def get_data():
client = Client("http://t3.dev:50070", "hadoop")
# client = InsecureClient(url="http://t3.dev:50070", user="******", root="/")
print(client.list("/huiqu/common/area.txt"))
with client.read("/huiqu/common/area.txt/part-00000") as read:
# print(read.read().decode('utf8'))
return {"data": read.read().decode('utf8')}
print(rowkey)
mutations = [Mutation(column=self.columnFamily + ":ipaddr", value=ipaddr), \
Mutation(column=self.columnFamily + ":visitTime", value=visitTime), \
Mutation(column=self.columnFamily + ":user_id", value=user_id), \
Mutation(column=self.columnFamily + ":link", value=link)
]
# 一次提交多行
mutations_batch.append(
BatchMutation(row=rowkey, mutations=mutations))
if len(mutations_batch) % batch_size == 0:
self.client.mutateRows(self.tablename, mutations_batch)
mutations_batch = []
if __name__ == "__main__":
# 建立hbase连接
hbasewriteer = CreateTableAndImportData('user_log_info', 'cf_log')
hbasewriteer.createTable()
# 连接HDFS
client = Client(HDFSNN)
# 获取文件列表
logFiles = client.list(LOGPATH)
# 读取文件
for logfile in logFiles:
with client.read(os.path.join(LOGPATH, logfile)) as deal_file_handle:
hbasewriteer.importData(deal_file_handle)
class ChatBotModel(object):
def __init__(self,
hadoop_url,
hdfs_index_file,
local_index_file,
corpus_dir,
unk_answer='',
max_answer_len=1024):
self.hadoop_url = hadoop_url
self.hdfs_index_file = hdfs_index_file
self.local_index_file = local_index_file
self.corpus_dir = corpus_dir
self.max_answer_len = max_answer_len
self.unk_answer = unk_answer
self.client = None
self.inverted_index = {}
def build_connection(self):
self.client = Client(self.hadoop_url)
def fetch_index_file(self):
self.client.download(hdfs_path=self.hdfs_index_file,
local_path=self.local_index_file,
overwrite=True)
def load_inverted_index(self):
with open(self.local_index_file, 'r', encoding='utf-8') as f:
for line in f:
word, *querys = line.strip().split('\t')
for query in querys:
file_name, query_id, score = query.split(':')
if word in self.inverted_index:
self.inverted_index[word].append(
[file_name, int(query_id),
float(score)])
else:
self.inverted_index[word] = []
self.inverted_index[word].append(
[file_name, int(query_id),
float(score)])
def prepare(self):
self.build_connection()
self.fetch_index_file()
self.load_inverted_index()
def read_corpus_answer(self, file_name, query_id):
file_path = os.path.join(self.corpus_dir, file_name)
file_status = self.client.status(file_path)
if file_status['length'] <= query_id:
return None
with self.client.read(hdfs_path=file_path,
offset=query_id,
length=self.max_answer_len,
encoding='utf-8') as f:
answer = f.read().strip().split('\n')[0]
return answer
def predict_answer(self, query):
words = jieba.lcut_for_search(query)
querys = {}
for word in words:
if word not in self.inverted_index:
continue
for file_name, query_id, score in self.inverted_index[word]:
query = (file_name, query_id)
if query in querys:
querys[query] += score
else:
querys[query] = score
if len(querys) == 0:
return self.unk_answer
best_query = max(querys.items(), key=lambda x: x[1])
(best_file_name, best_query_id), best_score = best_query
best_answer = self.read_corpus_answer(best_file_name, best_query_id)
if best_answer is None:
best_answer = self.unk_answer
return best_answer
import pandas as pd
import os
from hdfs import Client
# 目前读取hdfs文件采用方式：
# 1. 先从hdfs读取二进制数据流文件
# 2. 将二进制文件另存为.csv
# 3. 使用pandas读取csv文件
HDFSHOST = "http://172.16.18.112:50070"
train_path = "/9a7e7ef5a78f4f8388deff28cc5c2115/dataSet/devdatasetdef19761"
test_path = "/9a7e7ef5a78f4f8388deff28cc5c2115/dataSet/devdatasetdef19762"
train_FILENAME = train_path + "/data/Data.csv" #hdfs文件路径
test_FILENAME = test_path + "/data/Data.csv" #hdfs文件路径
client = Client(HDFSHOST)
with client.read(train_FILENAME) as tr_s:
tr_content = tr_s.read()
tr_s = str(tr_content, 'utf-8')
# 确保文件写入完毕
tr_file = open("trainData.csv", "w")
tr_file.flush()
os.fsync(tr_file)
tr_file.write(tr_s)
tr_file.close()
# 读取文件
df_train = pd.read_csv("trainData.csv", header=0)
print(df_train)
with client.read(test_FILENAME) as te_fs:
te_content = te_fs.read()
te_s = str(te_content, 'utf-8')
def train(train_path,
test_path,
output_path,
target,
train_split_ratio=0.33,
penalty='l2',
dual=False,
tol=1e-4,
C=1.0,
random_state=None,
multi_class='ovr'):
# 设置起始时间
time.localtime()
time_trains_start = time.strftime('%Y{y}%m{m}%d{d} %H{h}%M{f}%S{s}'.format(
y='/', m='/', d='', h=':', f=':', s=''))
start_time = time.time()
# 设置输入文件路径
train_FILENAME = train_path + "/data/Data.csv" # hdfs文件路径
test_FILENAME = test_path + "/data/Data.csv" # hdfs文件路径
client = Client(HDFS_HOSTS1)
# 训练数据读取
with client.read(train_FILENAME) as tr_s:
tr_content = tr_s.read()
tr_s = str(tr_content, 'utf-8')
# 确保文件写入完毕
tr_file = open("trainData.csv", "w")
tr_file.flush()
os.fsync(tr_file)
tr_file.write(tr_s)
tr_file.close()
df_train = pd.read_csv("trainData.csv", header=0)
print(df_train)
# 测试数据读取
with client.read(test_FILENAME) as te_fs:
te_content = te_fs.read()
te_s = str(te_content, 'utf-8')
# 确保文件写入完毕
te_file = open("testData.csv", "w")
te_file.flush()
os.fsync(te_file)
te_file.write(te_s)
te_file.close()
df_test = pd.read_csv("testData.csv", header=0)
print(df_test)
min_max_scaler = preprocessing.MinMaxScaler(feature_range=(-1, 1))
test_data_num = df_train.shape[0]
train_data_num = df_train.shape[0]
# 处理预测集
df_test = min_max_scaler.fit_transform(df_test)
df_test = np.array(df_test)
# 数据处理和清洗
cols = [tmp_i for tmp_i in df_train.columns if tmp_i not in [target]]
X = df_train[cols]
X = np.array(X)
X = min_max_scaler.fit_transform(X)
Y = df_train[target]
Y = np.array(Y)
# 训练集数据分割
X_train, X_test, Y_train, Y_test = train_test_split(
X, Y, test_size=train_split_ratio)
# 使用 scikit learn 中的LR模型进行训练
clf = LogisticRegression(penalty,
dual,
tol,
C,
random_state,
multi_class,
solver='liblinear')
clf.fit(X_train, Y_train)
# 准确率train_acc
train_acc = clf.score(X_test, Y_test)
print('score Scikit learn: ', train_acc)
# 精确率train_precision_score
train_precision_score = precision_score(Y_test, clf.predict(X_test))
# 召回率train_recall_score
train_recall_score = recall_score(Y_test, clf.predict(X_test))
# F1_Score
train_f1_score = f1_score(Y_test, clf.predict(X_test))
# roc_auc_score
train_roc_auc_score1 = roc_auc_score(Y_test, clf.predict(X_test))
# 使用 scikit learn 中的LR模型进行预测
result = clf.predict(df_test)
# print(result)
# 设置终止时间，并计算总时间
train_end = time.time()
train_seconds = train_end - start_time
