From 08da36c175eee583dfa8fb8659c33f53dd98f477 Mon Sep 17 00:00:00 2001
From: BipanjitGill <120119876+BipanjitGill@users.noreply.github.com>
Date: Wed, 25 Oct 2023 13:35:12 +0530
Subject: [PATCH 1/5] Add files via upload

---
 ML_Algorithms/K-Means/kMeans.py | 48 +++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)
 create mode 100644 ML_Algorithms/K-Means/kMeans.py

diff --git a/ML_Algorithms/K-Means/kMeans.py b/ML_Algorithms/K-Means/kMeans.py
new file mode 100644
index 0000000..f87dc29
--- /dev/null
+++ b/ML_Algorithms/K-Means/kMeans.py
@@ -0,0 +1,48 @@
+import numpy as np
+
+class K_Means:
+    def __init__(self, k=2, max_iter=100, tol=0.001):
+        self.k = k
+        self.max_iter = max_iter
+        self.tol = tol
+        
+
+    def fit(self,data):
+
+        self.centroids = {}
+
+        for i in range(self.k):
+            self.centroids[i] = data[i]
+
+        for i in range(self.max_iter):
+            self.classifications = {}
+
+            for i in range(self.k):
+                self.classifications[i] = []
+
+            for featureset in data:
+                distances = [np.linalg.norm(featureset-self.centroids[centroid]) for centroid in self.centroids]
+                classification = distances.index(min(distances))
+                self.classifications[classification].append(featureset)
+
+            prev_centroids = dict(self.centroids)
+
+            for classification in self.classifications:
+                self.centroids[classification] = np.average(self.classifications[classification],axis=0)
+
+            optimized = True
+
+            for c in self.centroids:
+                original_centroid = prev_centroids[c]
+                current_centroid = self.centroids[c]
+                if np.sum((current_centroid-original_centroid)/original_centroid*100.0) > self.tol:
+                    # print(np.sum((current_centroid-original_centroid)/original_centroid*100.0))
+                    optimized = False
+
+            if optimized:
+                break
+
+    def predict(self,data):
+        distances = [np.linalg.norm(data-self.centroids[centroid]) for centroid in self.centroids]
+        classification = distances.index(min(distances))
+        return classification
\ No newline at end of file

From 2aa13a7ce2d94faa3448148dd15fe09b5e0f1d16 Mon Sep 17 00:00:00 2001
From: BipanjitGill <120119876+BipanjitGill@users.noreply.github.com>
Date: Wed, 25 Oct 2023 15:16:04 +0530
Subject: [PATCH 2/5] create knn.py

---
 ML_Algorithms/KNN/iris_test.csv  |  31 ++++++++
 ML_Algorithms/KNN/iris_train.csv | 121 +++++++++++++++++++++++++++++++
 ML_Algorithms/KNN/knn.py         |  32 ++++++++
 3 files changed, 184 insertions(+)
 create mode 100644 ML_Algorithms/KNN/iris_test.csv
 create mode 100644 ML_Algorithms/KNN/iris_train.csv
 create mode 100644 ML_Algorithms/KNN/knn.py

diff --git a/ML_Algorithms/KNN/iris_test.csv b/ML_Algorithms/KNN/iris_test.csv
new file mode 100644
index 0000000..c0337a2
--- /dev/null
+++ b/ML_Algorithms/KNN/iris_test.csv
@@ -0,0 +1,31 @@
+SepalLengthCm,SepalWidthCm,PetalLengthCm,PetalWidthCm,Species
+6.1,2.8,4.7,1.2,Iris-versicolor
+5.7,3.8,1.7,0.3,Iris-setosa
+7.7,2.6,6.9,2.3,Iris-virginica
+6,2.9,4.5,1.5,Iris-versicolor
+6.8,2.8,4.8,1.4,Iris-versicolor
+5.4,3.4,1.5,0.4,Iris-setosa
+5.6,2.9,3.6,1.3,Iris-versicolor
+6.9,3.1,5.1,2.3,Iris-virginica
+6.2,2.2,4.5,1.5,Iris-versicolor
+5.8,2.7,3.9,1.2,Iris-versicolor
+6.5,3.2,5.1,2,Iris-virginica
+4.8,3,1.4,0.1,Iris-setosa
+5.5,3.5,1.3,0.2,Iris-setosa
+4.9,3.1,1.5,0.1,Iris-setosa
+5.1,3.8,1.5,0.3,Iris-setosa
+6.3,3.3,4.7,1.6,Iris-versicolor
+6.5,3,5.8,2.2,Iris-virginica
+5.6,2.5,3.9,1.1,Iris-versicolor
+5.7,2.8,4.5,1.3,Iris-versicolor
+6.4,2.8,5.6,2.2,Iris-virginica
+4.7,3.2,1.6,0.2,Iris-setosa
+6.1,3,4.9,1.8,Iris-virginica
+5,3.4,1.6,0.4,Iris-setosa
+6.4,2.8,5.6,2.1,Iris-virginica
+7.9,3.8,6.4,2,Iris-virginica
+6.7,3,5.2,2.3,Iris-virginica
+6.7,2.5,5.8,1.8,Iris-virginica
+6.8,3.2,5.9,2.3,Iris-virginica
+4.8,3,1.4,0.3,Iris-setosa
+4.8,3.1,1.6,0.2,Iris-setosa
diff --git a/ML_Algorithms/KNN/iris_train.csv b/ML_Algorithms/KNN/iris_train.csv
new file mode 100644
index 0000000..7a603e6
--- /dev/null
+++ b/ML_Algorithms/KNN/iris_train.csv
@@ -0,0 +1,121 @@
+SepalLengthCm,SepalWidthCm,PetalLengthCm,PetalWidthCm,Species
+4.6,3.6,1,0.2,Iris-setosa
+5.7,4.4,1.5,0.4,Iris-setosa
+6.7,3.1,4.4,1.4,Iris-versicolor
+4.8,3.4,1.6,0.2,Iris-setosa
+4.4,3.2,1.3,0.2,Iris-setosa
+6.3,2.5,5,1.9,Iris-virginica
+6.4,3.2,4.5,1.5,Iris-versicolor
+5.2,3.5,1.5,0.2,Iris-setosa
+5,3.6,1.4,0.2,Iris-setosa
+5.2,4.1,1.5,0.1,Iris-setosa
+5.8,2.7,5.1,1.9,Iris-virginica
+6,3.4,4.5,1.6,Iris-versicolor
+6.7,3.1,4.7,1.5,Iris-versicolor
+5.4,3.9,1.3,0.4,Iris-setosa
+5.4,3.7,1.5,0.2,Iris-setosa
+5.5,2.4,3.7,1,Iris-versicolor
+6.3,2.8,5.1,1.5,Iris-virginica
+6.4,3.1,5.5,1.8,Iris-virginica
+6.6,3,4.4,1.4,Iris-versicolor
+7.2,3.6,6.1,2.5,Iris-virginica
+5.7,2.9,4.2,1.3,Iris-versicolor
+7.6,3,6.6,2.1,Iris-virginica
+5.6,3,4.5,1.5,Iris-versicolor
+5.1,3.5,1.4,0.2,Iris-setosa
+7.7,2.8,6.7,2,Iris-virginica
+5.8,2.7,4.1,1,Iris-versicolor
+5.2,3.4,1.4,0.2,Iris-setosa
+5,3.5,1.3,0.3,Iris-setosa
+5.1,3.8,1.9,0.4,Iris-setosa
+5,2,3.5,1,Iris-versicolor
+6.3,2.7,4.9,1.8,Iris-virginica
+4.8,3.4,1.9,0.2,Iris-setosa
+5,3,1.6,0.2,Iris-setosa
+5.1,3.3,1.7,0.5,Iris-setosa
+5.6,2.7,4.2,1.3,Iris-versicolor
+5.1,3.4,1.5,0.2,Iris-setosa
+5.7,3,4.2,1.2,Iris-versicolor
+7.7,3.8,6.7,2.2,Iris-virginica
+4.6,3.2,1.4,0.2,Iris-setosa
+6.2,2.9,4.3,1.3,Iris-versicolor
+5.7,2.5,5,2,Iris-virginica
+5.5,4.2,1.4,0.2,Iris-setosa
+6,3,4.8,1.8,Iris-virginica
+5.8,2.7,5.1,1.9,Iris-virginica
+6,2.2,4,1,Iris-versicolor
+5.4,3,4.5,1.5,Iris-versicolor
+6.2,3.4,5.4,2.3,Iris-virginica
+5.5,2.3,4,1.3,Iris-versicolor
+5.4,3.9,1.7,0.4,Iris-setosa
+5,2.3,3.3,1,Iris-versicolor
+6.4,2.7,5.3,1.9,Iris-virginica
+5,3.3,1.4,0.2,Iris-setosa
+5,3.2,1.2,0.2,Iris-setosa
+5.5,2.4,3.8,1.1,Iris-versicolor
+6.7,3,5,1.7,Iris-versicolor
+4.9,3.1,1.5,0.1,Iris-setosa
+5.8,2.8,5.1,2.4,Iris-virginica
+5,3.4,1.5,0.2,Iris-setosa
+5,3.5,1.6,0.6,Iris-setosa
