bdext 0.1.61__py3-none-any.whl → 0.1.63__py3-none-any.whl

bdeissct_dl/bdeissct_model.py

@@ -129,5 +129,5 @@ for model in (BDEISSCT, BDEISSCT1, BDEISSCT2, BDEISSCT2000):
 
 
 
-CT_EPI_COLUMNS = [REPRODUCTIVE_NUMBER, INFECTION_DURATION, SAMPLING_FRACTION, UPSILON, X_C, F_E, F_S, X_S, LA]
+CT_EPI_COLUMNS = [REPRODUCTIVE_NUMBER, INFECTION_DURATION, SAMPLING_FRACTION, LA, F_E, F_S, X_S, UPSILON, X_C]
 CT_RATE_COLUMNS = [PSI, RHO]

bdeissct_dl/estimator_ct.py

@@ -7,12 +7,7 @@ from bdeissct_dl.model_serializer import load_model_keras, load_scaler_numpy
 
 def predict_parameters(df, model_path=MODEL_PATH):
     feature_columns = CT_EPI_COLUMNS
-    x_indices = []
-    for i, col in enumerate(df.columns):
-        if col in feature_columns:
-            x_indices.append(i)
-
-    X = df.iloc[:, x_indices].to_numpy(dtype=float, na_value=0)
+    X = df.loc[:, feature_columns].to_numpy(dtype=float, na_value=0)
 
     # Standardization of the input features with a
     # standard scaler
@@ -58,7 +53,6 @@ def main():
                              )
     parser.add_argument('--log', default=None, type=str, help="output log file")
     parser.add_argument('--sumstats', default=None, type=str, help="input file(s) with epi parameters")
-    parser.add_argument('--ci', action='store_true', help="calculate CIs")
     params = parser.parse_args()
 
     df = pd.read_csv(params.sumstats)

bdeissct_dl/models/data_scalerct.x_n_samples_seen.txt

@@ -0,0 +1 @@
+458752

bdeissct_dl/scaler_fitting.py

@@ -10,16 +10,13 @@ from bdeissct_dl.model_serializer import save_scaler_joblib, save_scaler_numpy
 from bdeissct_dl.training import get_data_characteristics
 
 
-def fit_scalers(paths, x_indices, y_indices, scaler_x=None, scaler_y=None):
+def fit_scalers(paths, x_indices, scaler_x=None):
     # First pass: calculate mean and var
     for path in paths:
         df = pd.read_csv(path)
         if scaler_x:
             X = df.iloc[:, x_indices].to_numpy(dtype=float, na_value=0)
             scaler_x.partial_fit(X)
-        if scaler_y:
-            Y = df.iloc[:, y_indices].to_numpy(dtype=float, na_value=0)
-            scaler_y.partial_fit(Y)
 
 
 def main():
@@ -41,17 +38,14 @@ def main():
 
     os.makedirs(params.model_path, exist_ok=True)
 
-    scaler_x, scaler_y = StandardScaler(), None
-    x_indices, y_indices, _ = \
+    scaler_x = StandardScaler()
+    x_indices, _ = \
         get_data_characteristics(paths=params.train_data, target_columns=TARGET_COLUMNS_BDEISSCT)
-    fit_scalers(paths=params.train_data, x_indices=x_indices, y_indices=y_indices, scaler_x=scaler_x, scaler_y=scaler_y)
+    fit_scalers(paths=params.train_data, x_indices=x_indices, scaler_x=scaler_x)
 
     if scaler_x is not None:
         save_scaler_joblib(scaler_x, params.model_path, suffix='x')
         save_scaler_numpy(scaler_x, params.model_path, suffix='x')
-    if scaler_y is not None:
-        save_scaler_joblib(scaler_y, params.model_path, suffix='y')
-        save_scaler_numpy(scaler_y, params.model_path, suffix='y')
 
 
 if '__main__' == __name__:

bdeissct_dl/train_ct.py

@@ -86,12 +86,12 @@ def main():
         np.random.shuffle(params.val_data)
 
 
-    x_indices, y_indices, y_col2index = get_data_characteristics(paths=params.train_data,
+    x_indices, y_col2index = get_data_characteristics(paths=params.train_data,
                                                                  feature_columns=feature_columns,
                                                                  target_columns=target_columns)
 
