[analysis] add all_clusters(모든 그룹을 다 표시)

analysis/age_group.py

@@ -3,30 +3,30 @@
 import os
 import warnings
 import seaborn as sns
-import matplotlib
-import matplotlib.pyplot as plt
-import matplotlib.font_manager as fm
 import numpy as np
 
 from sklearn.cluster import KMeans
 from sklearn.metrics import pairwise_distances
-
-# font_location = '/home/gun/playground/techforimpact/main/_data/NanumGothic.TTF'
-# font_name = fm.FontProperties(fname=font_location).get_name()
-# plt.rcParams["font.family"] = font_name
+from matplotlib import font_manager
+from matplotlib import cm
+from matplotlib import pyplot as plt
 
 # 경고 무시
 warnings.filterwarnings("ignore", category=FutureWarning)
 
 BASE_DIR = os.path.join(os.path.dirname(__file__), os.pardir)
-# outdir = input("_data 내의 폴더 이름은 무엇인가요?")
-outdir = input()
+outdir = input("_data 내의 폴더 이름은 무엇인가요?")
 datadir = os.path.join(BASE_DIR, "_data", outdir)
-outdir = os.path.join(BASE_DIR, "output", outdir)
-
-
+outdir = os.path.join(BASE_DIR, "output", "tmp", outdir)
+
+# matplotlib 한국어 폰트 설정
+font_name = font_manager.FontProperties(fname=os.path.join(BASE_DIR, "_data", "NanumSquareL.ttf")).get_name()
+# import matplotlib
+# print(matplotlib.matplotlib_fname())
+# print(matplotlib.get_cachedir())
+# exit(1)
 def most_common_age_group(df, d):
-    """가장 흔한 10년단위그룹이 뭔지 봅니다.
+    """10년단위로 무리짓고 가장 사람 많은 무리 출력.
     df: 데이터프레임
     d: 파일 이름"""
     age_groups = pd.cut(
@@ -60,10 +60,14 @@ def cluster(df, year, n_clusters=5, method="kmeans"):
     n_clusters: 그룹 수
     """
     os.makedirs(os.path.join(outdir, method), exist_ok=True)
-    youngest_age = ("", 100)
-    oldest_age = ("", 0)
+    os.makedirs(os.path.join(outdir, "all-clusters", method), exist_ok=True)
+    youngest_age = ('', 100)
+    oldest_age = ('', 0)
     print(f"({year}), {n_clusters} clusters")
     print(f"{'-' * 20}")
+    # Get a colormap for generating unique colors for clusters
+    colors = cm.rainbow(np.linspace(0, 1, n_clusters))
+
     # 데이터프레임에서 시도별로 묶은 후 나이 열만 가져옵니다.
     for sdName, df in df.groupby("sdName"):
         data_for_clustering = df[["age"]]
@@ -136,41 +140,47 @@ def cluster(df, year, n_clusters=5, method="kmeans"):
             oldest_age = (sdName, cluster_centers_age[-1])
         # 시각화
         plt.figure(figsize=(10, 6))
-        try:
-            sns.histplot(
-                data=youngest_cluster,
-                x="age",
-                kde=True,
-                label="Youngest Cluster",
-                color="blue",
-                element="step",
-                bins=range(
-                    youngest_cluster["age"].min(), youngest_cluster["age"].max() + 1, 1
-                ),
-            )
-        except:
-            pass
-        try:
-            sns.histplot(
-                data=oldest_cluster,
-                x="age",
-                kde=True,
-                label="Oldest Cluster",
-                color="red",
-                element="step",
-                bins=range(
-                    oldest_cluster["age"].min(), oldest_cluster["age"].max() + 1, 1
-                ),
-            )
-        except:
-            pass
-        plt.title(f"Age Distribution ({year})")
+        # try:
+        #     sns.histplot(data=youngest_cluster,
+        #                  x="age",
+        #                  kde=True,
+        #                  label="Youngest Cluster",
+        #                  color="blue",
+        #                  element="step",
+        #                  bins=range(youngest_cluster['age'].min(),
+        #                             youngest_cluster['age'].max() + 1, 1))
+        # except:
+        #     pass
+        # try:
+        #     sns.histplot(data=oldest_cluster,
+        #                  x="age",
+        #                  kde=True,
+        #                  label="Oldest Cluster",
+        #                  color="red",
+        #                  element="step",
+        #                  bins=range(oldest_cluster['age'].min(),
+        #                             oldest_cluster['age'].max() + 1, 1))
+        # except:
+        #     pass
+        for i in range(n_clusters):
+            cluster_data = df[df["cluster_label"] == i]
+            sns.histplot(data=cluster_data,
+                         x="age",
+                         kde=False,
+                         label=f"Cluster {i}",
+                         color=colors[i],
+                         element="step",
+                         bins=range(0,
+                                    100, 1))
+
+        plt.title(f"Age Distribution ({year}), area {sdName}", fontname = font_name)
         plt.xlabel("Age")
         plt.ylabel("Frequency")
         plt.legend()
         plt.show()
-        plt.savefig(os.path.join(outdir, method, f"{year}-{sdName}.png"))
-
+        plt.savefig(os.path.join(outdir, "all-clusters", method, f"{year}-{sdName}.png"))
+        plt.close()
+        print(f"Saved {year}-{sdName}.png")
         # # 클러스터링 결과로부터 각 데이터 포인트와 클러스터 중심 간의 거리를 계산합니다.
         # distances = pairwise_distances(data_for_clustering, cluster_centers)
 
@@ -230,8 +240,7 @@ def main():
         year = d[7:11]
         # most_common_age_group(df, year)
         # avg_age(df)
-        cluster(df, year, 7, "kmeans")
-        # cluster(df, year, 7, 'equal')
-
+        cluster(df, year, 7, 'kmeans')
+        cluster(df, year, 7, 'equal')
 
 main()