m, s = divmod(train_seconds, 60)
h, m = divmod(m, 60)
time_trains_all = "%02d:%02d:%02d" % (h, m, s)
# ++++++++++++++++++++++++++++++++++++++++训练结果保存+++++++++++++++++++++++++++++++++++++++#
## 保存摘要模型报告文件
# abstract_path = HDFS_HOSTS1 + output_path + '/abstract/data/'
abstract_path = output_path + '/abstract/data/'
f = open('abstract.csv', mode='w', newline='')
fileheader = [
'FrameWork', 'Version', 'model', 'accuracy', 'time_trains_start',
'time_trains_all', 'test_data_num', 'train_data_num'
]
w = csv.DictWriter(f, fileheader)
w.writeheader()
csv_dict = edict()
csv_dict.FrameWork = 'Scikit-learn'
csv_dict.Version = sklearn.__version__
csv_dict.model = '%s' % LogisticRegression
csv_dict.accuracy = str(train_acc)
csv_dict.time_trains_start = time_trains_start
csv_dict.time_trains_all = time_trains_all
csv_dict.test_data_num = str(test_data_num)
csv_dict.train_data_num = str(train_data_num)
w.writerow(csv_dict)
f.close()
client.delete(abstract_path + 'abstract.csv')
client.upload(abstract_path + 'abstract.csv', 'abstract.csv')
# if len(client.list(abstract_path)):
# client.delete(abstract_path + 'abstract.csv')
# client.upload(abstract_path + 'abstract.csv', 'abstract.csv')
# else:
# client.upload(abstract_path + 'abstract.csv', 'abstract.csv')
##保存模型版本信息csv文件
version_path = output_path + '/msg/data/'
f = open('msg.csv', mode='w', newline='')
fileheader = [
'accuracy', 'time_trains_start', 'time_trains_all', 'test_data_num',
'train_data_num'
]
w = csv.DictWriter(f, fileheader)
w.writeheader()
csv_dict = edict()
csv_dict.accuracy = str(train_acc)
csv_dict.time_trains_start = time_trains_start
csv_dict.time_trains_all = time_trains_all
csv_dict.test_data_num = str(test_data_num)
csv_dict.train_data_num = str(train_data_num)
w.writerow(csv_dict)
f.close()
client.delete(version_path + 'msg.csv')
client.upload(version_path + 'msg.csv', 'msg.csv')
## 保存训练评价指标模型报告文件
file_csv_path = output_path + '/evaluation/data/'
f = open('evaluation.csv', mode='w', newline='')
fileheader = [
'accuracy', 'train_precision_score', 'train_recall_score',
'train_f1_score', 'train_roc_auc_score1'
]
w = csv.DictWriter(f, fileheader)
w.writeheader()
csv_dict = edict()
csv_dict.accuracy = str(train_acc)
csv_dict.train_precision_score = train_precision_score
csv_dict.train_recall_score = train_recall_score
csv_dict.train_f1_score = train_f1_score
csv_dict.train_roc_auc_score1 = train_roc_auc_score1
w.writerow(csv_dict)
f.close()
client.delete(file_csv_path + 'evaluation.csv')
client.upload(file_csv_path + 'evaluation.csv', 'evaluation.csv')
# 保存测试集预测结果文件
file_csv_path = output_path + '/result/data/'
# 字典中的key值即为csv中列名
dataframe = pd.DataFrame({target: result})
# 将DataFrame存储为csv,index表示是否显示行名，default=True
dataframe.to_csv("result.csv", index=False, sep=',')
client.delete(file_csv_path + 'result.csv')
client.upload(file_csv_path + 'result.csv', 'result.csv')
rowkey = md5(str(user_id) + str(visitTime))
print(rowkey)
mutations = [Mutation(column=self.columnFamily + ":ipaddr", value=ipaddr), \
Mutation(column=self.columnFamily + ":visitTime", value=visitTime), \
Mutation(column=self.columnFamily + ":user_id", value=user_id), \
Mutation(column=self.columnFamily + ":link", value=link)
