Merge pull request #1550 from bjjwwang/kv_tool

add Kv tool

core/cube/cube-builder/tool/kv_to_seqfile.py

@@ -54,13 +54,21 @@ def kv_to_seqfile():
         finally:
             fp.close()
         for line in lines:
-            line_list = line.split(':')
+            line_list = line.split()
+            if len(line_list) < 1:
+                continue
             key = int(line_list[0])
-            value = str(line_list[1]).replace('\n', '')
+            show = int(line_list[1])
+            click = int(line_list[2])
+            values = [float(x) for x in line_list[3:]]
+
+           # str(line_list[1]).replace('\n', '')
             res.append(dict)
             key_bytes = struct.pack('Q', key)
-            row_bytes = struct.pack('%ss' % len(value), value)
-            print key, ':', value, '->', key_bytes, ':', row_bytes
+            row_bytes = ""
+            for v in values:
+                row_bytes += struct.pack('f', v)
+            print key, ':', values, '->', key_bytes, ':', row_bytes
             writer.write(key_bytes, row_bytes)
     f.close()
     write_donefile()

core/predictor/tools/seq_reader.cpp

@@ -55,7 +55,14 @@ void printSeq(std::string file, int limit) {
 
     total_count++;
     int64_t value_length = record.record_len - record.key_len;
-    std::cout << "key: " << key << " , value: " << string_to_hex(record.value.c_str()) << std::endl; 
+    float *data_ptr = new float[record.value.size() / 4];
+    memcpy(data_ptr, record.value.data(), record.value.size()); 
+    std::cout << "key: " << key << " , value: " << string_to_hex(record.value.c_str()) << std::endl;
+    for (int i =0; i < record.value.size() / 4; ++i) {
+      std::cout << data_ptr[i] << " ";
+    } 
+    std::cout << std::endl;
+    delete(data_ptr);
     if (total_count >= limit) {
         break;
     }