.column}" = ? WHERE identifier = ?',
+                    f'UPDATE "{self.table_name}" SET "{self.column}" = ? WHERE identifier = ?',
                     (disease_match, primary_key),
                 )
             elif len(result) == 0:

src/pheval/analyse/gene_prioritisation_analysis.py

@@ -31,7 +31,7 @@ def assess_gene_prioritisation(
         """
         relevant_ranks = []
         df = self.conn.execute(
-            f"""SELECT * FROM {self.table_name} WHERE phenopacket = '{phenopacket_path.name}'"""
+            f"""SELECT * FROM "{self.table_name}" WHERE phenopacket = '{phenopacket_path.name}'"""
         ).fetchdf()
         for _i, row in df.iterrows():
             result = (
@@ -55,7 +55,7 @@ def assess_gene_prioritisation(
                 relevant_ranks.append(gene_match)
                 primary_key = f"{phenopacket_path.name}-{row['gene_symbol']}"
                 self.conn.execute(
-                    f'UPDATE {self.table_name} SET "{self.column}" = ? WHERE identifier = ?',
+                    f'UPDATE "{self.table_name}" SET "{self.column}" = ? WHERE identifier = ?',
                     (gene_match, primary_key),
                 )
             if not result:

src/pheval/analyse/parse_corpus.py

@@ -81,7 +81,7 @@ def _create_gene_table(self) -> None:
         """
         self.conn.execute(
             f"""
-                    CREATE TABLE IF NOT EXISTS {self.table_name}_gene (
+                    CREATE TABLE IF NOT EXISTS "{self.table_name}_gene" (
                         identifier VARCHAR(255) PRIMARY KEY,
                         phenopacket VARCHAR,
                         gene_symbol VARCHAR,
@@ -96,7 +96,7 @@ def _create_variant_table(self) -> None:
         """
         self.conn.execute(
             f"""
-                    CREATE TABLE IF NOT EXISTS {self.table_name}_variant (
+                    CREATE TABLE IF NOT EXISTS "{self.table_name}_variant" (
                         identifier VARCHAR(255) PRIMARY KEY,
                         phenopacket VARCHAR,
                         chrom VARCHAR,
@@ -113,7 +113,7 @@ def _create_disease_table(self):
         """
         self.conn.execute(
             f"""
-                    CREATE TABLE IF NOT EXISTS {self.table_name}_disease (
+                    CREATE TABLE IF NOT EXISTS "{self.table_name}_disease" (
                         identifier VARCHAR(255) PRIMARY KEY,
                         phenopacket VARCHAR,
                         disease_identifier VARCHAR,
@@ -147,7 +147,7 @@ def _insert_genes(self, phenopacket_path: Path, genes: List[ProbandCausativeGene
             identifier = f"{phenopacket_path.name}-{gene.gene_symbol}"
             self.conn.execute(
                 f"""
-                INSERT OR IGNORE INTO {self.table_name}_gene (identifier, phenopacket, gene_symbol, gene_identifier)
+                INSERT OR IGNORE INTO "{self.table_name}_gene" (identifier, phenopacket, gene_symbol, gene_identifier)
                 VALUES (?, ?, ?, ?)
                 """,
                 (identifier, phenopacket_path.name, gene.gene_symbol, gene.gene_identifier),
@@ -166,7 +166,7 @@ def _insert_variants(self, phenopacket_path: Path, variants: List[GenomicVariant
             )
             self.conn.execute(
                 f"""
-                INSERT OR IGNORE INTO {self.table_name}_variant (identifier, phenopacket, chrom, pos, "ref", alt)
+                INSERT OR IGNORE INTO "{self.table_name}_variant" (identifier, phenopacket, chrom, pos, "ref", alt)
                 VALUES (?, ?, ?, ?, ?, ?)
                 """,
                 (
@@ -189,8 +189,8 @@ def _insert_diseases(self, phenopacket_path: Path, diseases: List[ProbandDisease
         for disease in diseases:
             identifier = f"{phenopacket_path.name}-{disease.disease_identifier}"
             self.conn.execute(
-                f"INSERT OR IGNORE INTO {self.table_name}_disease "
-                f"(identifier, phenopacket, disease_identifier, disease_name) VALUES (?, ?, ?, ?)",
+                f"""INSERT OR IGNORE INTO "{self.table_name}_disease" """
+                f"""(identifier, phenopacket, disease_identifier, disease_name) VALUES (?, ?, ?, ?)""",
                 (
                     identifier,
                     phenopacket_path.name,

src/pheval/analyse/rank_stats.py

@@ -68,7 +68,7 @@ def _execute_count_query(
         Returns:
             int: Count query result.
         """
-        query = f'SELECT COUNT(*) FROM {table_name} WHERE "{column_name}" {condition}'
+        query = f'SELECT COUNT(*) FROM "{table_name}" WHERE "{column_name}" {condition}'
         return conn.execute(query).fetchone()[0]
 
     @staticmethod
@@ -85,7 +85,7 @@ def _fetch_reciprocal_ranks(
         Returns:
             List[float]: List of reciprocal ranks.
         """
-        query = f'SELECT "{column_name}" FROM {table_name}'
+        query = f'SELECT "{column_name}" FROM "{table_name}"'
         return [1 / rank[0] if rank[0] > 0 else 0 for rank in conn.execute(query).fetchall()]
 
     @staticmethod
@@ -103,7 +103,7 @@ def _fetch_relevant_ranks(
             List[List[int]]: List of relevant ranks.
         """
         query = (
-            f'SELECT LIST("{column_name}") as values_list FROM {table_name} GROUP BY phenopacket'
+            f'SELECT LIST("{column_name}") as values_list FROM "{table_name}" GROUP BY phenopacket'
         )
         return [rank[0] for rank in conn.execute(query).fetchall()]
 

src/pheval/analyse/variant_prioritisation_analysis.py

@@ -33,7 +33,7 @@ def assess_variant_prioritisation(
         """
         relevant_ranks = []
         df = self.conn.execute(
-            f"""SELECT * FROM {self.table_name} WHERE phenopacket = '{phenopacket_path.name}'"""
+            f"""SELECT * FROM "{self.table_name}" WHERE phenopacket = '{phenopacket_path.name}'"""
         ).fetchdf()
         for _i, row in df.iterrows():
             causative_variant = GenomicVariant(
@@ -67,7 +67,7 @@ def assess_variant_prioritisation(
                     f"{causative_variant.ref}-{causative_variant.alt}"
                 )
                 self.conn.execute(
-                    f'UPDATE {self.table_name} SET "{self.column}" = ? WHERE identifier = ?',
+                    f'UPDATE "{self.table_name}" SET "{self.column}" = ? WHERE identifier = ?',
                     (variant_match, primary_key),
                 )
             elif len(result) == 0: