ddi-fw 0.0.149__py3-none-any.whl → 0.0.151__py3-none-any.whl

ddi_fw/test/jaccard_similarity.py

@@ -1,85 +0,0 @@
-import pandas as pd
-
-# data = {'A': [1, 1, 1, 0, 0],
-#         'B': [0, 1, 1, 1, 0],
-#         'C': [0, 0, 1, 1, 1]}
-
-# df = pd.DataFrame(data)
-
-
-# from scipy.spatial.distance import pdist, squareform
-
-# jaccard_dist = pdist(df.values, metric='jaccard')
-# jaccard_dist_matrix = squareform(jaccard_dist)
-
-# print(jaccard_dist_matrix)
-
-
-# import pandas as pd
-# from scipy.spatial.distance import euclidean, pdist, squareform
-
-
-# def similarity_func(u, v):
-#     return 1/(1+euclidean(u,v))
-
-# DF_var = pd.DataFrame.from_dict({"s1":[1.2,3.4,10.2],"s2":[1.4,3.1,10.7],"s3":[2.1,3.7,11.3],"s4":[1.5,3.2,10.9]})
-# DF_var.index = ["g1","g2","g3"]
-
-# dists = pdist(DF_var, similarity_func)
-# DF_euclid = pd.DataFrame(squareform(dists), columns=DF_var.index, index=DF_var.index)
-
-# print(DF_euclid)
-
-
-from sklearn.metrics import jaccard_score
-import seaborn as sns
-import matplotlib.pyplot as plt
-
-data = [[0, 1, 0], [0, 1, 1], [0, 1, 0], [1, 1, 1], [1, 0, 1]]
-
-similarity_matrix = []
-for i in range(len(data)):
-        row = []
-        for j in range(len(data)):
-          row.append(jaccard_score(data[i], data[j]))
-        similarity_matrix.append(row)
-
-sns.heatmap(pd.DataFrame(similarity_matrix), annot=True, cmap="YlGnBu")
-plt.show()
-
-
-# https://stackoverflow.com/questions/35639571/python-pandas-distance-matrix-using-jaccard-similarity
-import pandas as pd
-entries = [
-    {'id':'1', 'category1':'100', 'category2': '0', 'category3':'100'},
-    {'id':'2', 'category1':'100', 'category2': '0', 'category3':'100'},
-    {'id':'3', 'category1':'0', 'category2': '100', 'category3':'100'},
-    {'id':'4', 'category1':'100', 'category2': '100', 'category3':'100'},
-    {'id':'5', 'category1':'100', 'category2': '0', 'category3':'100'}
-           ]
-df = pd.DataFrame(entries)
-
-from scipy.spatial.distance import squareform
-from scipy.spatial.distance import pdist, jaccard
-
-res = 1 - pdist(df[['category1','category2','category3']], 'jaccard')
-# squareform(res)
-distance = pd.DataFrame(squareform(res), index=df.index, columns= df.index)
-print(distance)
-
-entries2 = [
-    {'id':'1', 'cat':['p1','p2','p3']},
-    {'id':'2', 'cat':['p3','p4','p5']},
-    {'id':'3', 'cat':['p5','p6','p7']},
-           ]
-df2 = pd.DataFrame(entries2)
-
-c = df2['cat']
-
-y = set()
-
-for x in c:
-  for k in x:
-    y.add(k)
-
-print(y)

ddi_fw/test/mlfow_test.py

@@ -1,165 +0,0 @@
-# import mlflow
-# from mlflow import tensorflow
-# mlflow.set_tracking_uri("sqlite:///mlflow.db")
-# mlflow.set_experiment("multi-class-ddi-classification")
-
-
-# def mlp_mlflow_run(
-#     name,
-#     model_params,
-#     train_params,
-#     train_dataset,
-#     val_dataset,
-#     test_dataset,
-#     y_test,
-# ):
-#     with mlflow.start_run(run_name=name):
-#         mlflow.log_params(model_params)
-#         mlflow.log_params(train_params)
-#         mlflow.set_tag("model_name", "MLP")
-
-         
-
-
-#         mlflow.log_metric("accuracy", accuracy)
-#         mlflow.tensorflow.log_model(mlp, "tf_models") #folder
-
-import mlflow
-import pandas as pd
-import tensorflow as tf
-import matplotlib.pyplot as plt
-from sklearn.model_selection import train_test_split
-from sklearn.metrics import mean_squared_error
-from sklearn.datasets import fetch_california_housing
-import tensorflow_addons as tfa
-
-from tensorflow.keras.callbacks import EarlyStopping
- 
-
-from sklearn.preprocessing import StandardScaler
-from sklearn.ensemble import RandomForestRegressor
-import seaborn as sns
-
-from tensorflow.keras.layers import Dense, Dropout
-from tensorflow.keras.models import Sequential
-from tensorflow.keras.losses import MeanSquaredError
-
-
-mlflow.set_tracking_uri("sqlite:///mlflow.db")
-mlflow.set_experiment("income")
-
-
-dset = fetch_california_housing()
-data = dset['data']
-y = dset['target']
-LABEL = dset['target_names'][0]
-
-NUMERIC_FEATURES = ['MedInc', 'HouseAge', 'AveRooms', 'AveBedrms', 'Population', 'AveOccup', 'Longitude', 'Latitude']
-FEATURES = NUMERIC_FEATURES
-
-data = pd.DataFrame(data, columns=dset['feature_names'])
-data[LABEL] = y
-
-data.head()
-
-train_data, test_data = train_test_split(data, test_size=0.2)
-print(f"Train dataset shape: {train_data.shape}")
-print(f"Test dataset shape: {test_data.shape}")
-
-
-X_train, X_val = train_test_split(train_data, test_size=0.2)
-
-sc = StandardScaler()
-X_train.loc[:, NUMERIC_FEATURES] = sc.fit_transform(X_train[NUMERIC_FEATURES])
-X_val.loc[:, NUMERIC_FEATURES] = sc.transform(X_val[NUMERIC_FEATURES])
-test_data.loc[:, NUMERIC_FEATURES] = sc.transform(test_data[NUMERIC_FEATURES])
-
-
-def build_mlp(params):
-    mlp = Sequential([
-        Dense(params["layer1_size"], activation=params['activation']),
-        Dropout(params['dropout_rate']),
-        Dense(params["layer2_size"], activation=params['activation']),
-        Dropout(params['dropout_rate']),
-        Dense(params["layer3_size"], activation=params['activation']),
-        Dense(1, activation='relu')
-    ])
-    return mlp
-
-def train_mlp(mlp, train_params, train_dataset, val_dataset):
-    optimizer = tfa.optimizers.AdamW(
-        learning_rate=train_params["learning_rate"],
-        weight_decay=train_params["weight_decay"],
-    )
-    mlp.compile(
-        optimizer=optimizer,
-        loss=MeanSquaredError(name="mse"),
-        metrics=[tf.keras.metrics.RootMeanSquaredError(name="rmse")]
-    )
-
-    early = EarlyStopping(
-        monitor="val_loss",
-        mode="min",
-        patience=train_params["early_stop_patience"],
-        restore_best_weights=True,
-    )
-    callback_list = [early]
-
-    hist = mlp.fit(
-        train_dataset,
-        epochs=train_params["num_epochs"],
-        validation_data=val_dataset,
-        callbacks=callback_list,
-    )
-    return mlp
-
-
-def mlp_mlflow_run(
-    name,
-    mlp_params,
-    train_params,
-    train_dataset,
-    val_dataset,
-    test_dataset,
-    y_test,
-):
-    with mlflow.start_run(run_name=name):
-        mlflow.log_params(mlp_params)
-        mlflow.log_params(train_params)
-        mlflow.set_tag("model_name", "MLP")
-        mlp = build_mlp(mlp_params)
-        mlp = train_mlp(mlp, train_params, train_dataset, val_dataset)
-        test_preds = mlp.predict(test_dataset)
-        test_rms = mean_squared_error(
-            y_test, test_preds.ravel(), squared=False
-        )
-        mlflow.log_metric("test_rmse", test_rms)
-        mlflow.tensorflow.log_model(mlp, "tf_models")
-
-        
-# To TF Dataset
-mlp_train_ds = tf.data.Dataset.from_tensor_slices((X_train[FEATURES], X_train[LABEL])).batch(512).shuffle(512*4).prefetch(512)
-mlp_val_ds = tf.data.Dataset.from_tensor_slices((X_val[FEATURES], X_val[LABEL])).batch(512).shuffle(512*4).prefetch(512)
-mlp_test_ds = tf.data.Dataset.from_tensor_slices(test_data[FEATURES]).batch(512).prefetch(512)
-
-mlp_params = {
-    "layer1_size": 512,
-    "layer2_size": 128,
-    "layer3_size": 64,
-    "dropout_rate": 0.3,
-    "activation": 'relu'
-
-}
-train_params = dict(
-    learning_rate=0.001, weight_decay=0.00001, early_stop_patience=10, num_epochs=1000
-)
-
-mlp_mlflow_run(
-    "mlp_base",
-    mlp_params,
-    train_params,
-    mlp_train_ds,
-    mlp_val_ds,
-    mlp_test_ds,
-    test_data[LABEL],
-)