-    scaler_x, scaler_y = StandardScaler(), None
-    fit_scalers(paths=params.train_data, x_indices=x_indices, y_indices=y_indices, scaler_x=scaler_x, scaler_y=scaler_y)
+    scaler_x = StandardScaler()
+    fit_scalers(paths=params.train_data, x_indices=x_indices, scaler_x=scaler_x)
 
     if scaler_x is not None:
         save_scaler_joblib(scaler_x, params.model_path, suffix='ct.x')

bdeissct_dl/training.py

@@ -54,20 +54,20 @@ def get_test_data(dfs=None, paths=None, scaler_x=None):
 
 
 def get_data_characteristics(paths, target_columns=TARGET_COLUMNS_BDCT, feature_columns=None):
-    x_indices = []
-    y_indices = []
-    col2index = {}
+    col2index_y = {}
+    col2index_x = {}
 
     df = pd.read_csv(paths[0])
-    feature_columns = set(get_X_columns(df.columns)) if feature_columns is None else set(feature_columns)
-    target_columns = set(target_columns) if target_columns is not None else set()
+    feature_columns = get_X_columns(df.columns) if feature_columns is None else feature_columns
+    feature_column_set = set(feature_columns)
+    target_columns = target_columns if target_columns is not None else []
+    target_column_set = set(target_columns)
     for i, col in enumerate(df.columns):
-        if col in feature_columns:
-            x_indices.append(i)
-        if col in target_columns:
-            y_indices.append(i)
-            col2index[col] = i
-    return x_indices, y_indices, col2index
+        if col in feature_column_set:
+            col2index_x[col] = i
+        if col in target_column_set:
+            col2index_y[col] = i
+    return [col2index_x[_] for _ in feature_columns], col2index_y
 
 
 def get_train_data(target_columns, columns_x, columns_y, file_pattern=None, filenames=None, scaler_x=None, \
@@ -192,7 +192,7 @@ def main():
         np.random.shuffle(params.val_data)
 
 
-    x_indices, y_indices, y_col2index = get_data_characteristics(paths=params.train_data, target_columns=target_columns)
+    x_indices, y_col2index = get_data_characteristics(paths=params.train_data, target_columns=target_columns)
 
     scaler_x = load_scaler_numpy(params.model_path, suffix='x')
 

{bdext-0.1.61.dist-info → bdext-0.1.63.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: bdext
-Version: 0.1.61
+Version: 0.1.63
 Summary: Estimation of BDEISS-CT parameters from phylogenetic trees.
 Home-page: https://github.com/modpath/bdeissct
 Author: Anna Zhukova

