Merge pull request #150 from scikit-learn-contrib/chp_add_rand_state_ddpm

Chp add rand state ddpm

Author: JulienRoussel77

examples/benchmark.md

@@ -305,6 +305,32 @@ except ModuleNotFoundError:
 For the example, we use a simple MLP model with 3 layers of neurons.
 Then we train the model without taking a group on the stations
 
+```python
+import numpy as np
+from qolmat.imputations.imputers_pytorch import ImputerDiffusion
+from qolmat.imputations.diffusions.ddpms import TabDDPM
+
+X = np.array([[1, 1, 1, 1], [np.nan, np.nan, 3, 2], [1, 2, 2, 1], [2, 2, 2, 2]])
+imputer = ImputerDiffusion(model=TabDDPM(random_state=11), epochs=50, batch_size=1)
+
+imputer.fit_transform(X)
+```
+
+```python
+import numpy as np
+from qolmat.imputations.imputers_pytorch import ImputerDiffusion
+from qolmat.imputations.diffusions.ddpms import TabDDPM
+
+X = np.array([[1, 1, 1, 1], [np.nan, np.nan, 3, 2], [1, 2, 2, 1], [2, 2, 2, 2]])
+imputer = ImputerDiffusion(model=TabDDPM(random_state=11), epochs=50, batch_size=1)
+
+imputer.fit_transform(X)
+```
+
+```python
+1.33573675, 1.40472937
+```
+
 ```python
 fig = plt.figure(figsize=(10 * n_stations, 3 * n_cols))
 for i_station, (station, df) in enumerate(df_data.groupby("station")):

qolmat/analysis/__init__.py

@@ -34,8 +34,9 @@ class LittleTest(McarTest):
     imputer : Optional[ImputerEM]
         Imputer based on the EM algorithm. The 'model' attribute must be equal to 'multinormal'.
         If None, the default ImputerEM is taken.
-    random_state : Union[None, int, np.random.RandomState], optional
-        Controls the randomness of the fit_transform, by default None
+    random_state : int, RandomState instance or None, default=None
+        Controls the randomness.
+        Pass an int for reproducible output across multiple function calls.
     """
 
     def __init__(

qolmat/analysis/holes_characterization.py

@@ -63,8 +63,9 @@ class _HoleGenerator:
         Names of the columns for which holes must be created, by default None
     ratio_masked : Optional[float]
         Ratio of values ​​to mask, by default 0.05.
-    random_state : Optional[int]
-        The seed used by the random number generator, by default 42.
+    random_state : int, RandomState instance or None, default=None
+        Controls the randomness.
+        Pass an int for reproducible output across multiple function calls.
     groups: Tuple[str, ...]
         Column names used to group the data
     """
@@ -150,8 +151,9 @@ class UniformHoleGenerator(_HoleGenerator):
         Names of the columns for which holes must be created, by default None
     ratio_masked : Optional[float], optional
         Ratio of masked values ​​to add, by default 0.05.
-    random_state : Optional[int], optional
-        The seed used by the random number generator, by default 42.
+    random_state : int, RandomState instance or None, default=None
+        Controls the randomness.
+        Pass an int for reproducible output across multiple function calls.
     sample_proportional: bool, optional
         If True, generates holes in target columns with same equal frequency.
         If False, reproduces the empirical proportions between the variables.
@@ -215,8 +217,9 @@ class _SamplerHoleGenerator(_HoleGenerator):
         Names of the columns for which holes must be created, by default None
     ratio_masked : Optional[float], optional
         Ratio of masked values ​​to add, by default 0.05.
-    random_state : Optional[int], optional
-        The seed used by the random number generator, by default 42.
+    random_state : int, RandomState instance or None, default=None
+        Controls the randomness.
+        Pass an int for reproducible output across multiple function calls.
     groups: Tuple[str, ...]
         Column names used to group the data
     """
@@ -321,8 +324,9 @@ class GeometricHoleGenerator(_SamplerHoleGenerator):
         Names of the columns for which holes must be created, by default None
     ratio_masked : Optional[float], optional
         Ratio of masked values ​​to add, by default 0.05.
-    random_state : Union[None, int, np.random.RandomState], optional
-        The seed used by the random number generator, by default 42.
+    random_state : int, RandomState instance or None, default=None
+        Controls the randomness.
+        Pass an int for reproducible output across multiple function calls.
     groups: Tuple[str, ...]
         Column names used to group the data
     """
@@ -390,8 +394,9 @@ class EmpiricalHoleGenerator(_SamplerHoleGenerator):
         Names of the columns for which holes must be created, by default None
     ratio_masked : Optional[float], optional
         Ratio of masked values ​​to add, by default 0.05.
-    random_state : Optional[int], optional
-        The seed used by the random number generator, by default 42.
+    random_state : int, RandomState instance or None, default=None
+        Controls the randomness.
+        Pass an int for reproducible output across multiple function calls.
     groups: Tuple[str, ...]
         Column names used to group the data
     """
@@ -485,8 +490,9 @@ class MultiMarkovHoleGenerator(_HoleGenerator):