ddi_fw/test/sklearn-tfidf.py

@@ -1,16 +0,0 @@
-from sklearn.feature_extraction.text import TfidfTransformer
-from sklearn.feature_extraction.text import CountVectorizer
-from sklearn.pipeline import Pipeline
-corpus = ['this is the first document',
-          'this document is the second document',
-          'and this is the third one',
-          'is this the first document']
-vocabulary = ['this', 'document', 'first', 'is', 'second', 'the',
-              'and', 'one']
-pipe = Pipeline([('count', CountVectorizer(vocabulary=vocabulary)),
-                  ('tfid', TfidfTransformer())]).fit(corpus)
-pipe['count'].transform(corpus).toarray()
- 
-pipe['tfid'].idf_
-
-pipe.transform(corpus).shape

ddi_fw/test/test.py

@@ -1,93 +0,0 @@
-from rdkit import Chem
-from rdkit.Chem import AllChem
-
-from urllib.request import urlopen
-from urllib.parse import quote
-
-from Bio.KEGG import REST
-
-
-x = REST.kegg_find(database='drug', query='D03136')
-y = x.read()
-print(x)
-def CIRconvert(ids):
-    try:
-        url = 'http://cactus.nci.nih.gov/chemical/structure/' + quote(ids) + '/smiles'
-        ans = urlopen(url).read().decode('utf8')
-        return ans
-    except:
-        return 'Did not work'
-
-# identifiers  = ['3-Methylheptane', 'Aspirin', 'Diethylsulfate', 'Diethyl sulfate', '50-78-2', 'Adamant']
-
-# smiles = []
-
-# for ids in identifiers :
-#     smiles.append(CIRconvert(ids))
-#     # print(ids, CIRconvert(ids))
-
-
-# from rdkit.Chem import SaltRemover
-
-# remover = SaltRemover(defnData="[Na+]\\nCC(=O)O", defnFormat=SaltRemover.InputFormat.SMILES)
-# len(remover)
-
-# remover = SaltRemover(defnFormat=SaltRemover.InputFormat.SMILES, defnData="[Cl]")
-# mol = Chem.MolFromSmiles(smiles[0])
-
-# morgan_hashed = AllChem.GetMorganFingerprintAsBitVect(mol,2,nBits=881)
-# print(morgan_hashed.ToBitString())
-
-#https://go.drugbank.com/structures/small_molecule_drugs/DB01076.smiles
-
-# targets -> target -> polypeptide
-# enzymes -> enzyme -> polypeptide
-smiles = {'DB001075':'[H][C@]12OC[C@@H](O[N+]([O-])=O)[C@@]1([H])OC[C@@H]2O',
-          'DB001076':'CC(C)C1=C(C(=O)NC2=CC=CC=C2)C(=C(N1CC[C@@H](O)C[C@@H](O)CC(O)=O)C1=CC=C(F)C=C1)C1=CC=CC=C1',
-          'DB001077':'CC(C)C1=C(C(=O)NC2=CC=CC=C2)C(=C(N1CC[C@@H](O)C[C@@H](O)CC(O)=O)C1=CC=C(F)C=C1)C1=CC=CC=C1',
-          }
-morgan_hashed_dict = {}
-# smile = '[H][C@]12OC[C@@H](O[N+]([O-])=O)[C@@]1([H])OC[C@@H]2O'
-# smile = 'CC(C)C1=C(C(=O)NC2=CC=CC=C2)C(=C(N1CC[C@@H](O)C[C@@H](O)CC(O)=O)C1=CC=C(F)C=C1)C1=CC=CC=C1'