]
self.client.mutateRow(self.tablename, rowkey, mutations)
if __name__ == "__main__":
# 建立hbase连接
hbasewriteer = CreateTableAndImportData('user_log_info', 'cf_log')
hbasewriteer.createTable()
# 连接HDFS
client = Client(HDFSNN, timeout=200000)
# 获取文件列表
logFiles = client.list(LOGPATH)
# 读取文件
for logfile in logFiles:
with client.read(LOGPATH + logfile) as fp:
for line in fp:
record = line.split(" ")
hbasewriteer.importData(record)
def interface(train_path,
test_path,
output_path,
target,
chaid_ratio,
train_split_ratio=0.3,
n_estimators=100,
max_depth=5,
min_samples_split=3,
min_samples_leaf=2,
min_split_gain=0.0,
colsample_bytree="log2",
subsample=0.8,
random_state=100):
# 设置起始时间
time.localtime()
time_trains_start = time.strftime('%Y{y}%m{m}%d{d} %H{h}%M{f}%S{s}'.format(
y='/', m='/', d='', h=':', f=':', s=''))
start_time = time.time()
# 设置输入文件路径
train_FILENAME = train_path + "/data/Data.csv" # hdfs文件路径
test_FILENAME = test_path + "/data/Data.csv" # hdfs文件路径
client = Client(HDFS_HOSTS1)
# 训练数据读取
with client.read(train_FILENAME) as tr_s:
tr_content = tr_s.read()
tr_s = str(tr_content, 'utf-8')
# 确保文件写入完毕
tr_file = open("trainData.csv", "w")
tr_file.flush()
os.fsync(tr_file)
tr_file.write(tr_s)
tr_file.close()
df_train = pd.read_csv("trainData.csv", header=0)
print(df_train)
# 测试数据读取
with client.read(test_FILENAME) as te_fs:
te_content = te_fs.read()
te_s = str(te_content, 'utf-8')
# 确保文件写入完毕
te_file = open("testData.csv", "w")
te_file.flush()
os.fsync(te_file)
te_file.write(te_s)
te_file.close()
df_test = pd.read_csv("testData.csv", header=0)
print(df_test)
test_data_num = df_train.shape[0]
train_data_num = df_train.shape[0]
# 卡方检测选出和label列最相关的前chaid_ratio（默认值为前80%）的列
ch2 = SelectKBest(chi2, k=int(df_train.shape[1] * chaid_ratio))
chi_df_train = pd.DataFrame(ch2.fit_transform(df_train, df_train[target]))
label_df = df_train[target]
# wine数据集 和 sonar 数据集
clf = RandomForestClassifier(n_estimators, max_depth, min_samples_split,
min_samples_leaf, min_split_gain,
colsample_bytree, subsample, random_state)
# 数据集分割与训练
train_count = int(train_split_ratio * len(chi_df_train))
clf.fit(chi_df_train.ix[:train_count], label_df.ix[:train_count])
train_acc = metrics.accuracy_score(
label_df.ix[:train_count], clf.predict(chi_df_train.ix[:train_count]))
print("模型的准确率：", train_acc)
# 精确率
train_precision_score = metrics.precision_score(
label_df.ix[:train_count], clf.predict(chi_df_train.ix[:train_count]))
# 召回率
train_recall_score = metrics.recall_score(
label_df.ix[:train_count], clf.predict(chi_df_train.ix[:train_count]))
# F1_Score
train_f1_score = metrics.f1_score(
label_df.ix[:train_count], clf.predict(chi_df_train.ix[:train_count]))
# roc_auc_score
train_roc_auc_score1 = metrics.roc_auc_score(
label_df.ix[:train_count], clf.predict(chi_df_train.ix[:train_count]))
# 对测试集进行处理，保证其和训练集卡方检测后的列数一致
ch2_list = list(ch2.get_support())
ch2_list.pop()
df_test_head = list(df_test.columns)
for x, y in zip(ch2_list, df_test_head):
if x == False:
df_test_head.remove(y)
df_test = df_test[df_test_head]
# 预测
result = clf.predict(df_test)
# print(result)
# 设置终止时间，并计算总时间
train_end = time.time()
train_seconds = train_end - start_time
m, s = divmod(train_seconds, 60)