         Names of the columns for which holes must be created, by default None
     ratio_masked : Optional[float], optional
         Ratio of masked values to add, by default 0.05
-    random_state : Optional[int], optional
-        The seed used by the random number generator, by default 42.
+    random_state : int, RandomState instance or None, default=None
+        Controls the randomness.
+        Pass an int for reproducible output across multiple function calls.
     groups: Tuple[str, ...]
         Column names used to group the data
     """
@@ -634,8 +640,9 @@ class GroupedHoleGenerator(_HoleGenerator):
         Names of the columns for which holes must be created, by default None
     ratio_masked : Optional[float], optional
         Ratio of masked to add, by default 0.05
-    random_state : Optional[int], optional
-        The seed used by the random number generator, by default 42.
+    random_state : int, RandomState instance or None, default=None
+        Controls the randomness.
+        Pass an int for reproducible output across multiple function calls.
     groups : Tuple[str, ...]
         Names of the columns forming the groups, by default []
     """

qolmat/benchmark/missing_patterns.py

@@ -1,16 +1,17 @@
-from typing import Dict, List, Callable, Tuple
+from typing import Dict, List, Callable, Tuple, Union
 from typing_extensions import Self
-import math
+import sys
 import numpy as np
 import pandas as pd
 import time
 from datetime import timedelta
 from tqdm import tqdm
-import gc
 
 import torch
 from torch.utils.data import DataLoader, TensorDataset
 from sklearn import preprocessing
+from sklearn import utils as sku
+
 
 from qolmat.imputations.diffusions.base import AutoEncoder, ResidualBlock, ResidualBlockTS
 from qolmat.imputations.diffusions.utils import get_num_params
@@ -39,6 +40,7 @@ def __init__(
         p_dropout: float = 0.0,
         num_sampling: int = 1,
         is_clip: bool = True,
+        random_state: Union[None, int, np.random.RandomState] = None,
     ):
         """Diffusion model for tabular data based on
         Denoising Diffusion Probabilistic Models (DDPM) of
@@ -68,6 +70,9 @@ def __init__(
             Dropout probability, by default 0.0
         num_sampling : int, optional
             Number of samples generated for each cell, by default 1
+        random_state : int, RandomState instance or None, default=None
+            Controls the randomness.
+            Pass an int for reproducible output across multiple function calls.
         """
         self.device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
 
@@ -108,6 +113,9 @@ def __init__(
         self.is_clip = is_clip
 
         self.normalizer_x = preprocessing.StandardScaler()
+        self.random_state = sku.check_random_state(random_state)
+        seed_torch = self.random_state.randint(2**31 - 1)
+        torch.manual_seed(seed_torch)
 
     def _q_sample(self, x: torch.Tensor, t: torch.Tensor) -> Tuple[torch.Tensor, torch.Tensor]:
         """Section 3.2, algorithm 1 formula implementation. Forward process, defined by `q`.
@@ -345,7 +353,6 @@ def fit(
         round: int = 10,
         cols_imputed: Tuple[str, ...] = (),
     ) -> Self:
-
         """Fit data
 
         Parameters
@@ -537,6 +544,7 @@ def __init__(
         p_dropout: float = 0.0,
         num_sampling: int = 1,
         is_rolling: bool = False,
+        random_state: Union[None, int, np.random.RandomState] = None,
     ):
         """Diffusion model for time-series data based on the works of
         Ho et al., 2020 (https://arxiv.org/abs/2006.11239),
@@ -575,6 +583,9 @@ def __init__(
             Number of samples generated for each cell, by default 1
         is_rolling : bool, optional
             Use pandas.DataFrame.rolling for preprocessing data, by default False
+        random_state : int, RandomState instance or None, default=None
+            Controls the randomness.
+            Pass an int for reproducible output across multiple function calls.
         """
         super().__init__(
             num_noise_steps,
@@ -586,6 +597,7 @@ def __init__(
             num_blocks,
             p_dropout,
             num_sampling,
+            random_state=random_state,
         )
 
         self.dim_feedforward = dim_feedforward

qolmat/imputations/diffusions/ddpms.py

@@ -568,6 +568,17 @@ def __init__(
         freq_str : str
             Frequency string of DateOffset of Pandas.
             It is for processing time-series data, used in diffusion models e.g., TsDDPM.
+
+        Examples
+        --------
+        >>> import numpy as np
+        >>> from qolmat.imputations.imputers_pytorch import ImputerDiffusion
+        >>> from qolmat.imputations.diffusions.ddpms import TabDDPM
+        >>>
+        >>> X = np.array([[1, 1, 1, 1], [np.nan, np.nan, 3, 2], [1, 2, 2, 1], [2, 2, 2, 2]])
+        >>> imputer = ImputerDiffusion(model=TabDDPM(random_state=11), epochs=50, batch_size=1)
+        >>>
+        >>> df_imputed = imputer.fit_transform(X)
         """
         super().__init__(groups=groups, columnwise=False)
         self.model = model