-
-for drugbank_id, smile in smiles.items():
-    mol = Chem.MolFromSmiles(smile)
-    morgan_hashed = AllChem.GetMorganFingerprintAsBitVect(mol,2,nBits=881)
-    morgan_hashed_dict.update({drugbank_id: morgan_hashed.ToList()})
-    # print(morgan_hashed.ToBitString())
-
-
-import pandas as pd
-df = pd.DataFrame(morgan_hashed_dict.values())
-
-from scipy.spatial.distance import pdist, squareform
-
-jaccard_dist = 1 - pdist(df.values, metric='jaccard')
-jaccard_dist_matrix = squareform(jaccard_dist)
-
-print(jaccard_dist_matrix)
-
-
-
-import numpy as np
-import pandas as pd
-
-# df = pd.DataFrame({'sample':[np.array(range(99999, 99999 + 1000))]}) 
-df = pd.DataFrame({'sample':[np.random.random_sample((1000,))]}) 
-
-df['sample'] = df['sample'].apply(lambda x: str(x).replace('\n', ''))
-
-df.to_csv('sample.csv', index=False)
-
-
-from ast import literal_eval
-new_df = pd.read_csv('sample.csv')
-def fnc(x):
-     return np.array(literal_eval(x.replace('[ ', '[').replace(' ', ',')))
-# new_df['array_col'] = new_df['sample'].apply(lambda x: np.array(literal_eval(x.replace('[ ', '[').replace(' ', ','))))
-new_df['array_col'] = new_df['sample'].apply(lambda x: fnc(x))
-
-
-
-print(new_df.loc[0, 'array_col'][0:10])
-

ddi_fw/test/torch_cuda_test.py

@@ -1,9 +0,0 @@
-import torch
-print(f'PyTorch version: {torch.__version__}')
-print('*'*10)
-print(f'_CUDA version: ')
-# !nvcc --version
-print('*'*10)
-print(f'CUDNN version: {torch.backends.cudnn.version()}')
-print(f'Available GPU devices: {torch.cuda.device_count()}')
-print(f'Device Name: {torch.cuda.get_device_name()}')

ddi_fw/test/type_guarding_test.py

@@ -1,18 +0,0 @@
-# from typing import List
-# from itertools import product
-# from ddi_fw.utils import ZipHelper
-
-# from ddi_fw.utils.enums import DrugBankTextDataTypes, UMLSCodeTypes
-
-# def generate_pairs(umls_code_types:  List[UMLSCodeTypes] = None, text_types:  List[DrugBankTextDataTypes] = None):
-#     _umls_codes = [t.value[0] for t in umls_code_types]
-#     _text_types = [t.value[0] for t in text_types]
-#     items = [f'{item[0]}_{item[1]}' for item in product(_umls_codes, _text_types)]
-#     print(items)
-
-
-# if __name__ == "__main__":
-#     generate_pairs(umls_code_types=[UMLSCodeTypes.TUI, UMLSCodeTypes.ENTITIES], text_types= [DrugBankTextDataTypes.DESCRIPTION])
-
-
-# # reveal_type(UMLSCodeTypes.ENTITIES)  # Revealed type is "Literal[Direction.up]?"