From 2da5ca2500823f26347a6ead300aee4b63dde4fc Mon Sep 17 00:00:00 2001
From: XLC <631@qq.com>
Date: Sun, 15 Dec 2019 23:23:38 +0800
Subject: [PATCH] update

---
 ...櫒瀛︿範-鍧﹀厠鍗槦鍥剧墖璇嗗埆鍒嗙被.md | 39 ++++++++++++++++++-
 1 file changed, 38 insertions(+), 1 deletion(-)

diff --git a/chapter5/5.2Spark鏈哄櫒瀛︿範-鍧﹀厠鍗槦鍥剧墖璇嗗埆鍒嗙被.md b/chapter5/5.2Spark鏈哄櫒瀛︿範-鍧﹀厠鍗槦鍥剧墖璇嗗埆鍒嗙被.md
index bdb9d92..daa4da3 100644
--- a/chapter5/5.2Spark鏈哄櫒瀛︿範-鍧﹀厠鍗槦鍥剧墖璇嗗埆鍒嗙被.md
+++ b/chapter5/5.2Spark鏈哄櫒瀛︿範-鍧﹀厠鍗槦鍥剧墖璇嗗埆鍒嗙被.md
@@ -148,11 +148,48 @@ print(type(img))
 
 
 #### 5.2.3 Spark 鍔犺浇鏁版嵁闆�
-
 涓婇潰鎴戜滑宸茬粡鎶婃暟鎹泦澶勭悊瀹屾瘯涔嬪悗锛岀劧鍚庢垜浠彲浠ラ�氳繃`Spark`鏉ュ姞杞芥暟鎹泦銆�
 
 ```
+import cv2
+import os
+import pandas as pd
+from pyspark.mllib.evaluation import BinaryClassificationMetrics
+from pyspark.sql import SparkSession
+from pyspark.ml.linalg import Vectors
+from pyspark.ml.classification import LogisticRegression
+
+def get_file_path(root_path):
+    file_list = []
+    dir_or_files = os.listdir(root_path)
+    for dir_file in dir_or_files:
+        dir_file_path = os.path.join(root_path, dir_file)
+        file_list.append(dir_file_path)
+    return file_list
+
+
+def img2vector(imgfilename):
+    img = cv2.imread(imgfilename, cv2.IMREAD_GRAYSCALE)
+    rows, columns = img.shape
+    img = img.reshape(rows * columns)
+    # print(type(img))
+    return Vectors.dense(img)
+
+root_path = r"testing2"
+fileList = get_file_path(root_path)
+vectos = []
+for x in fileList:
+    vector = img2vector(x)
+    if "btr-70" in x:
+        label = 0
+    elif "t-72" in x:
+        label = 1
+    else:
+        label = 2
+    vectos.append((vector, label))
+df = pd.DataFrame(vectos, columns=['features', 'label'])
 spark = SparkSession.builder.master("local[*]").appName("demo").getOrCreate()
+spark.sparkContext.setLogLevel("error")
 sparkDF = spark.createDataFrame(df) # df鏄垜浠�氳繃pandas鏋勫缓鐨凞ataframe
 ```