+5.9,3.2,4.8,1.8,Iris-versicolor
+5.1,2.5,3,1.1,Iris-versicolor
+6.9,3.2,5.7,2.3,Iris-virginica
+6,2.7,5.1,1.6,Iris-versicolor
+6.1,2.6,5.6,1.4,Iris-virginica
+7.7,3,6.1,2.3,Iris-virginica
+5.5,2.5,4,1.3,Iris-versicolor
+4.4,2.9,1.4,0.2,Iris-setosa
+4.3,3,1.1,0.1,Iris-setosa
+6,2.2,5,1.5,Iris-virginica
+7.2,3.2,6,1.8,Iris-virginica
+4.6,3.1,1.5,0.2,Iris-setosa
+5.1,3.5,1.4,0.3,Iris-setosa
+4.4,3,1.3,0.2,Iris-setosa
+6.3,2.5,4.9,1.5,Iris-versicolor
+6.3,3.4,5.6,2.4,Iris-virginica
+4.6,3.4,1.4,0.3,Iris-setosa
+6.8,3,5.5,2.1,Iris-virginica
+6.3,3.3,6,2.5,Iris-virginica
+4.7,3.2,1.3,0.2,Iris-setosa
+6.1,2.9,4.7,1.4,Iris-versicolor
+6.5,2.8,4.6,1.5,Iris-versicolor
+6.2,2.8,4.8,1.8,Iris-virginica
+7,3.2,4.7,1.4,Iris-versicolor
+6.4,3.2,5.3,2.3,Iris-virginica
+5.1,3.8,1.6,0.2,Iris-setosa
+6.9,3.1,5.4,2.1,Iris-virginica
+5.9,3,4.2,1.5,Iris-versicolor
+6.5,3,5.2,2,Iris-virginica
+5.7,2.6,3.5,1,Iris-versicolor
+5.2,2.7,3.9,1.4,Iris-versicolor
+6.1,3,4.6,1.4,Iris-versicolor
+4.5,2.3,1.3,0.3,Iris-setosa
+6.6,2.9,4.6,1.3,Iris-versicolor
+5.5,2.6,4.4,1.2,Iris-versicolor
+5.3,3.7,1.5,0.2,Iris-setosa
+5.6,3,4.1,1.3,Iris-versicolor
+7.3,2.9,6.3,1.8,Iris-virginica
+6.7,3.3,5.7,2.1,Iris-virginica
+5.1,3.7,1.5,0.4,Iris-setosa
+4.9,2.4,3.3,1,Iris-versicolor
+6.7,3.3,5.7,2.5,Iris-virginica
+7.2,3,5.8,1.6,Iris-virginica
+4.9,3.1,1.5,0.1,Iris-setosa
+6.7,3.1,5.6,2.4,Iris-virginica
+4.9,3,1.4,0.2,Iris-setosa
+6.9,3.1,4.9,1.5,Iris-versicolor
+7.4,2.8,6.1,1.9,Iris-virginica
+6.3,2.9,5.6,1.8,Iris-virginica
+5.7,2.8,4.1,1.3,Iris-versicolor
+6.5,3,5.5,1.8,Iris-virginica
+6.3,2.3,4.4,1.3,Iris-versicolor
+6.4,2.9,4.3,1.3,Iris-versicolor
+5.6,2.8,4.9,2,Iris-virginica
+5.9,3,5.1,1.8,Iris-virginica
+5.4,3.4,1.7,0.2,Iris-setosa
+6.1,2.8,4,1.3,Iris-versicolor
+4.9,2.5,4.5,1.7,Iris-virginica
+5.8,4,1.2,0.2,Iris-setosa
+5.8,2.6,4,1.2,Iris-versicolor
+7.1,3,5.9,2.1,Iris-virginica
diff --git a/ML_Algorithms/KNN/knn.py b/ML_Algorithms/KNN/knn.py
new file mode 100644
index 0000000..cdda149
--- /dev/null
+++ b/ML_Algorithms/KNN/knn.py
@@ -0,0 +1,32 @@
+import numpy as np
+import pandas as pd
+
+def euclidean_distance(x1,x2):
+    distance=0
+    for i in range(len(x1)):
+        distance+=np.square(x1[i]-x2[i])
+    return distance
+
+def knn(training_x,training_y,testing_x):
+    predictions=[]
+    for i in range(len(testing_x)):
+        distance=[]
+        for j in range(len(training_x)):
+            distance.append(euclidean_distance(testing_x[i],training_x[j]))
+        mydict={"class":training_y,"Distances":distance}
+        distance_df=pd.DataFrame.from_dict(mydict)
+        sorted_distance = distance_df.sort_values(by=["Distances"])
+        predict_labels=sorted_distance["class"][:5]
+        predicted_label=predict_labels.value_counts().index.tolist()[0]
+        predictions.append(predicted_label)
+    return predictions
+
+train_df=pd.read_csv("Code-Forge\ML_Algorithms\KNN\iris_train.csv")
+train_x=train_df.drop("Species",axis=1).to_numpy()
+train_y=train_df["Species"].to_numpy()
+
+test_df=pd.read_csv("Code-Forge\ML_Algorithms\KNN\iris_test.csv")
+test_x=test_df.drop("Species",axis=1).to_numpy()
+test_y=test_df["Species"].to_numpy()
+
+predictions=knn(train_x,train_y,test_x)

