def import_export():
path = approot.get_dataset('Data.csv')
data = pd.read_csv(path)
print(data)
path = approot.get_dataset('Data.pickle')
data.to_pickle(path)
def relative_blocks(blockname):
relative_block_name = list()
relativeBlockFile = approot.get_dataset("relativeBlockName.json")
file = open(relativeBlockFile, 'r', encoding='utf-8')
jsonObject = json.load(file)
if blockname in jsonObject.keys():
for key in jsonObject[blockname]:
relative_block_name.append(key)
return relative_block_name
def readCSV2(filename):
data = pd.read_csv(filename)
dataGroup = data.groupby("name")
result = dict()
tempdict = dict()
for name, groupstack in dataGroup:
tempdict.clear()
temp = groupstack.sort_values(by="count", ascending=False)
for index, row in temp.iterrows():
tempdict[row["blockname"]] = row["count"]
result[name] = tempdict.copy()
filename = approot.get_dataset("relativeBlockName.json")
file = open(filename, 'w', encoding='utf-8')
json.dump(result, file, ensure_ascii=False)
def readCSV(filename):
pd.set_option('display.max_rows', None)
pd.set_option('display.max_columns', None)
pd.set_option('display.width', 300)
data = pd.read_csv(filename)
data.columns = ['id', 'name', 'parent_json', 'children_json']
blockname = pd.DataFrame(columns=['name', 'blockname', 'count'])
for index, row in data.iterrows():
objects = json.loads(row['children_json'])
print((row['id'], row['name']))
for object in objects:
blockname = blockname.append(
pd.DataFrame({"name": row['name'], "blockname": object['name'], "count": object['count']}, index=["0"]),
ignore_index=True)
print(blockname)
blockFile = approot.get_dataset("blocknames.csv")
blockname.to_csv(blockFile)
def save_model():
clf = SVC()
iris = datasets.load_iris()
X, y = iris.data, iris.target
clf.fit(X, y)
# method pickle 存放数据
# pickle_file = approot.get_root('clf.pickle')
# with open(pickle_file, 'wb') as f:
# pickle.dump(clf, f)
# with open(pickle_file, 'rb') as f:
# clf2 = pickle.load(f)
# print(clf2.predict(X[0:1]))
# method 2:joblib
pickle_file = approot.get_dataset('joblib.pickle')
# joblib.dump(clf,pickle_file)
clf3 = joblib.load(pickle_file)
print(clf3.predict(X[0:1]))
pd.DataFrame({"name": row['name'], "blockname": object['name'], "count": object['count']}, index=["0"]),
ignore_index=True)
print(blockname)
blockFile = approot.get_dataset("blocknames.csv")
blockname.to_csv(blockFile)
# 读取文档排序后保存
def readCSV2(filename):
data = pd.read_csv(filename)
dataGroup = data.groupby("name")
result = dict()
tempdict = dict()
for name, groupstack in dataGroup:
tempdict.clear()
temp = groupstack.sort_values(by="count", ascending=False)
for index, row in temp.iterrows():
tempdict[row["blockname"]] = row["count"]
result[name] = tempdict.copy()
filename = approot.get_dataset("relativeBlockName.json")
file = open(filename, 'w', encoding='utf-8')
json.dump(result, file, ensure_ascii=False)
if __name__ == '__main__':
# filename = approot.get_dataset("SELECT_t___FROM_demo_crawlWeight2_t.csv")
# readCSV(filename)
filename = approot.get_dataset("blocknames.csv")
readCSV2(filename)
for key, value in relations.items():
if value == deviceId:
flag = key
break
return flag
def test3():
font = fm.FontProperties(fname='HYQiHei-25J.ttf')
name_list = ['星期一', '星期二', '星期三', '星期四']
num_list = [1.5, 0.6, 7.8, 6]
plt.bar(range(len(num_list)), num_list, color='rgb', tick_label=name_list)
plt.xticks(fontproperties=font)
plt.show()
if __name__ == '__main__':
# select_DEVICE_ID_CONTEXT_ID_from_DWB_DA_8_27.csv 设备id 864621038192553 的行为记录
file = approot.get_dataset(
'select_DEVICE_ID_CONTEXT_ID__from_DWB_DA_2018-9-4.csv')
readCsv(file=file)
# wordCloudDemo(' '.join(searchKey.values))
# contentIds = getContentNum(contentId)
# df = searchUrl(contentIds)
# drawPicture(df)
# test2()
# test()
# test3()
def startup(phone):
filename = approot.get_dataset(
"select_DEVICE_ID_CONTEXT_ID__from_DWB_DA.csv")
deivceId = relation(phone)
data = read_history2(filename, str(deivceId))
from app import approot
import pandas as pd
import numpy as np
from sklearn.preprocessing import Imputer
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
from sklearn.cross_validation import train_test_split
from sklearn.preprocessing import StandardScaler
def print_parameter(X, Y):
print(X)
print(Y)
if __name__ == '__main__':
path = approot.get_dataset('Data.csv')
dataset = pd.read_csv(path)
X = dataset.iloc[:, :-1].values
Y = dataset.iloc[:, 3].values
print_parameter(X, Y)
imputer = Imputer(missing_values="NaN", strategy="mean", axis=0)
imputer = imputer.fit(X[:, 1:3])
X[:, 1:3] = imputer.transform(X[:, 1:3])
print_parameter(X, Y)
labelencoder_X = LabelEncoder()
X[:, 0] = labelencoder_X.fit_transform(X[:, 0])
print_parameter(X, Y)