# ml ## Setup ## Example Data ``` python import seaborn as sns ``` ``` python df = sns.load_dataset("penguins").dropna( subset=["bill_length_mm", "bill_depth_mm", "flipper_length_mm", "body_mass_g", "species"] ).reset_index(drop=True) feat_col = ["bill_length_mm", "bill_depth_mm", "flipper_length_mm", "body_mass_g"] target_df = pd.get_dummies(df["species"], prefix="species", dtype=float) target_col = target_df.columns.tolist() df[target_col] = target_df df.shape ``` (342, 10) ``` python df[feat_col + ["species"] + target_col].head() ```
bill_length_mm bill_depth_mm flipper_length_mm body_mass_g species species_Adelie species_Chinstrap species_Gentoo
0 39.1 18.7 181.0 3750.0 Adelie 1.0 0.0 0.0
1 39.5 17.4 186.0 3800.0 Adelie 1.0 0.0 0.0
2 40.3 18.0 195.0 3250.0 Adelie 1.0 0.0 0.0
3 36.7 19.3 193.0 3450.0 Adelie 1.0 0.0 0.0
4 39.3 20.6 190.0 3650.0 Adelie 1.0 0.0 0.0
## Splitter ------------------------------------------------------------------------ source ### get_splits ``` python def get_splits( df:DataFrame, stratified:str | None=None, # col used for stratified sampling group:str | None=None, # col used to keep grouped rows together nfold:int=5, seed:int=123 )->list: ``` *Split samples in a dataframe with stratified, grouped, or stratified-grouped K-fold logic.* ``` python splits = get_splits(df, stratified="species", nfold=3) split0 = splits[0] len(split0[0]), len(split0[1]) ``` StratifiedKFold(n_splits=3, random_state=123, shuffle=True) # species in train set: 3 # species in test set: 3 (228, 114) ## Train/Test Split ------------------------------------------------------------------------ source ### split_data ``` python def split_data( df:DataFrame, # dataframe of values feat_col:Sequence, # feature columns target_col:Sequence, # target columns split:tuple )->tuple: ``` *Given a split tuple, return X_train, y_train, X_test, and y_test.* ``` python X_train, y_train, X_test, y_test = split_data(df, feat_col, target_col, split0) X_train.shape, y_train.shape, X_test.shape, y_test.shape ``` ((228, 4), (228, 3), (114, 4), (114, 3)) ## Trainer ------------------------------------------------------------------------ source ### train_ml ``` python def train_ml( df:DataFrame, # dataframe of values feat_col:Sequence, # feature columns target_col:Sequence, # target columns split:tuple, model, # sklearn model instance save:str | pathlib.Path | None=None, # output path for joblib model params:dict | None=None, # kwargs forwarded to model.fit )->tuple: ``` *Fit and predict with a sklearn model, returning validation targets and predictions.* ``` python model = LinearRegression() target, pred = train_ml(df, feat_col, target_col, split0, model) pred.head() ```
species_Adelie species_Chinstrap species_Gentoo
0 0.993427 0.137000 -0.130427
3 1.064457 0.046586 -0.111043
9 0.839056 0.118838 0.042105
11 0.669557 0.423417 -0.092974
14 1.050863 -0.073914 0.023052
## Cross-Validation ------------------------------------------------------------------------ source ### train_ml_cv ``` python def train_ml_cv( df:DataFrame, # dataframe of values feat_col:Sequence, # feature columns target_col:Sequence, # target columns splits:Sequence, model, # sklearn model instance save:str | None=None, # model name prefix for saved folds params:dict | None=None, # kwargs forwarded to model.fit )->DataFrame: ``` *Run cross-validation through the given splits.* ``` python oof = train_ml_cv(df, feat_col, target_col, splits=splits, model=LinearRegression()) oof.head() ```
species_Adelie species_Chinstrap species_Gentoo nfold
0 0.993427 0.137000 -0.130427 0
1 0.790344 0.103762 0.105894 1