From 0c33718ca770092987667924f9a23aeb8a1c2877 Mon Sep 17 00:00:00 2001
From: BipanjitGill <120119876+BipanjitGill@users.noreply.github.com>
Date: Wed, 25 Oct 2023 15:20:16 +0530
Subject: [PATCH 3/5] Add files via upload


From ddf432ce17089778a653e923c3c90fc3fbb6aa83 Mon Sep 17 00:00:00 2001
From: BipanjitGill <120119876+BipanjitGill@users.noreply.github.com>
Date: Fri, 27 Oct 2023 19:03:20 +0530
Subject: [PATCH 4/5] Delete ML_Algorithms/KNN directory

---
 ML_Algorithms/KNN/iris_test.csv  |  31 --------
 ML_Algorithms/KNN/iris_train.csv | 121 -------------------------------
 ML_Algorithms/KNN/knn.py         |  32 --------
 3 files changed, 184 deletions(-)
 delete mode 100644 ML_Algorithms/KNN/iris_test.csv
 delete mode 100644 ML_Algorithms/KNN/iris_train.csv
 delete mode 100644 ML_Algorithms/KNN/knn.py

diff --git a/ML_Algorithms/KNN/iris_test.csv b/ML_Algorithms/KNN/iris_test.csv
deleted file mode 100644
index c0337a2..0000000
--- a/ML_Algorithms/KNN/iris_test.csv
+++ /dev/null
@@ -1,31 +0,0 @@
-SepalLengthCm,SepalWidthCm,PetalLengthCm,PetalWidthCm,Species
-6.1,2.8,4.7,1.2,Iris-versicolor
-5.7,3.8,1.7,0.3,Iris-setosa
-7.7,2.6,6.9,2.3,Iris-virginica
-6,2.9,4.5,1.5,Iris-versicolor
-6.8,2.8,4.8,1.4,Iris-versicolor
-5.4,3.4,1.5,0.4,Iris-setosa
-5.6,2.9,3.6,1.3,Iris-versicolor
-6.9,3.1,5.1,2.3,Iris-virginica
-6.2,2.2,4.5,1.5,Iris-versicolor
-5.8,2.7,3.9,1.2,Iris-versicolor
-6.5,3.2,5.1,2,Iris-virginica
-4.8,3,1.4,0.1,Iris-setosa
-5.5,3.5,1.3,0.2,Iris-setosa
-4.9,3.1,1.5,0.1,Iris-setosa
-5.1,3.8,1.5,0.3,Iris-setosa
-6.3,3.3,4.7,1.6,Iris-versicolor
-6.5,3,5.8,2.2,Iris-virginica
-5.6,2.5,3.9,1.1,Iris-versicolor
-5.7,2.8,4.5,1.3,Iris-versicolor
-6.4,2.8,5.6,2.2,Iris-virginica
-4.7,3.2,1.6,0.2,Iris-setosa
-6.1,3,4.9,1.8,Iris-virginica
-5,3.4,1.6,0.4,Iris-setosa
-6.4,2.8,5.6,2.1,Iris-virginica
-7.9,3.8,6.4,2,Iris-virginica
-6.7,3,5.2,2.3,Iris-virginica
-6.7,2.5,5.8,1.8,Iris-virginica
-6.8,3.2,5.9,2.3,Iris-virginica
-4.8,3,1.4,0.3,Iris-setosa
-4.8,3.1,1.6,0.2,Iris-setosa
diff --git a/ML_Algorithms/KNN/iris_train.csv b/ML_Algorithms/KNN/iris_train.csv
deleted file mode 100644
index 7a603e6..0000000
--- a/ML_Algorithms/KNN/iris_train.csv
+++ /dev/null
@@ -1,121 +0,0 @@
-SepalLengthCm,SepalWidthCm,PetalLengthCm,PetalWidthCm,Species
-4.6,3.6,1,0.2,Iris-setosa
-5.7,4.4,1.5,0.4,Iris-setosa
-6.7,3.1,4.4,1.4,Iris-versicolor
-4.8,3.4,1.6,0.2,Iris-setosa
-4.4,3.2,1.3,0.2,Iris-setosa
