add: Bind Filter and Fit

.gitignore

@@ -11,6 +11,7 @@ venv/
 
 # build cache
 build/
+__pycache__
 
 # config
 .vscode

GaussianMixture.py

@@ -1,36 +0,0 @@
-import os
-import numpy as np
-from tqdm import tqdm
-from matplotlib import pyplot as plt
-from sklearn.mixture import GaussianMixture
-
-path = 'result/bind'
-file_list = os.listdir(path)
-
-pbar = tqdm(total=len(file_list))
-
-for file in file_list:
-    name = file.split('.')[0]
-    file = os.path.join(path, file)
-    data = np.loadtxt(file, dtype=np.uint16)
-    x = data[:, 0]
-    y = data[:, 1]
-
-    model = GaussianMixture(n_components=2)
-    model.fit(data)
-
-    nx = np.array([])
-    ny = model.predict(data)
-    fig = plt.figure(figsize=(8, 8))
-    for cluster in np.unique(ny):
-        idx = np.where(ny == cluster)[0]
-        nx = idx if len(idx) > len(nx) else nx
-        plt.scatter(data[idx, 0], data[idx, 1], s=0.1)
-    fig.savefig('result/GMM/' + name + '.png')
-    plt.close()
-
-    np.savetxt('result/bind-GMM/' + name + '.txt', data[nx], fmt='%d')
-
-    pbar.update(1)
-
-pbar.close()

main.py

@@ -0,0 +1,30 @@
+import os
+import re
+import numpy as np
+from tqdm import tqdm
+from qdx import BindFilter, Bind
+
+binds = []
+BF = BindFilter()
+
+path = 'result/bind'
+file_list = os.listdir(path)
+
+reg = re.compile(r'(([0-9]{4})-([0-9])-([0.9])).txt')
+
+pbar = tqdm(desc="Gaussian Mixture Bind Filter", total=len(file_list))
+
+for file in file_list:
+    name, E, n, m = reg.match(file).groups()
+    file = os.path.join(path, file)
+
+    BF(file)
+    BF.draw('result/GMM/' + name + '.png')
+    np.savetxt('result/bind-GMM/' + name + '.txt', BF.fit_data, fmt='%d')
+    binds.append(Bind(int(E), int(n), int(m), BF.fit_data))
+
+    pbar.update(1)
+
+    break
+
+pbar.close()

qdx/Bind.py

@@ -0,0 +1,28 @@
+from cProfile import label
+import numpy as np
+import matplotlib.pyplot as plt
+from sklearn.linear_model import LinearRegression
+
+
+class Bind(object):
+    k, b = 0, 0
+
+    def __init__(self, E, n, m, data):
+        self.E = E
+        self.n, self.m = n, m
+        self.x, self.y = data[:, 0], data[:, 1]
+
+    def fit(self):
+        self.reg = LinearRegression()
+        self.reg.fit(self.x, self.y)
+        self.k = self.reg.coef_[0][0]
+        self.b = self.reg.intercept_[0]
+
+    def draw(self, title):
+        fig = plt.figure(figsize=(8, 8))
+        ax = fig.add_subplot(1, 1, 1)
+        ax.scatter(self.x, self.y, s=0.1, c='k', label='raw')
+        ax.plot(self.x, self.reg.predict(self.x), c='r', label='fit')
+        ax.legend()
+        fig.savefig(title)
+        plt.close()

qdx/BindFilter.py

@@ -0,0 +1,33 @@
+import numpy as np
+from matplotlib import pyplot as plt
+from sklearn.mixture import GaussianMixture
+
+
+class BindFilter(object):
+    def __init__(self):
+        pass
+
+    def fit(self, file):
+        self.clusters = []
+        self.fit_data = np.array([])
+
+        data = np.loadtxt(file, dtype=np.uint16)
+
+        model = GaussianMixture(n_components=2)
+        model.fit(data)
+
+        ny = model.predict(data)
+        for i in np.unique(ny):
+            idx = np.where(ny == i)[0]
+            self.fit_data = idx if len(idx) > len(self.fit_data) else self.fit_data
+            self.clusters.append(data[idx])
+
+        self.fit_data = data[self.fit_data]
+
+    def draw(self, title):
+        fig = plt.figure(figsize=(8, 8))
+        ax = fig.add_subplot(1, 1, 1)
+        for cluster in self.clusters:
+            ax.scatter(cluster[:, 0], cluster[:, 1], s=0.1)
+        fig.savefig(title)
+        plt.close()

qdx/Block.py

@@ -0,0 +1,11 @@
+from .Bind import Bind
+
+
+class Block(object):
+    binds = []
+
+    def __init__(self) -> None:
+        pass
+
+    def addBind(self, b: Bind):
+        self.binds.append(b)

qdx/__init__.py

@@ -0,0 +1,2 @@
+from .Bind import Bind
+from .BindFilter import BindFilter