2 0.673088 0.317647 0.009265 2
3 1.064457 0.046586 -0.111043 0
4 1.122991 0.154406 -0.277398 1
## Score ------------------------------------------------------------------------ source ### post_process ``` python def post_process( pred_like:pandas.DataFrame | pandas.Series, epsilon:float=1e-08 ): ``` *Clip negatives and renormalize probability-like predictions.* ``` python post_process(pred.head()) ```
species_Adelie species_Chinstrap species_Gentoo
0 0.878807 1.211930e-01 8.846216e-09
3 0.958070 4.192990e-02 9.000554e-09
9 0.839056 1.188384e-01 4.210543e-02
11 0.612601 3.873988e-01 9.149350e-09
14 0.978535 9.311731e-09 2.146502e-02
------------------------------------------------------------------------ source ### post_process_oof ``` python def post_process_oof( oof_ml:DataFrame, target_col:Sequence )->DataFrame: ``` *Post-process prediction columns in an out-of-fold dataframe.* ``` python oof = post_process_oof(oof, target_col) oof[target_col].head() ```
species_Adelie species_Chinstrap species_Gentoo
0 0.878807 0.121193 8.846216e-09
1 0.790344 0.103762 1.058942e-01
2 0.673088 0.317647 9.264531e-03
3 0.958070 0.041930 9.000554e-09
4 0.879124 0.120876 7.828416e-09
------------------------------------------------------------------------ source ### get_score ``` python def get_score( target:DataFrame, pred:DataFrame, func:Callable )->Series: ``` *Apply a row-wise score function to aligned target and prediction frames.* ------------------------------------------------------------------------ source ### js_divergence_flat ``` python def js_divergence_flat( target_series:pandas.Series | numpy.ndarray, pred_series:pandas.Series | numpy.ndarray, epsilon:float=1e-08 )->float: ``` *Compute Jensen-Shannon divergence between two flattened probability vectors.* ------------------------------------------------------------------------ source ### kl_divergence_flat ``` python def kl_divergence_flat( target_series:pandas.Series | numpy.ndarray, pred_series:pandas.Series | numpy.ndarray, epsilon:float=1e-08 )->float: ``` *Compute KL divergence between two flattened probability vectors.* ------------------------------------------------------------------------ source ### calculate_ce ``` python def calculate_ce( target_series:pandas.Series | numpy.ndarray, pred_series:pandas.Series | numpy.ndarray, epsilon:float=1e-08 )->float: ``` *Compute cross-entropy between two flattened probability vectors.* ``` python target = df.loc[oof.index, target_col].copy() pd.DataFrame({ "jsd": get_score_jsd(target, oof), "kld": get_score_kld(target, oof), "ce": get_score_ce(target, oof), }).head() ```
jsd kld ce
0 0.043958 0.129190 0.129190
1 0.078813 0.235286 0.235287
2 0.129371 0.395879 0.395879
3 0.014756 0.042834 0.042835
4 0.043837 0.128829 0.128829
## Predictor ------------------------------------------------------------------------ source ### predict_ml ``` python def predict_ml( df:DataFrame, # dataframe with features feat_col:Sequence, # feature columns target_col:collections.abc.Sequence[str] | None=None, model_pth:str | pathlib.Path='model.joblib' )->DataFrame: ``` *Predict from a saved sklearn model.* ``` python model_path = Path("_tmp/penguins_ml.joblib") model_path.parent.mkdir(parents=True, exist_ok=True) _ = train_ml(df, feat_col, target_col, split0, LinearRegression(), save=model_path) predict_ml(df.iloc[split0[1]], feat_col, target_col, model_pth=model_path).head() ```
species_Adelie species_Chinstrap species_Gentoo
0 0.993427 0.137000 -0.130427
3 1.064457 0.046586 -0.111043
9 0.839056 0.118838 0.042105
11 0.669557 0.423417 -0.092974
14 1.050863 -0.073914 0.023052