bdext-0.1.63.dist-info/RECORD

@@ -0,0 +1,29 @@
+README.md,sha256=Fk-VeZXo2zltZ9NXdFnnHS3ETwtiBPRiZ86ttUQUgTE,5894
+bdeissct_dl/__init__.py,sha256=glAW73vlD9Abbb_Fto-sKys078qVEn5iTcx2Mq3Z72s,361
+bdeissct_dl/bdeissct_model.py,sha256=--dnDxvvWcFb45bKIGv8-GUAcSnXA_x6p4D9MFsyXPk,3566
+bdeissct_dl/dl_model.py,sha256=q8RFbbd2n52Y0_HMKSEHdIgBouE4LbHL5CZO3M_3G3E,7364
+bdeissct_dl/estimator.py,sha256=UIQAy62I0_2HKagfck9WBGbbHU6l_WfRypP9CyeHrFE,7313
+bdeissct_dl/estimator_ct.py,sha256=P5Up-NnAYS2Nen5_KPEYP04VXr5hm1Dtjq5TuW5OHjM,2604
+bdeissct_dl/main_covid.py,sha256=wCeJgc4XzEPjcVCaQt_-zGiVX0wdpQhFq2qh9xQzc7w,2882
+bdeissct_dl/model_finder.py,sha256=TC6EcIE6rBO6PefaYfn2reEl6HPkORbIgTzQGsDoXcU,1763
+bdeissct_dl/model_serializer.py,sha256=Ojhy-fUElc4NClhJaF0EWnrAJGK0omk8e7cwwrBk3Yk,3768
+bdeissct_dl/pinball_loss.py,sha256=Xg2jFDlwPOt0AhBY574lWB0yRyuA0bQRiyOYHGL6P54,1602
+bdeissct_dl/scaler_fitting.py,sha256=SdU9DHj9JUAONfbcIfrvK5OYgzcwHlbVQP2rJknF8tQ,1975
+bdeissct_dl/sumstat_checker.py,sha256=BHMgoqjymHc3Ic-Sv7m-zuvCeLlCt4OCDVaKDltSII0,1867
+bdeissct_dl/train_ct.py,sha256=AYhotLFlb_OIoUQzir6SrvCmI1p0FhemjWkdNz0dkTQ,5392
+bdeissct_dl/training.py,sha256=QBjly8e_8yqvxDbHGPw0F4LeL8BbA6UQ8SANFc0NCYY,8990
+bdeissct_dl/tree_encoder.py,sha256=WrrSk_HXOF_rAKHpU7u9_i_gCmp5tz7Tk_Jvbwx0N_g,19193
+bdeissct_dl/tree_manager.py,sha256=UXxUVmEkxwUhKpJeACVgiXZ8Kp1o_hiv8Qb80b6qmVU,11814
+bdeissct_dl/models/CT.psi.keras,sha256=iBrIAvvry6Vew_YhJ_2kjKI3IHm2nH-MtKo1jsQSsC4,40136
+bdeissct_dl/models/CT.rho.keras,sha256=CHiIFf2f22Hx_2JdPA7iT0epAqQHYWpRlzFHejp34e0,40135
+bdeissct_dl/models/data_scalerct.x.gz,sha256=MvqalwyVbvXTvv03usmBt6TMyfc2ecr1Xv1XvRaLCa8,682
+bdeissct_dl/models/data_scalerct.x_mean.npy,sha256=8WalRktKWWvrgAM5ViBVo2fuSfq7zTrCIVtwSeQFzM0,200
+bdeissct_dl/models/data_scalerct.x_n_samples_seen.txt,sha256=APPIZMPUPTCdiHMNx0SrYFFojbLlqbaF5PPZIshGgX8,6
+bdeissct_dl/models/data_scalerct.x_scale.npy,sha256=yg7kI49ycLpVepmb4LXzU9MDlXz7jILAFVna5rPkdDM,200
+bdeissct_dl/models/data_scalerct.x_var.npy,sha256=wWyJxoBhm3BKZ5zi0PVejGCnZaooKj7MjaNv_W0uyrE,200
+bdext-0.1.63.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+bdext-0.1.63.dist-info/METADATA,sha256=-3CPE2SesHL44cFjx1MyCzoApT-6bgAgTp_OT_DkjMY,6834
+bdext-0.1.63.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+bdext-0.1.63.dist-info/entry_points.txt,sha256=En4b5js0-eCuBp0Jiqye0fte6svXbXSLiSJOW_KdzV4,286
+bdext-0.1.63.dist-info/top_level.txt,sha256=z4dadFfcLghr4lwROy7QR3zEICpa-eCPT6mmcoHeEJY,12
+bdext-0.1.63.dist-info/RECORD,,

bdeissct_dl/assess_R_CT.py

@@ -1,21 +0,0 @@
-import numpy as np
-import pandas as pd
-
-from bdeissct_dl.bdeissct_model import REPRODUCTIVE_NUMBER, INFECTION_DURATION, RHO, F_E, F_S, X_S, UPSILON, X_C
-from bdeissct_dl.tree_encoder import SCALING_FACTOR
-
-for model in ('BD', 'BDCT', 'BDEI', 'BDEICT', 'BDSS', 'BDSSCT', 'BDEISS', 'BDEISSCT'):
-    df = pd.read_csv(f'/home/azhukova/projects/bdeissct_dl/simulations_bdeissct/test/200_500/{model}/trees.csv.xz')
-    print(model, REPRODUCTIVE_NUMBER, np.quantile(df[REPRODUCTIVE_NUMBER], [0, 0.5, 1]))
-    print(model, INFECTION_DURATION, np.quantile(df[INFECTION_DURATION] * df[SCALING_FACTOR], [0, 0.5, 1]))
-    print(model, RHO, np.quantile(df[RHO], [0, 0.5, 1]))
-    if 'EI' in model:
-        print(model, F_E, np.quantile(df[F_E], [0, 0.5, 1]))
-        print(df[df[F_E] > 1].index)
-    if 'SS' in model:
-        print(model, F_S, np.quantile(df[F_S], [0, 0.5, 1]))
-        print(model, X_S, np.quantile(df[X_S], [0, 0.5, 1]))
-    if 'CT' in model:
-        print(model, UPSILON, np.quantile(df[UPSILON], [0, 0.5, 1]))
-        print(model, X_C, np.quantile(df[X_C], [0, 0.5, 1]))
-    print('---')