-6.3,2.5,5,1.9,Iris-virginica
-6.4,3.2,4.5,1.5,Iris-versicolor
-5.2,3.5,1.5,0.2,Iris-setosa
-5,3.6,1.4,0.2,Iris-setosa
-5.2,4.1,1.5,0.1,Iris-setosa
-5.8,2.7,5.1,1.9,Iris-virginica
-6,3.4,4.5,1.6,Iris-versicolor
-6.7,3.1,4.7,1.5,Iris-versicolor
-5.4,3.9,1.3,0.4,Iris-setosa
-5.4,3.7,1.5,0.2,Iris-setosa
-5.5,2.4,3.7,1,Iris-versicolor
-6.3,2.8,5.1,1.5,Iris-virginica
-6.4,3.1,5.5,1.8,Iris-virginica
-6.6,3,4.4,1.4,Iris-versicolor
-7.2,3.6,6.1,2.5,Iris-virginica
-5.7,2.9,4.2,1.3,Iris-versicolor
-7.6,3,6.6,2.1,Iris-virginica
-5.6,3,4.5,1.5,Iris-versicolor
-5.1,3.5,1.4,0.2,Iris-setosa
-7.7,2.8,6.7,2,Iris-virginica
-5.8,2.7,4.1,1,Iris-versicolor
-5.2,3.4,1.4,0.2,Iris-setosa
-5,3.5,1.3,0.3,Iris-setosa
-5.1,3.8,1.9,0.4,Iris-setosa
-5,2,3.5,1,Iris-versicolor
-6.3,2.7,4.9,1.8,Iris-virginica
-4.8,3.4,1.9,0.2,Iris-setosa
-5,3,1.6,0.2,Iris-setosa
-5.1,3.3,1.7,0.5,Iris-setosa
-5.6,2.7,4.2,1.3,Iris-versicolor
-5.1,3.4,1.5,0.2,Iris-setosa
-5.7,3,4.2,1.2,Iris-versicolor
-7.7,3.8,6.7,2.2,Iris-virginica
-4.6,3.2,1.4,0.2,Iris-setosa
-6.2,2.9,4.3,1.3,Iris-versicolor
-5.7,2.5,5,2,Iris-virginica
-5.5,4.2,1.4,0.2,Iris-setosa
-6,3,4.8,1.8,Iris-virginica
-5.8,2.7,5.1,1.9,Iris-virginica
-6,2.2,4,1,Iris-versicolor
-5.4,3,4.5,1.5,Iris-versicolor
-6.2,3.4,5.4,2.3,Iris-virginica
-5.5,2.3,4,1.3,Iris-versicolor
-5.4,3.9,1.7,0.4,Iris-setosa
-5,2.3,3.3,1,Iris-versicolor
-6.4,2.7,5.3,1.9,Iris-virginica
-5,3.3,1.4,0.2,Iris-setosa
-5,3.2,1.2,0.2,Iris-setosa
-5.5,2.4,3.8,1.1,Iris-versicolor
-6.7,3,5,1.7,Iris-versicolor
-4.9,3.1,1.5,0.1,Iris-setosa
-5.8,2.8,5.1,2.4,Iris-virginica
-5,3.4,1.5,0.2,Iris-setosa
-5,3.5,1.6,0.6,Iris-setosa
-5.9,3.2,4.8,1.8,Iris-versicolor
-5.1,2.5,3,1.1,Iris-versicolor
-6.9,3.2,5.7,2.3,Iris-virginica
-6,2.7,5.1,1.6,Iris-versicolor
-6.1,2.6,5.6,1.4,Iris-virginica
-7.7,3,6.1,2.3,Iris-virginica
-5.5,2.5,4,1.3,Iris-versicolor
-4.4,2.9,1.4,0.2,Iris-setosa
-4.3,3,1.1,0.1,Iris-setosa
-6,2.2,5,1.5,Iris-virginica
-7.2,3.2,6,1.8,Iris-virginica
-4.6,3.1,1.5,0.2,Iris-setosa
-5.1,3.5,1.4,0.3,Iris-setosa
-4.4,3,1.3,0.2,Iris-setosa
-6.3,2.5,4.9,1.5,Iris-versicolor
-6.3,3.4,5.6,2.4,Iris-virginica
-4.6,3.4,1.4,0.3,Iris-setosa
-6.8,3,5.5,2.1,Iris-virginica
-6.3,3.3,6,2.5,Iris-virginica
-4.7,3.2,1.3,0.2,Iris-setosa
-6.1,2.9,4.7,1.4,Iris-versicolor
-6.5,2.8,4.6,1.5,Iris-versicolor
-6.2,2.8,4.8,1.8,Iris-virginica
-7,3.2,4.7,1.4,Iris-versicolor
-6.4,3.2,5.3,2.3,Iris-virginica
-5.1,3.8,1.6,0.2,Iris-setosa