h, m = divmod(m, 60)
time_trains_all = "%02d:%02d:%02d" % (h, m, s)
# print(time_trains_start,time_trains_all)
# ++++++++++++++++++++++++++++++++++++++++训练结果保存+++++++++++++++++++++++++++++++++++++++#
## 保存摘要模型报告文件
abstract_path = output_path + '/abstract/data/'
f = open('abstract.csv', mode='w', newline='')
fileheader = [
'FrameWork', 'Version', 'model', 'accuracy', 'time_trains_start',
'time_trains_all', 'test_data_num', 'train_data_num'
]
w = csv.DictWriter(f, fileheader)
w.writeheader()
csv_dict = edict()
csv_dict.FrameWork = 'Scikit-learn'
csv_dict.Version = sklearn.__version__
csv_dict.model = '%s' % RandomForestClassifier
csv_dict.accuracy = str(train_acc)
csv_dict.time_trains_start = time_trains_start
csv_dict.time_trains_all = time_trains_all
csv_dict.test_data_num = str(test_data_num)
csv_dict.train_data_num = str(train_data_num)
w.writerow(csv_dict)
f.close()
client.delete(abstract_path + 'abstract.csv')
client.upload(abstract_path + 'abstract.csv', 'abstract.csv')
##保存模型版本信息csv文件
version_path = output_path + '/msg/data/'
f = open('msg.csv', mode='w', newline='')
fileheader = [
'accuracy', 'time_trains_start', 'time_trains_all', 'test_data_num',
'train_data_num'
]
w = csv.DictWriter(f, fileheader)
w.writeheader()
csv_dict = edict()
csv_dict.accuracy = str(train_acc)
csv_dict.time_trains_start = time_trains_start
csv_dict.time_trains_all = time_trains_all
csv_dict.test_data_num = str(test_data_num)
csv_dict.train_data_num = str(train_data_num)
w.writerow(csv_dict)
f.close()
client.delete(version_path + 'msg.csv')
client.upload(version_path + 'msg.csv', 'msg.csv')
## 保存训练评价指标模型报告文件
file_csv_path = output_path + '/evaluation/data/'
f = open('evaluation.csv', mode='w', newline='')
fileheader = [
'accuracy', 'train_precision_score', 'train_recall_score',
'train_f1_score', 'train_roc_auc_score1'
]
w = csv.DictWriter(f, fileheader)
w.writeheader()
csv_dict = edict()
csv_dict.accuracy = str(train_acc)
csv_dict.train_precision_score = train_precision_score
csv_dict.train_recall_score = train_recall_score
csv_dict.train_f1_score = train_f1_score
csv_dict.train_roc_auc_score1 = train_roc_auc_score1
w.writerow(csv_dict)
f.close()
client.delete(file_csv_path + 'evaluation.csv')
client.upload(file_csv_path + 'evaluation.csv', 'evaluation.csv')
# 保存测试集预测结果文件
file_csv_path = output_path + '/result/data/'
dataframe = pd.DataFrame({target: result})
dataframe.to_csv("result.csv", index=False, sep=',')
client.delete(file_csv_path + 'result.csv')
client.upload(file_csv_path + 'result.csv', 'result.csv')
def post(self, request, *args, **kwargs):
import uuid
permission_classes = (IsAuthenticated,)
start_time = time.time()
file_serializer = DatasourceSerializer(data=request.data)
if file_serializer.is_valid():
path = file_serializer.validated_data['file_name']
user = request.user.id
# 上传文件的大小
filesize = round((path.size) / 1024 / 1024, 2)
# 获取该用户所有文件的大小
mydata_id = DataSource.objects.filter(user_id=user)
myData_size = 0
for i in mydata_id:
try:
x = i.fileSize.replace("KB", '')
myData_size += float(x)
except:
continue
myData_size = round(myData_size / 1024, 2) # 单位MB
# 该用户即将上传文件加本身有的大小
now_userDataSize = filesize + myData_size
