ClawHub Safety Indicators: A Coding Information to Finish-to-Finish Safety Sign Evaluation and Verdict Classification on the AI Abilities Dataset
TEXT_COL = “skill_md_content” NUM_COLS = [“skillspector_score”, “static_finding_count”, “skillspector_issue_count”, “virustotal_malicious_count”] TARGET = “clawscan_verdict” def prep(df): out = df.copy() out[TEXT_COL] = out[TEXT_COL].fillna(“”).astype(str).str.slice(0, 6000) for c in NUM_COLS: out[c] = pd.to_numeric(out[c], errors=”coerce”) return out train_p, test_p = prep(train_df), prep(test_df) get_text = FunctionTransformer(lambda X: X[TEXT_COL].values, validate=False) text_pipe = Pipeline([ (“select”, get_text), (“tfidf”, TfidfVectorizer(max_features=20000, ngram_range=(1,2), min_df=3, sublinear_tf=True)), ]) num_pipe =…