Commit 4c05cc9d authored by Thomas Huetter's avatar Thomas Huetter
Browse files

minor fixes

parent 74ecde05
Loading
Loading
Loading
Loading

python_ast/download_prepare.sh

100644 → 100755
+3 −6
Original line number Original line Diff line number Diff line
@@ -12,14 +12,11 @@ wget http://files.srl.inf.ethz.ch/data/py150.tar.gz
# extract abstract syntax trees
# extract abstract syntax trees
tar -xzf py150.tar.gz
tar -xzf py150.tar.gz


# change to extracted directory
cd py150

# convert ast to bracket notation
# convert ast to bracket notation
python ../parse_json.py --inputfile python100k_train.json > python_ast.bracket
python3 parse_json.py --inputfile python100k_train.json > python_ast.bracket


# convert ast to bracket notation
# convert ast to bracket notation
python ../parse_json.py --inputfile python50k_eval.json >> python_ast.bracket
python3 parse_json.py --inputfile python50k_eval.json >> python_ast.bracket


# sort the trees ascending by their size
# sort the trees ascending by their size
../sort_dataset.sh python_ast.bracket
./sort_dataset.sh python_ast.bracket
 No newline at end of file