# 查找用户所限制文件上传容量的大小
user_dataSize_old = UserLevel.objects.get(user_id=user).up_load
print(type(user_dataSize_old))
if now_userDataSize > user_dataSize_old:
return Response({'msg': '您的数据容量不足,请清理数据后在尝试', 'status': False})
# if 1 > 2:
# pass
else:
try:
is_header = file_serializer.validated_data['is_header']
# user =1
separator = file_serializer.validated_data['column_delimiter']
except:
# 数据库文件没有表头,所以设置
is_header = ''
separator = '\n'
last = (str(path).lower()).split('.')[-1].upper()
if last == 'CSV' or last == 'TXT' or last == 'SQL':
if path.size > LIMIT_FILE_SIZE:
format_name = uuid.uuid1()
file_serializer.validated_data['format_filename'] = format_name
file_serializer.save()
client = Client(HDFS_HOST)
file_path = os.path.join(settings.MEDIA_ROOT, str(path))
with open(file_path, 'rb') as f1: # 判断文件的编码
data_type = chardet.detect(f1.readline())['encoding']
if data_type == 'None':
return Response({'msg': '数据格式有误', 'status': False})
os.renames(file_path, os.path.join(settings.MEDIA_ROOT, str(format_name)))
client.upload("/datahoop", os.path.join(settings.MEDIA_ROOT, str(format_name)), n_threads=4)
os.remove(os.path.join(settings.MEDIA_ROOT, str(format_name)))
try:
with client.read('/datahoop/' + str(format_name), encoding=data_type) as reader:
filesize = ((client.status('/datahoop/' + str(format_name)))['length']) / 1024
filesize = str(round(filesize, 2)) + 'KB'
reader = reader.readlines()
except:
return Response({'msg': '数据读取失败', 'status': False})
column_delimiter = separator
if is_header == 1:
title = (reader[0]).split(column_delimiter)
json = {}
s = ((reader[0]).split(column_delimiter))
for i in s:
json[i.replace('\r\n', '')] = [typ.StringType, True]
print(json)
else:
total = len((reader[0]).split(column_delimiter))
title = []
for i in range(total):
title.append('_C' + str(i))
json = {}
for i in title:
json[i] = [typ.StringType, True]
column_num = len((reader[0]).split(column_delimiter))
row_num = len(reader)
DataSource.objects.filter(format_filename=format_name).update(user_id=user,
title=title[:20],
fileSize=filesize,
where='hdfs', row_num=row_num,
column_num=column_num)
over_time = time.time()
print('ID为<%s>用户--数据上传<%s>文件的时间为--<%s>秒' % (user, format_name, over_time - start_time))
return Response({'msg': '数据存储成功', 'status': True})
else:
global object_id
filePath = os.path.join(settings.MEDIA_ROOT, str(path))
file_serializer.save()
filesize = str(round((path.size) / 1024, 2)) + 'KB'
if last == 'XLS' or last == 'XLSX':
pass
elif last == 'TXT':
object_id = tools.save_mongo_txt(filePath, user, is_header, separator, str(path))
if object_id != 'none':
file_serializer.validated_data['obj_id'] = object_id
file_serializer.validated_data['file_name'] = str(path)
file_serializer.save()
else:
DataSource.objects.filter(file_name=str(path), user=1).delete()
os.remove(os.path.join(settings.MEDIA_ROOT, str(path)))
return Response({'msg': '数据格式有误', 'status': False})
elif last == 'CSV':
object_id = tools.save_mongo_csv(filePath, user, is_header, separator, str(path))
if object_id != 'none':
file_serializer.validated_data['obj_id'] = object_id
file_serializer.validated_data['file_name'] = str(path)
file_serializer.save()
else:
