T7更新

T7_client.py

@@ -0,0 +1,96 @@
+import json
+import os
+import socket
+import struct
+import sys
+
+import PySimpleGUI as sg
+
+
+def recvdata(conn, filepath):
+    header_size = struct.unpack('i', conn.recv(4))[0]
+    header_bytes = conn.recv(header_size)
+    header_json = header_bytes.decode('utf-8')
+    header_dic = json.loads(header_json)
+    content_len = header_dic['contentlen']
+    content_name = header_dic['contentname']
+    recv_len = 0
+    pdf = os.path.join(filepath, content_name)
+    with open(pdf, 'wb') as file:
+        while recv_len < content_len:
+            correntrecv = conn.recv(1024 * 1000)
+            file.write(correntrecv)
+            recv_len += len(correntrecv)
+
+
+def senddata(conn, path, chipum):
+    name = os.path.basename(os.path.realpath(path))
+    try:
+        with open(path, 'rb') as file:
+            content = file.read()
+            headerdic = dict(
+                contentlen=len(content),
+                contentname=name,
+                chipum=chipum
+            )
+            headerjson = json.dumps(headerdic)
+            headerbytes = headerjson.encode('utf-8')
+            headersize = len(headerbytes)
+            conn.send(struct.pack('i', headersize))
+            conn.send(headerbytes)
+            conn.sendall(content)
+    except ConnectionResetError:
+        print('不存在这个文件！')
+
+
+def connect():
+    client = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+    dest_ip = '192.168.11.121'
+    dest_port = int(8191)
+    client.connect((dest_ip, dest_port))
+    return client
+
+
+def transclient(sendfile, resfile, chipnum):
+    conn = connect()
+    senddata(conn, sendfile, chipnum)
+    recvdata(conn, resfile)
+
+
+def make_gui():
+    sg.theme('DarkBlack1')
+
+    layout = [
+        [sg.Text('排样芯片数'), sg.Spin([i for i in range(20)], initial_value=5, size=(3, 1), key='_CHIPNUM_')],
+        [sg.Text()],
+        [
+            sg.Text('导入排样excel')],
+        [
+            sg.Input(key='_FILE1_'), sg.FileBrowse('选择文件')],
+        [sg.Text()],
+        [
+            sg.Text('生成排样位置')],
+        [
+            sg.Input(key='_FILE2_'), sg.FolderBrowse('选择文件夹')],
+        [sg.Text()],
+        [
+            sg.OK('生成'), sg.Cancel('取消')]]
+    # iconpath = os.path.join(os.path.abspath(sys.path[0]), 'other', 'icon.ico')
+    window = sg.Window('解码排样T7程序', layout, font='Helvetica 11')
+
+    while True:
+        event, values = window.Read()
+        if event == '生成':
+            if not values['_FILE1_'] or not values['_FILE2_']:
+                sg.popup_non_blocking('请正确提供参数')
+            else:
+                transclient(values['_FILE1_'], os.path.join(values['_FILE2_']), values['_CHIPNUM_'])
+                sg.Popup('排样成功！')
+                window.Close()
+        else:
+            window.Close()
+            break
+
+
+if __name__ == '__main__':
+    make_gui()

T7_server.py

@@ -0,0 +1,87 @@
+import json
+import os
+import socket
+import struct
+import sys
+from datetime import datetime
+
+from tools.common import basedir
+from tools.t7 import AutoLayout as T7
+
+
+def recvdata(conn, path):
+    """
+    接受文件
+    :param conn:
+    :param path:
+    :return:
+    """
+    header_size = struct.unpack('i', conn.recv(4))[0]
+    header_bytes = conn.recv(header_size)
+    header_json = header_bytes.decode('utf-8')
+    header_dic = json.loads(header_json)
+    content_len = header_dic['contentlen']
+    content_name = header_dic['contentname']
+    chipnum = header_dic['chipnum']
+    recv_len = 0
+    fielpath = os.path.join(path, '%s_%s' % (datetime.now().strftime("%m%d%H%M"), content_name))
+    file = open(fielpath, 'wb')
+    while recv_len < content_len:
+        correntrecv = conn.recv(1024 * 1000)
+        file.write(correntrecv)
+        recv_len += len(correntrecv)
+    file.close()
+    return fielpath, chipnum
+
+
+def senddata(conn, path, message=None):
+    name = os.path.basename(os.path.realpath(path))
+    if not message:
+        with open(path, 'rb') as file:
+            content = file.read()
+        headerdic = dict(
+            contentlen=len(content),
+            contentname=name
+        )
+        headerjson = json.dumps(headerdic)
+        headerbytes = headerjson.encode('utf-8')
+        headersize = len(headerbytes)
+        conn.send(struct.pack('i', headersize))
+        conn.send(headerbytes)
+        conn.sendall(content)
+    else:
+        headerdic = dict(
+            contentlen=len(path),
+            contentname='message'
+        )
+        headerjson = json.dumps(headerdic)
+        headerbytes = headerjson.encode('utf-8')
+        headersize = len(headerbytes)
+        conn.send(struct.pack('i', headersize))
+        conn.send(headerbytes)
+        conn.sendall(path.encode('utf-8'))
+
+
+def server():
+    myserver = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+    adrss = ("", 8191)
+    myserver.bind(adrss)
+    myserver.listen(5)
+    while True:
+        try:
+            myclient, adddr = myserver.accept()
+            recv_content, chipnum = recvdata(myclient, os.path.join(basedir, 'example'))
+            layout = T7(recv_content, chipnum)
+            outputpath = layout.run()
+            senddata(myclient, outputpath)
+        except Exception as e:
+            print(e)
+            continue
+
+
+if __name__ == '__main__':
+    if len(sys.argv) > 1:
+        layout = T7(sys.argv[1], sys.argv[2])
+        outputpath = layout.run()
+    else:
+        server()

tools/t7.py

@@ -1,10 +1,11 @@
-import pandas as pd
+import os
+import time
 from collections import defaultdict
 from datetime import datetime
-import time
-import os
 
-from .common import basedir, log
+import pandas as pd
+
+from tools.common import basedir, log
 
 
 class AutoLayout:
@@ -12,9 +13,10 @@ class AutoLayout:
     自动化派样
     """
 
-    def __init__(self, path, output=basedir, data_limit=1520):
+    def __init__(self, path, chipnum, output=basedir, data_limit=1520):
         self.path = path
         self.output = output
+        self.chipnum = int(chipnum)
         self.data_limit = data_limit
 
         self.index_assignments = defaultdict(list)
@@ -30,11 +32,14 @@ class AutoLayout:
         self.loc_chip_num = 1
         # 芯片客户
         self.chip_customer = defaultdict(set)
+        # 文库
+        self.chip_classification = defaultdict(set)
         self.rule = self.read_rule()
         # 甲基化文库不大于200,WGBS文库不大于200G
         self.chip_speciallib_size = dict()
         self.logger = log(os.path.basename(f'{path}.txt'))
         self.return_log = list()
+        self.no_assign_data = list()
 
     def read_excel(self):
         """
@@ -71,6 +76,7 @@ class AutoLayout:
                 self.chip_speciallib_size[chipname] += library_data['size']
 
         self.chip_customer[chipname].add(library_data['customer'])
+        self.chip_classification[chipname].add(library_data['classification'])
 
     def add_new_chip(self, library_data):
         """
@@ -109,6 +115,7 @@ class AutoLayout:
     def dec_barcode_radio(self, chipname):
         data = self.index_assignments[chipname]
         df = pd.DataFrame(data)
+        df['barcode'] = df['barcode'].str.slice(0, 16)
         barcode_df = pd.DataFrame(df['barcode'].str.split('', expand=True).iloc[:, 1:-1].values,
                                   columns=['T' + str(x) for x in range(16)]).join(df['data_needed'])
         total = barcode_df['data_needed'].sum()
@@ -124,18 +131,26 @@ class AutoLayout:
                 base_N_size = 0
 
             col_df['ratio'] = (col_df['data_needed']) / (total - base_N_size)
-            is_need_base = col_df.index[col_df['ratio'] < 0.088]
+            # is_need_base = col_df.index[col_df['ratio'] < 0.088]
-            need_base_list = list(is_need_base)
 
+            A, B, C, D = list(), list(), list(), list(),
+
+            need_base_list = list()
             ratio = col_df['ratio'].to_dict()
             for decbase in ['A', 'T', 'C', 'G']:
                 if decbase not in ratio:
                     ratio[decbase] = 0
-                    need_base_list.append(decbase)
+                if ratio[decbase] >= 0.6:
-            # 小于标准的base 是不是空的，空的说明都满足
+                    A.append(decbase)
-            if need_base_list:
+                if 0.2 <= ratio[decbase] < 0.6:
+                    B.append(decbase)
+                if 0.08 <= ratio[decbase] < 0.2:
+                    C.append(decbase)
+                if ratio[decbase] <= 0.8:
+                    D.append(decbase)
+            if not ((len(B) + len(C) == 4) or (len(D) == 1 and len(C) == 3)):
                 is_not_balance_list.append(
-                    '%s 第%s位置, %s 有碱基不平衡，算出结果为 %s' % (chipname, i, need_base_list, ratio)
+                    '%s 第%s位置,有碱基不平衡，算出结果为 %s' % (chipname, i, ratio)
                 )
 
         if len(is_not_balance_list) > 2:
@@ -145,46 +160,49 @@ class AutoLayout:
 