-6.9,3.1,5.4,2.1,Iris-virginica
-5.9,3,4.2,1.5,Iris-versicolor
-6.5,3,5.2,2,Iris-virginica
-5.7,2.6,3.5,1,Iris-versicolor
-5.2,2.7,3.9,1.4,Iris-versicolor
-6.1,3,4.6,1.4,Iris-versicolor
-4.5,2.3,1.3,0.3,Iris-setosa
-6.6,2.9,4.6,1.3,Iris-versicolor
-5.5,2.6,4.4,1.2,Iris-versicolor
-5.3,3.7,1.5,0.2,Iris-setosa
-5.6,3,4.1,1.3,Iris-versicolor
-7.3,2.9,6.3,1.8,Iris-virginica
-6.7,3.3,5.7,2.1,Iris-virginica
-5.1,3.7,1.5,0.4,Iris-setosa
-4.9,2.4,3.3,1,Iris-versicolor
-6.7,3.3,5.7,2.5,Iris-virginica
-7.2,3,5.8,1.6,Iris-virginica
-4.9,3.1,1.5,0.1,Iris-setosa
-6.7,3.1,5.6,2.4,Iris-virginica
-4.9,3,1.4,0.2,Iris-setosa
-6.9,3.1,4.9,1.5,Iris-versicolor
-7.4,2.8,6.1,1.9,Iris-virginica
-6.3,2.9,5.6,1.8,Iris-virginica
-5.7,2.8,4.1,1.3,Iris-versicolor
-6.5,3,5.5,1.8,Iris-virginica
-6.3,2.3,4.4,1.3,Iris-versicolor
-6.4,2.9,4.3,1.3,Iris-versicolor
-5.6,2.8,4.9,2,Iris-virginica
-5.9,3,5.1,1.8,Iris-virginica
-5.4,3.4,1.7,0.2,Iris-setosa
-6.1,2.8,4,1.3,Iris-versicolor
-4.9,2.5,4.5,1.7,Iris-virginica
-5.8,4,1.2,0.2,Iris-setosa
-5.8,2.6,4,1.2,Iris-versicolor
-7.1,3,5.9,2.1,Iris-virginica
diff --git a/ML_Algorithms/KNN/knn.py b/ML_Algorithms/KNN/knn.py
deleted file mode 100644
index cdda149..0000000
--- a/ML_Algorithms/KNN/knn.py
+++ /dev/null
@@ -1,32 +0,0 @@
-import numpy as np
-import pandas as pd
-
-def euclidean_distance(x1,x2):
-    distance=0
-    for i in range(len(x1)):
-        distance+=np.square(x1[i]-x2[i])
-    return distance
-
-def knn(training_x,training_y,testing_x):
-    predictions=[]
-    for i in range(len(testing_x)):
-        distance=[]
-        for j in range(len(training_x)):
-            distance.append(euclidean_distance(testing_x[i],training_x[j]))
-        mydict={"class":training_y,"Distances":distance}
-        distance_df=pd.DataFrame.from_dict(mydict)
-        sorted_distance = distance_df.sort_values(by=["Distances"])
-        predict_labels=sorted_distance["class"][:5]
-        predicted_label=predict_labels.value_counts().index.tolist()[0]
-        predictions.append(predicted_label)
-    return predictions
-
-train_df=pd.read_csv("Code-Forge\ML_Algorithms\KNN\iris_train.csv")
-train_x=train_df.drop("Species",axis=1).to_numpy()
-train_y=train_df["Species"].to_numpy()
-
-test_df=pd.read_csv("Code-Forge\ML_Algorithms\KNN\iris_test.csv")
-test_x=test_df.drop("Species",axis=1).to_numpy()
-test_y=test_df["Species"].to_numpy()
-
-predictions=knn(train_x,train_y,test_x)