# uuid = uuid.uuid1()
# file_serializer.validated_data['obj_id'] = uuid
# file_serializer.validated_data['file_name'] = str(path)
# file_serializer.save()
DataSource.objects.filter(file_name=str(path), user=1).delete()
os.remove(os.path.join(settings.MEDIA_ROOT, str(path)))
return Response({'msg': '数据格式有误', 'status': False})
elif last == 'SQL':
try:
object_id = tools.save_mongo_sql(filePath, user)
file_serializer.validated_data['obj_id'] = object_id
file_serializer.validated_data['file_name'] = str(path)
file_serializer.save()
except Exception as e:
DataSource.objects.filter(file_name=str(path), user=1).delete()
os.remove(os.path.join(settings.MEDIA_ROOT, str(path)))
return Response({'msg': '数据格式有误', 'status': False})
with open(filePath, 'rb') as f1: # 判断文件的编码
data_type = chardet.detect(f1.readline())['encoding']
with open(filePath, encoding=data_type, errors='ignore') as reader: # 按编码读文件
reader = reader.readlines()
if is_header == 1:
title = (reader[0]).split(separator)
json = {}
s = ((reader[0]).split(separator))
for i in s:
json[i.replace('\r\n', '')] = [typ.StringType, True]
column_num = len((reader[0]).split(separator))
else:
if last != 'SQL':
total = len((reader[0]).split(separator))
title = []
for i in range(total):
title.append('_C' + str(i))
json = {}
for i in title:
json[i] = [typ.StringType, True]
column_num = len((reader[0]).split(separator))
else:
total = re.findall(r'[^()]+', reader[0])[1].split(',')
title = []
for i in range(len(total)):
title.append('_C' + str(i))
json = {}
for i in title:
json[i] = [typ.StringType, True]
column_num = len(total)
row_num = len(reader)
DataSource.objects.filter(obj_id=object_id).update(user_id=user, title=title[:20],
fileSize=filesize, where='mongodb',
row_num=row_num, column_num=column_num)
os.remove(os.path.join(settings.MEDIA_ROOT, str(path)))
over_time = time.time()
print('ID为<%s>用户--数据上传<%s>文件的时间为--<%s>秒' % (user, path, over_time - start_time))
return Response({'msg': '数据存储成功', 'status': True})
else:
return Response({'msg': '暂不支持此类文件上传', 'status': False})
else:
return Response({'msg': '不是一个有效的数据', 'status': False})
def get(self, request, detail_id):
id = detail_id
view_num = DataSource.objects.get(id=id).view_num
DataSource.objects.filter(id=id).update(view_num=view_num + 1)
user_id = request.user.id
object = DataSource.objects.get(id=id)
where = object.obj_id
if where == '':
try:
file = object.format_filename
file = str(file)
header = 'media/' + str(object.user.image)
username = object.user.username
hdfs_path = '/datahoop/' + file
client = Client(HDFS_HOST)
json = {}
json['header'] = header
file_user_id = object.user.id
relation = Relationship.objects.filter(author_id=user_id)
all = []
for i in relation:
all.append(i.User_ByID)
if str(file_user_id) in all:
json['is_focus'] = 1
else:
json['is_focus'] = 0
objects = Collect.objects.filter(source=1, user=user_id, file_id=id)
if objects:
json['is_collect'] = 1
else:
json['is_collect'] = 0
love = Love.objects.filter(user=user_id, file_id=id, source=1)
if love:
json['is_love'] = 1
else:
json['is_love'] = 0
file_user_id = object.user_id
if user_id == file_user_id:
json['is_me'] = 1
else:
json['is_me'] = 0
json['file_name'] = str(object.file_name)
json['title'] = object.detail
