Loading deepchem/datasets/__init__.py +22 −4 Original line number Diff line number Diff line Loading @@ -172,10 +172,10 @@ class Dataset(object): The order of shards returned is guaranteed to remain fixed. """ for _, row in self.metadata_df.iterrows(): X = load_from_disk(row['X-transformed']) y = load_from_disk(row['y-transformed']) w = load_from_disk(row['w-transformed']) ids = load_from_disk(row['ids']) X = np.array(load_from_disk(row['X-transformed'])) y = np.array(load_from_disk(row['y-transformed'])) w = np.array(load_from_disk(row['w-transformed'])) ids = np.array(load_from_disk(row['ids']), dtype=object) yield (X, y, w, ids) def iterbatches(self, batch_size=None, epoch=0): Loading Loading @@ -213,11 +213,29 @@ class Dataset(object): dangerous (!) for large datasets which don't fit into memory. """ Xs, ys, ws, ids = [], [], [], [] print("to_numpy()") print("len(self)") print(len(self)) for (X_b, y_b, w_b, ids_b) in self.itershards(): Xs.append(X_b) ys.append(y_b) ws.append(w_b) ids.append(np.squeeze(ids_b)) #print("to_numpy()") #for y_b, ids_b in zip(ys, ids): # print("y_b.shape, ids_b.shape") # print(y_b.shape, ids_b.shape) print("len(ids)") print(len(ids)) print("[type(ids_b) for ids_b in ids]") print([type(ids_b) for ids_b in ids]) #print("[len(ids_b) for ids_b in ids]") #print([len(ids_b) for ids_b in ids]) print("sum([len(ys_b) for ys_b in ys])") print(sum([len(ys_b) for ys_b in ys])) print("sum([len(ws_b) for ws_b in ws])") print(sum([len(ws_b) for ws_b in ws])) np.concatenate(ids) return (np.vstack(Xs), np.vstack(ys), np.vstack(ws), np.concatenate(ids)) Loading deepchem/metrics/__init__.py +3 −3 Original line number Diff line number Diff line Loading @@ -161,9 +161,9 @@ class Metric(object): Raises: NotImplementedError: If metric_str is not in METRICS. """ print("compute_singletask_metric()") print("y_true.shape, y_pred.shape, w.shape") print(y_true.shape, y_pred.shape, w.shape) #print("compute_singletask_metric()") #print("y_true.shape, y_pred.shape, w.shape") #print(y_true.shape, y_pred.shape, w.shape) y_true = y_true[w != 0] y_pred = y_pred[w != 0] if self.mode == "classification": Loading deepchem/models/__init__.py +2 −2 Original line number Diff line number Diff line Loading @@ -162,8 +162,8 @@ class Model(object): y_preds.append(y_pred_batch) #ys.append(y_batch) #w_preds.append(w_batch) print("X_batch.shape, y_batch.shape, y_pred_batch.shape") print(X_batch.shape, y_batch.shape, y_pred_batch.shape) #print("X_batch.shape, y_batch.shape, y_pred_batch.shape") #print(X_batch.shape, y_batch.shape, y_pred_batch.shape) #y = np.vstack(ys) y_pred = np.vstack(y_preds) #w_pred = np.vstack(w_preds) Loading Loading
deepchem/datasets/__init__.py +22 −4 Original line number Diff line number Diff line Loading @@ -172,10 +172,10 @@ class Dataset(object): The order of shards returned is guaranteed to remain fixed. """ for _, row in self.metadata_df.iterrows(): X = load_from_disk(row['X-transformed']) y = load_from_disk(row['y-transformed']) w = load_from_disk(row['w-transformed']) ids = load_from_disk(row['ids']) X = np.array(load_from_disk(row['X-transformed'])) y = np.array(load_from_disk(row['y-transformed'])) w = np.array(load_from_disk(row['w-transformed'])) ids = np.array(load_from_disk(row['ids']), dtype=object) yield (X, y, w, ids) def iterbatches(self, batch_size=None, epoch=0): Loading Loading @@ -213,11 +213,29 @@ class Dataset(object): dangerous (!) for large datasets which don't fit into memory. """ Xs, ys, ws, ids = [], [], [], [] print("to_numpy()") print("len(self)") print(len(self)) for (X_b, y_b, w_b, ids_b) in self.itershards(): Xs.append(X_b) ys.append(y_b) ws.append(w_b) ids.append(np.squeeze(ids_b)) #print("to_numpy()") #for y_b, ids_b in zip(ys, ids): # print("y_b.shape, ids_b.shape") # print(y_b.shape, ids_b.shape) print("len(ids)") print(len(ids)) print("[type(ids_b) for ids_b in ids]") print([type(ids_b) for ids_b in ids]) #print("[len(ids_b) for ids_b in ids]") #print([len(ids_b) for ids_b in ids]) print("sum([len(ys_b) for ys_b in ys])") print(sum([len(ys_b) for ys_b in ys])) print("sum([len(ws_b) for ws_b in ws])") print(sum([len(ws_b) for ws_b in ws])) np.concatenate(ids) return (np.vstack(Xs), np.vstack(ys), np.vstack(ws), np.concatenate(ids)) Loading
deepchem/metrics/__init__.py +3 −3 Original line number Diff line number Diff line Loading @@ -161,9 +161,9 @@ class Metric(object): Raises: NotImplementedError: If metric_str is not in METRICS. """ print("compute_singletask_metric()") print("y_true.shape, y_pred.shape, w.shape") print(y_true.shape, y_pred.shape, w.shape) #print("compute_singletask_metric()") #print("y_true.shape, y_pred.shape, w.shape") #print(y_true.shape, y_pred.shape, w.shape) y_true = y_true[w != 0] y_pred = y_pred[w != 0] if self.mode == "classification": Loading
deepchem/models/__init__.py +2 −2 Original line number Diff line number Diff line Loading @@ -162,8 +162,8 @@ class Model(object): y_preds.append(y_pred_batch) #ys.append(y_batch) #w_preds.append(w_batch) print("X_batch.shape, y_batch.shape, y_pred_batch.shape") print(X_batch.shape, y_batch.shape, y_pred_batch.shape) #print("X_batch.shape, y_batch.shape, y_pred_batch.shape") #print(X_batch.shape, y_batch.shape, y_pred_batch.shape) #y = np.vstack(ys) y_pred = np.vstack(y_preds) #w_pred = np.vstack(w_preds) Loading
