From 4a345b832cb92dbb9cf7c67c52f56a34b9d8fac0 Mon Sep 17 00:00:00 2001
From: coolneng <akasroua@gmail.com>
Date: Sun, 13 Dec 2020 22:24:52 +0100
Subject: [PATCH] Fix data normalization for knn
---
src/P1/processing.py | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/src/P1/processing.py b/src/P1/processing.py
index fd41bdf..7edbbd0 100644
--- a/src/P1/processing.py
+++ b/src/P1/processing.py
@@ -8,7 +8,7 @@ from sklearn.metrics import confusion_matrix, roc_auc_score, roc_curve
from sklearn.naive_bayes import GaussianNB
from sklearn.neighbors import KNeighborsClassifier
from sklearn.neural_network import MLPClassifier
-from sklearn.preprocessing import scale
+from sklearn.preprocessing import MinMaxScaler
from sklearn.svm import LinearSVC
from sklearn.tree import DecisionTreeClassifier
@@ -32,7 +32,8 @@ def predict_data(data, target, model, results):
model_name = model
model = choose_model(model=model)
if model_name == "knn":
- data = scale(data)
+ scaler = MinMaxScaler()
+ data[data.columns] = scaler.fit_transform(data[data.columns])
confusion_matrices, auc, fpr, tpr = [], [], [], []
for train_index, test_index in split_k_sets(data):
model.fit(data.iloc[train_index], target.iloc[train_index])