json['hdfs'] = object.format_filename
json['fav_num'] = object.fav_num
json['view_num'] = object.view_num
json['thumb_num'] = object.thumb_num
json['label'] = [object.label_name, '']
json['username'] = username
json['data'] = []
with client.read(hdfs_path, encoding='utf-8') as reader:
for i in (reader.readlines())[0:20]:
print(i)
json['data'].append(i.split(','))
return Response(json, status=status.HTTP_200_OK)
except Exception as e:
print(e)
return Response(status=status.HTTP_404_NOT_FOUND)
else:
try:
client = pymongo.MongoClient(MONGO_DB_URI)
db = client.datahoop.data
json = {}
fileName = str(object.file_name)
obj_id = object.obj_id
file_user_id = object.user.id
relation = Relationship.objects.filter(author_id=user_id)
all = []
for i in relation:
all.append(i.User_ByID)
if str(file_user_id) in all:
json['is_focus'] = 1
else:
json['is_focus'] = 0
result = db.find({'_id': ObjectId(obj_id)})
fileType = (fileName.split('.')[-1]).lower() # 获取文件后缀名
table_name = fileName
sheetList = ''
sheet = ''
json['file_user_id'] = file_user_id
json['header'] = 'media/' + str(object.user.image)
json['file_name'] = str(object.file_name)
if user_id == file_user_id:
json['is_me'] = 1
else:
json['is_me'] = 0
json['title'] = object.detail
objects = Collect.objects.filter(source=1, user=user_id, file_id=id)
if objects:
json['is_collect'] = 1
else:
json['is_collect'] = 0
love = Love.objects.filter(user=user_id, file_id=id, source=1)
if love:
json['is_love'] = 1
else:
json['is_love'] = 0
json['obj_id'] = object.obj_id
json['fav_num'] = object.fav_num
json['view_num'] = object.view_num
json['thumb_num'] = object.thumb_num
json['label'] = [object.label_name, '']
json['username'] = object.user.username
if fileType == 'xls' or fileType == 'xlsx': # 读取ｅｘｃｅｌ文件 返回列表
sheetList = (sorted((result[0]['fileData'])))
rel = sorted((result[0]['fileData']).items())[0][1][0:501]
default_sheet = sorted((result[0]['fileData']).items())[0][0]
sheet = request.GET.get('sheet')
if sheet:
rel = (result[0]['fileData'][sheet][0:501])
else:
sheet = default_sheet
elif fileType == 'csv' or fileType == 'txt':
import pandas as pd
# empty = pandas.DataFrame()
# data = empty.append(result[0]['fileData'])
# rel = data[0:].values.tolist()[0:20]
data = pd.DataFrame(result[0]['fileData'])
rel = data.values.tolist()[0:200]
for i in range(len(rel)):
for j in range(len(rel[i])):
if str(rel[i][j]) == "nan":
rel[i][j] = ""
json['data'] = rel
elif fileType == 'sql':
rel = (result[0]['fileData'])[0:20]
json['data'] = rel
client.close()
return Response(json, status=status.HTTP_200_OK)
except Exception as e:
print(e)
return Response(status=status.HTTP_404_NOT_FOUND)
# 创建文件夹
client.makedirs(file_dir)
# 返回目标信息
info = client.status(file_name, strict=False)
print(info)
# 写入文件(覆盖)
client.write(file_name, data="hello hdfs !", overwrite=True)
# 写入文件(追加)
client.write(file_name, data="hello way !", overwrite=False, append=True)
# 读取文件内容
with client.read(file_name, encoding='utf-8') as f:
print(f.read())
# 文件下载
client.download(file_name, loacl_file_name, overwrite=True)
# 文件上传
client.upload(file_name + '111', loacl_file_name, cleanup=True)
# 删除文件
client.delete(file_name2)
# 文件重命名
client.rename(file_name, file_name2)
# 文件夹底下文件