create dataset

scripts/dataset_001.py

@@ -0,0 +1,36 @@
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.naive_bayes import GaussianNB
+from sklearn.preprocessing import LabelEncoder
+from sklearn.metrics import accuracy_score, classification_report, confusion_matrix
+import pickle
+import matplotlib.pyplot as plt
+import seaborn as sns
+import os
+
+curdir = os.getcwd()
+path_delim = '/'
+df = pd.read_csv(curdir + path_delim + 'data/bquxjob_6ffc1cff_18c02a130c1.csv')
+df = df.dropna()
+print(df)
+
+print(df["classificationResult"].unique())
+
+df['testResult'] = df['classificationResult']
+df.loc[df['testResult'] == 'Normal', 'testResult'] = 'Normal'
+df.loc[df['testResult'] == 'Sickle Cell Trait', 'testResult'] = 'SCT'
+df.loc[df['testResult'] == 'Sickle Cell Disease', 'testResult'] = 'SCD'
+df.loc[df['testResult'] == 'Positive for Sickle Cell. HPLC for Confirmation', 'testResult'] = 'Inconclusive'
+df.loc[df['testResult'] == 'Inconclusive. Very low Absorbance - Repeat test with Higher Blood Volume', 'testResult'] = 'Inconclusive'
+df.loc[df['testResult'] == 'Negative Borderline. Repeat Test', 'testResult'] = 'Inconclusive'
+df.loc[df['testResult'] == 'Inconclusive. Very low Absorbance - Repeat test with Higher Blood Volume', 'testResult'] = 'Inconclusive'
+df.loc[df['testResult'] == 'Inconclusive. Repeat with test with lower volume of blood', 'testResult'] = 'Inconclusive'
+print(df.groupby(["testResult"]).describe())
+
+df = df.drop(['classificationResult', "finalResult"], axis=1)
+
+writer = pd.ExcelWriter(curdir + path_delim + "data/vertex_dataset3.xlsx", engine = 'openpyxl')
+df.to_excel(writer, sheet_name = 'op', index=False)
+df.to_csv(curdir + path_delim + "data/vertex_dataset3.csv", index=False)
+# df_count.to_excel(writer, sheet_name = "count")
+writer.close()