轮廓系数-平滑度-聚类添加字段和对比图

cluster_power.py → cluster_analysis.py

@@ -38,6 +38,16 @@ def read_cfs(cfs, input_path, output_path, is_folder=False):
         dfs[j] = dfj
     return dfs
 
+def normalize(input_path, turbine):
+    turbines = [pd.read_csv(f) for f in os.listdir(os.path.join(input_path))]
+    turbines = [turbine.values[:, 1:].astype(np.float32) for turbine in turbines]
+    turbines = np.vstack(turbines)
+    mean, std = np.mean(turbines, axis=0), np.std(turbines, axis=0)
+
+    c_time = turbine['C_TIME']
+    turbine = (turbine.iloc[:, 1:] - mean) / std
+    turbine.insert(loc=0, column='C_TIME', value=c_time)
+    return turbine
 
 def get_cfs(cluster, turbine_id):
     cfs = {}