     @staticmethod
     def level(row):
-        if row['customer'] == '贞固':
+
-            return 1
+        today_date = datetime.now()
-        if row['split_method'] == '极致周期':
+
+        # 将时间字符串转换为 datetime 对象
+        # mytime = datetime.strptime(row['time'], "%Y-%m-%d")
+        # mytime = row['time'].strftime("%Y-%m-%d")
+        mytime = row['time']
+        if row['拆分方式'] == '极致周期' or '极致' in row['拆分方式']:
             return 2
 
-        # 医沐、清港泉、WES（自己建库）也是极致周期，
+        # 判断日期是之前的还是之后的
-        if row['customer'] == '医沐' or row['customer'] == '清港泉':
+        if mytime < today_date:
             return 3
 
-        # 赛福、桐树基因的文库尽量跟极致周期测人的样本排一起上机
+        if '加急' in row['priority']:
-        if row['customer'] == '赛福' or row['customer'] == '桐树基因':
+            return 4
-            return 7
 
-        if row['classification'] == 'Nextera':
+        if '补测' in row['priority']:
             return 5
 
-        if '华大' in row['classification']:
-            return 6
-
         else:
             return 100
 
     @staticmethod
     def read_rule():
-        df = pd.read_excel(os.path.join(basedir, 'rule', 'exclusive.xlsx'))
+        df = pd.read_excel(os.path.join(basedir, 'rule', 'exclusive_classfication.xlsx'))
         newdf = pd.DataFrame()
-        newdf['customer1'] = df['customer2']
+        newdf['c1'] = df['c2']
-        newdf['customer1'] = df['customer1']
+        newdf['c2'] = df['c1']
-        return pd.concat([df, newdf])
+        res = pd.concat([df, newdf])
+        return res.reset_index()
 
-    def use_rule(self, chipname, customer):
+    def use_rule(self, chipname, classfication):
-        may_customer = set(self.rule[self.rule['customer1'] == customer]['customer2'])
+        may_classfic= set(self.rule[self.rule['c1'] == classfication]['c2'])
-        if self.chip_customer[chipname].intersection(may_customer):
+        if self.chip_customer[chipname].intersection(may_classfic):
             return True
         return False
 
     def judge_data(self, chipname, library_data):
         size = library_data['size']
-        customer = library_data['customer']
+        # customer = library_data['customer']
         library = library_data['library']
+        classification = library_data['classification']
 
         # 芯片大小不能超过设定限制
         sizelimit = True
@@ -196,37 +214,71 @@ class AutoLayout:
         if self.chip_barcode_recode[chipname].intersection({item['barcode'] for item in library_data['data']}):
             notrepeatbarcode = False
             self.logger.error(f'{library} {chipname} 文库有barcode重复')
-        # 互斥的客户
+        # # 互斥的客户
-        exclusivecostom = True
+        # exclusivecostom = True
-        if self.use_rule(chipname, customer):
+        # if self.use_rule(chipname, customer):
-            exclusivecostom = False
+        #     exclusivecostom = False
+        #     self.logger.error(f'{library} {chipname} 有互斥单位')
+
+        # 互斥的文库
+        exclusive_classific= True
+        if self.use_rule(chipname, classification):
+            exclusive_classific= False
             self.logger.error(f'{library} {chipname} 有互斥单位')
+
         # 不平衡文库大于200G 不能添加
         splibrary = True
-        if library_data['classification'] in ['扩增子', '不平衡文库', '单细胞文库', '甲基化'] \
+        if classification in ['扩增子', '不平衡文库', '单细胞文库', '甲基化'] \
                 and self.chip_speciallib_size[chipname] + size > 200:
             splibrary = False
             self.logger.error(f'{library} {chipname} 不平衡文库相加大于设定限制')
-        if sizelimit and notrepeatbarcode and exclusivecostom and splibrary:
+        if sizelimit and notrepeatbarcode and exclusive_classific and splibrary:
             return True
         return False
 
