From 11ca03861e85ce46a7c6120e31768c2f3a089d3b Mon Sep 17 00:00:00 2001 From: Pritimay Sarkar Date: Tue, 26 Sep 2023 04:39:20 +0530 Subject: [PATCH] check logistic regression accuracy --- scripts/logistic.py | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) create mode 100644 scripts/logistic.py diff --git a/scripts/logistic.py b/scripts/logistic.py new file mode 100644 index 0000000..2a51665 --- /dev/null +++ b/scripts/logistic.py @@ -0,0 +1,31 @@ +import pandas as pd +from sklearn.model_selection import train_test_split +from sklearn.linear_model import LogisticRegression +from sklearn.preprocessing import LabelEncoder +from sklearn.metrics import accuracy_score, classification_report + +data = pd.read_excel('/Users/apple/Downloads/21092023-July_Sept.xlsx', sheet_name="op") +data = data.dropna() +print(data) + +label_encoder = LabelEncoder() +categorical_cols = ['Gender', 'Caste', 'Category', 'Marital Status', 'Blood Group'] +for col in categorical_cols: + data[col] = label_encoder.fit_transform(data[col]) + +X = data[['Age', 'Gender', 'Caste', 'Category', 'Marital Status']] +y = data['Test Result'] + +X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42) + +model = LogisticRegression() +model.fit(X_train, y_train) + +y_pred = model.predict(X_test) + +accuracy = accuracy_score(y_test, y_pred) +classification_report_result = classification_report(y_test, y_pred) + +print(f"Accuracy: {accuracy}") +print("Classification Report:") +print(classification_report_result)