bdext-0.1.61.dist-info/RECORD

@@ -1,23 +0,0 @@
-README.md,sha256=Fk-VeZXo2zltZ9NXdFnnHS3ETwtiBPRiZ86ttUQUgTE,5894
-bdeissct_dl/__init__.py,sha256=glAW73vlD9Abbb_Fto-sKys078qVEn5iTcx2Mq3Z72s,361
-bdeissct_dl/assess_R_CT.py,sha256=MMozDi4zMeNkzIbg8fYYl0-H_ncHtiQUJR8EkVKLV10,1095
-bdeissct_dl/bdeissct_model.py,sha256=4jJs_8NyvrHUve2VeIg9Hj2mc78a7ZuU6xBiI0ZkaMs,3566
-bdeissct_dl/dl_model.py,sha256=q8RFbbd2n52Y0_HMKSEHdIgBouE4LbHL5CZO3M_3G3E,7364
-bdeissct_dl/estimator.py,sha256=UIQAy62I0_2HKagfck9WBGbbHU6l_WfRypP9CyeHrFE,7313
-bdeissct_dl/estimator_ct.py,sha256=YgbFN1vY86Lcp_46QG1kd38CC4K2Crv2S8Hv7-Cz0Xg,2802
-bdeissct_dl/main_covid.py,sha256=wCeJgc4XzEPjcVCaQt_-zGiVX0wdpQhFq2qh9xQzc7w,2882
-bdeissct_dl/model_finder.py,sha256=TC6EcIE6rBO6PefaYfn2reEl6HPkORbIgTzQGsDoXcU,1763
-bdeissct_dl/model_serializer.py,sha256=Ojhy-fUElc4NClhJaF0EWnrAJGK0omk8e7cwwrBk3Yk,3768
-bdeissct_dl/pinball_loss.py,sha256=Xg2jFDlwPOt0AhBY574lWB0yRyuA0bQRiyOYHGL6P54,1602
-bdeissct_dl/scaler_fitting.py,sha256=wHKCfsFl9ig6U5W17imuKSEn9Xg295S37q0gqF-LRFI,2361
-bdeissct_dl/sumstat_checker.py,sha256=BHMgoqjymHc3Ic-Sv7m-zuvCeLlCt4OCDVaKDltSII0,1867
-bdeissct_dl/train_ct.py,sha256=axo4OjeCYbx-VBvVaCspnTmqdrORZ1f87ANvFBLvNqM,5459
-bdeissct_dl/training.py,sha256=WC0epgi7kW0ER6hxjoxwEW15UbFkv1OHDqrBZg4R3uk,8944
-bdeissct_dl/tree_encoder.py,sha256=WrrSk_HXOF_rAKHpU7u9_i_gCmp5tz7Tk_Jvbwx0N_g,19193
-bdeissct_dl/tree_manager.py,sha256=UXxUVmEkxwUhKpJeACVgiXZ8Kp1o_hiv8Qb80b6qmVU,11814
-bdext-0.1.61.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-bdext-0.1.61.dist-info/METADATA,sha256=JHeS2OB4iplQF2vHlESLzDJn3kAoitp2M8yCIKgZIac,6834
-bdext-0.1.61.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-bdext-0.1.61.dist-info/entry_points.txt,sha256=En4b5js0-eCuBp0Jiqye0fte6svXbXSLiSJOW_KdzV4,286
-bdext-0.1.61.dist-info/top_level.txt,sha256=z4dadFfcLghr4lwROy7QR3zEICpa-eCPT6mmcoHeEJY,12
-bdext-0.1.61.dist-info/RECORD,,