1 files changed, 84 insertions, 0 deletions
diff --git a/main.py b/main.py
new file mode 100644
index 0000000..610901f
--- /dev/null
+++ b/main.py
@@ -0,0 +1,84 @@
+import argparse
+import ast
+import collections
+import os
+
+import pandas
+import sklearn.dummy
+import sklearn.ensemble
+import sklearn.model_selection
+import sklearn.tree
+
+import canonicalize
+import dynamic
+import regex
+
+def get_programs(path: str, names: str, do_canonicalize: bool = False):
+    """Load progams from path."""
+    programs = {}
+
+    users = sorted([int(uid) for uid in os.listdir(path) if uid.isdigit()])
+    for user in users:
+        user_dir = os.path.join(path, str(user), 'submissions')
+        user_subs = set()
+
+        for submission in os.listdir(user_dir):
+            with open(os.path.join(user_dir, submission), 'r') as f:
+                code = f.read().strip()
+
+            # skip syntactically incorrect programs
+            try:
+                ast.parse(code)
+            except:
+                continue
+
+            # canonicalize
+            if do_canonicalize:
+                code = canonicalize.canonicalize(code, given_names=names)
+
+            # remember
+            if code in user_subs:
+                continue
+            user_subs.add(code)
+
+            seq, total, passed = submission.split('-')
+            if code not in programs:
+                programs[code] = {'users': set(), 'correct': total == passed}
+            programs[code]['users'].add(user)
+
+    return programs
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(description='Get patterns from student programs.')
+    parser.add_argument('path', help='path to data directory')
+    parser.add_argument('--names', nargs='*', required=False, help='names that should not be anonymized')
+    parser.add_argument('--exec', required=False, help='code to append for dynamic patterns')
+    parser.add_argument('--inputs', nargs='*', required=False, help='inputs for dynamic patterns')
+
+    args = parser.parse_args()
+    path = args.path.rstrip('/')
+    problem_name = os.path.basename(path)
+
+    programs = get_programs(path, args.names, do_canonicalize=True)
+
+    attrs = collections.OrderedDict()
+    attrs.update(regex.get_attributes(programs))
+    attrs.update(dynamic.get_attributes(programs, args.exec, args.inputs))
+    print('Attributes:', attrs.keys())
+
+    for program in programs:
+        for attr in attrs:
+            programs[program][attr] = program in attrs[attr]['programs']
+    data = pandas.DataFrame.from_dict(programs, orient='index')
+    y = data['correct']
+    X = data.drop(['users', 'correct'], axis='columns')
+
+    learners = collections.OrderedDict([
+        ('major', sklearn.dummy.DummyClassifier()),
+        ('tree', sklearn.tree.DecisionTreeClassifier()),
+        ('rf', sklearn.ensemble.RandomForestClassifier()),
+    ])
+
+    for name, learner in learners.items():
+        scores = sklearn.model_selection.cross_val_score(learner, X, y, cv=10)
+        print('{}:\t{}'.format(name, scores.mean()))