     def assign_samples(self):
         ori_library_data = list()
+
+        if '未测' not in self.ori_data.keys():
+            raise UserWarning('提供excel没有 未测 sheet ,请核查！')
         ori_library_df = pd.DataFrame(self.ori_data['未测'])
+
+        need_col = ['#library', 'sublibrary', 'i5', 'i7', 'data_needed', 'real_data', 'customer',
+                    'classification', 'priority', 'time', '拆分方式', 'barcode'
+                    ]
+        get_col = set(ori_library_df.columns)
+        unhave_col = set(need_col) - get_col
+
+        if unhave_col:
+            unhave_fom = '; '.join(unhave_col)
+            raise UserWarning(f'未测表里没有{unhave_fom}  表头,请核查！')
+
+        numeric_mask = pd.to_numeric(ori_library_df['data_needed'], errors='coerce').notna()
+        time_mask = pd.to_datetime(ori_library_df['time'], errors='coerce').notna()
+
+        ori_library_df['note'] = ''
+        ori_library_df.loc[~numeric_mask, 'note'] = 'data_needed 列非数字'
+        ori_library_df.loc[~time_mask, 'note'] = 'time 列非日期'
+
+        need_col.append('note')
+
+        self.no_assign_data.extend(ori_library_df[~(numeric_mask & time_mask)].to_dict('records'))
+        # 使用布尔索引筛选出不是数字和非日期的行
+        ori_library_df = ori_library_df[numeric_mask & time_mask]
         ori_library_df['level'] = ori_library_df.apply(self.level, axis=1)
+
         for library, library_df in ori_library_df.groupby('#library'):
             ori_library_data.append(dict(
                 library=library,
                 size=library_df['data_needed'].sum(),
-                split_method=library_df['split_method'].values[0],
+                split_method=library_df['拆分方式'].values[0],
                 time=library_df['time'].values[0],
                 level=library_df['level'].values[0],
                 customer=library_df['customer'].values[0],
                 classification=library_df['classification'].values[0],
-                data=library_df.to_dict('records')
+                data=library_df[need_col].to_dict('records')
             ))
-        ori_sort_data = sorted(ori_library_data, key=lambda x: (x['level'], -x['size'], x['time']))
+        ori_sort_data = sorted(ori_library_data, key=lambda x: (x['level'], x['time']))
 
         i = 0
         while ori_sort_data:
@@ -263,6 +315,7 @@ class AutoLayout:
         pass
 
     def run(self):
+        self.assign_samples()
         try:
             self.assign_samples()
         except Exception as e:
@@ -271,19 +324,21 @@ class AutoLayout:
         outputname = 'assignments_%s_%s' % (datetime.now().strftime("%m%d%H%M"), os.path.basename(self.path))
         outputpath = os.path.join(self.output, 'result', outputname)
         writer = pd.ExcelWriter(outputpath)
-        no_assign_data = list()
+
+        chip_loc = 1
         for chip_idx, chip_assignments in self.index_assignments.items():
-            self.dec_barcode_radio(chip_idx)
             df = pd.DataFrame(chip_assignments)
-            if df['data_needed'].sum() < 1400:
+            if df['data_needed'].sum() < 1400 or chip_loc > self.chipnum:
-                no_assign_data.extend(chip_assignments)
+                self.no_assign_data.extend(chip_assignments)
                 continue
-            if '极致周期' in df['split_method'].values:
+            if '极致' in df['拆分方式'].values:
                 addname = 'X'
             else:
                 addname = ''
+            self.dec_barcode_radio(chip_idx)
             df.to_excel(writer, sheet_name=addname + chip_idx, index=False)
-        pd.DataFrame(no_assign_data).to_excel(writer, sheet_name='未测', index=False)
+            chip_loc += 1
+        pd.DataFrame(self.no_assign_data).to_excel(writer, sheet_name='未测', index=False)
         if self.return_log:
             pd.DataFrame(self.return_log).to_excel(writer, sheet_name='log', index=False)
         writer.close()
@@ -292,9 +347,10 @@ class AutoLayout:
 
 if __name__ == '__main__':
     start_time = time.time()
-    excel_file = 'example/07031754_20230703.xlsx'
+    filepath = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'example', 'input排样表.xlsx')
+    # excel_file = 'example/input排样表.xlsx'
     output_file = ''
-    layout = AutoLayout(excel_file, output_file)
+    layout = AutoLayout(filepath, output_file)
     layout.run()
     end_time = time.time()
     execution_time = end_time - start_time