format filues (#212)

Author: strickvl

bank_subscription_prediction/__init__.py

@@ -1 +1 @@
-"""Bank Subscription Prediction Project using ZenML.""" 
+"""Bank Subscription Prediction Project using ZenML."""

bank_subscription_prediction/pipelines/__init__.py

@@ -1 +0,0 @@
- 

bank_subscription_prediction/pipelines/training_pipeline.py

@@ -1,11 +1,12 @@
-from zenml import pipeline
-from steps.data_loader import load_data
+import logging
+
 from steps.data_cleaner import clean_data_step
+from steps.data_loader import load_data
 from steps.data_preprocessor import preprocess_data_step
 from steps.data_splitter import split_data_step
-from steps.model_trainer import train_xgb_model_with_feature_selection
 from steps.model_evaluator import evaluate_model
-import logging
+from steps.model_trainer import train_xgb_model_with_feature_selection
+from zenml import pipeline
 
 # Set up logger
 logger = logging.getLogger(__name__)

bank_subscription_prediction/predict_bank_cd_subs_by_xgboost_clf_for_imbalance_dataset.ipynb

@@ -211,10 +211,9 @@
     "##   1. reading various files into the dataframe\n",
     "##   2. to performa various data manipulation tasks\n",
     "\n",
-    "import pandas as pd\n",
-    "\n",
     "# load numpy\n",
-    "import numpy as np"
+    "import numpy as np\n",
+    "import pandas as pd"
    ]
   },
   {
@@ -238,33 +237,27 @@
     "# for custom transformer\n",
     "from sklearn.base import BaseEstimator, TransformerMixin\n",
     "\n",
-    "# for creating pipeline\n",
-    "from sklearn.pipeline import Pipeline, FeatureUnion\n",
-    "\n",
     "# for cross validation\n",
     "from sklearn.cross_validation import train_test_split\n",
-    "from sklearn.cross_validation import train_test_split\n",
-    "from sklearn import cross_validation\n",
-    "from sklearn.model_selection import cross_val_predict, cross_val_score\n",
-    "\n",
-    "# for various metrics and reporting\n",
-    "from sklearn import metrics\n",
-    "from sklearn.metrics import roc_curve\n",
-    "from sklearn.metrics import precision_recall_curve\n",
-    "from sklearn.metrics import accuracy_score\n",
-    "from sklearn.metrics import confusion_matrix\n",
-    "from sklearn.metrics import classification_report\n",
-    "from sklearn.metrics import accuracy_score\n",
-    "from sklearn.metrics import confusion_matrix\n",
     "\n",
     "# feature selection\n",
     "from sklearn.feature_selection import SelectFromModel\n",
     "\n",
-    "# xgboost library\n",
-    "from xgboost import XGBClassifier\n",
+    "# for various metrics and reporting\n",
+    "from sklearn.metrics import (\n",
+    "    classification_report,\n",
+    "    confusion_matrix,\n",
+    "    precision_recall_curve,\n",
+    "    roc_curve,\n",
+    ")\n",
+    "from sklearn.model_selection import cross_val_predict\n",
     "\n",
+    "# for creating pipeline\n",
+    "from sklearn.pipeline import FeatureUnion, Pipeline\n",
+    "\n",
+    "# xgboost library\n",
     "# plot feature importance\n",
-    "from xgboost import plot_importance, plot_tree"
+    "from xgboost import XGBClassifier, plot_importance"
    ]
   },
   {
@@ -313,11 +306,11 @@
     "# following code is for IBM Watson Studio loading. note if you are not using Watson studion ,\n",
     "# one can skip this.\n",
     "\n",
-    "import sys\n",
     "import types\n",
+    "\n",
+    "import ibm_boto3\n",
     "import pandas as pd\n",
     "from botocore.client import Config\n",
-    "import ibm_boto3\n",
     "\n",
     "\n",
     "def __iter__(self):\n",
@@ -1248,10 +1241,10 @@
     "# Definition of the CategoricalEncoder class, copied from PR #9151.\n",
     "# Just run this cell, or copy it to your code, do not try to understand it (yet).\n",
     "\n",
+    "from scipy import sparse\n",
     "from sklearn.base import BaseEstimator, TransformerMixin\n",
-    "from sklearn.utils import check_array\n",
     "from sklearn.preprocessing import LabelEncoder\n",
-    "from scipy import sparse\n",
+    "from sklearn.utils import check_array\n",
     "\n",
     "\n",
     "class CategoricalEncoder(BaseEstimator, TransformerMixin):\n",

bank_subscription_prediction/run.py

@@ -1,7 +1,8 @@
 """Main module to run the Bank Subscription Prediction pipeline."""
 
-import click
 import logging
+
+import click
 from pipelines.training_pipeline import bank_subscription_training_pipeline
 
 logger = logging.getLogger(__name__)

bank_subscription_prediction/steps/__init__.py

@@ -1 +0,0 @@
- 

bank_subscription_prediction/steps/data_loader.py

@@ -1,12 +1,13 @@
-import pandas as pd
+import logging
 import os
-import requests
-from zenml import step
 
 # Download the zip file
 import zipfile
 from io import BytesIO
-import logging
+
+import pandas as pd
+import requests
+from zenml import step
 
 # Set up logger
 logger = logging.getLogger(__name__)

bank_subscription_prediction/steps/data_preprocessor.py

@@ -1,7 +1,8 @@
+import logging
+from typing import List
+
 import pandas as pd
 from zenml import step
-from typing import List
-import logging
 
 # Set up logger
 logger = logging.getLogger(__name__)

bank_subscription_prediction/steps/data_splitter.py

@@ -1,8 +1,9 @@
+import logging
+from typing import Annotated, Tuple
+
 import pandas as pd
-from zenml import step
 from sklearn.model_selection import train_test_split
-from typing import Tuple, Annotated
-import logging
+from zenml import step
 
 # Set up logger
 logger = logging.getLogger(__name__)

bank_subscription_prediction/steps/model_evaluator.py

@@ -1,26 +1,20 @@
+from typing import Dict, List, Tuple
+
+import numpy as np
 import pandas as pd
+import plotly.express as px
+import plotly.graph_objects as go
 import xgboost as xgb
 from sklearn.feature_selection import SelectFromModel
 from sklearn.metrics import (
     accuracy_score,
-    classification_report,
+    auc,
     confusion_matrix,
-    roc_curve,
     precision_recall_curve,
-    auc,
-    roc_auc_score,
+    roc_curve,
 )
-import matplotlib.pyplot as plt
-import plotly.express as px
-import plotly.graph_objects as go
-from plotly.subplots import make_subplots
-import numpy as np
-import json
-from typing import Dict, Any, List, Tuple
 from typing_extensions import Annotated
-
 from zenml import step
-from zenml.materializers.built_in_materializer import BuiltInMaterializer
 from zenml.types import HTMLString