From 59c6ed1a9fa54e17430c5f3746c7290ec35ada66 Mon Sep 17 00:00:00 2001
From: BipanjitGill <120119876+BipanjitGill@users.noreply.github.com>
Date: Sun, 29 Oct 2023 21:34:39 +0530
Subject: [PATCH 5/5] Add comments in kMeans.py

---
 ML_Algorithms/K-Means/kMeans.py | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/ML_Algorithms/K-Means/kMeans.py b/ML_Algorithms/K-Means/kMeans.py
index f87dc29..a83045a 100644
--- a/ML_Algorithms/K-Means/kMeans.py
+++ b/ML_Algorithms/K-Means/kMeans.py
@@ -1,16 +1,22 @@
+# Code for kMeans algorithm which is an Unsupervised Learning algorithm, which groups the unlabeled dataset into different clusters
+
 import numpy as np
 
 class K_Means:
-    def __init__(self, k=2, max_iter=100, tol=0.001):
+    def __init__(self, k=2, max_iter=100, tol=0.001):  
         self.k = k
+        # k= number of clusters
         self.max_iter = max_iter
+        #  max_iter= maximum number of times to iterate through the dataset 
         self.tol = tol
+        # tol= maximum tolerance level in the output
         
 
     def fit(self,data):
-
+        # Initializing the centroid for each cluster 
         self.centroids = {}
 
+        # Taking random points as centroid
         for i in range(self.k):
             self.centroids[i] = data[i]
 
@@ -21,28 +27,39 @@ def fit(self,data):
                 self.classifications[i] = []
 
             for featureset in data:
+                
+                # Calculating distance from each centroid
                 distances = [np.linalg.norm(featureset-self.centroids[centroid]) for centroid in self.centroids]
+                
+                #Finding the centroid from which distance is minimum
                 classification = distances.index(min(distances))
                 self.classifications[classification].append(featureset)
 
             prev_centroids = dict(self.centroids)
 
+            # Finding the new centroid on the basis of new classified points
             for classification in self.classifications:
                 self.centroids[classification] = np.average(self.classifications[classification],axis=0)
 
             optimized = True
 
+            #Checking if the centroid each cluster converge
             for c in self.centroids:
                 original_centroid = prev_centroids[c]
                 current_centroid = self.centroids[c]
+                
+                # Comparing the previous and new centroids
                 if np.sum((current_centroid-original_centroid)/original_centroid*100.0) > self.tol:
                     # print(np.sum((current_centroid-original_centroid)/original_centroid*100.0))
                     optimized = False
-
+             
+            # If the centroids converge then it is done else again iterate through the whole dataset and find the new centroids   
             if optimized:
                 break
 
     def predict(self,data):
+        # Calculating the distance of test data from the centroid of each cluster
         distances = [np.linalg.norm(data-self.centroids[centroid]) for centroid in self.centroids]
+        # Classify the data with the cluster from which distance is minimum 
         classification = distances.index(min(distances))
-        return classification
\ No newline at end of file
+        return classification