Python DataFrameClient.switch_database方法代码示例

# 需要导入模块: from influxdb.influxdb08 import DataFrameClient [as 别名]
# 或者: from influxdb.influxdb08.DataFrameClient import switch_database [as 别名]
                 [ 'wage_us_yoy', '(wage_us_weekly_nonsupervisory/lag(wage_us_weekly_nonsupervisory,12)-1)*100' ],
                 [ 'wti_yoy', '(avg(wti_spot,M)/lag(avg(wti_spot,M),12)-1)*100' ],
                 [ 'zillow_median_sale_price_yoy', '(zillow_median_sale_price/lag(zillow_median_sale_price,12)-1)*100' ],
                 [ 'ng_yoy', '(ng_hh_spot/lag(ng_hh_spot,12)-1)*100' ],
                 [ 'gdp_us_yoy', '(gdp_us/lag(gdp_us,4)-1)*100' ],
                 ]

processed_list = [
                  [ 'wage_lag_15m', 'mlag(wage_us_yoy,15)' ],
                  [ 'zillow_median_sale_price_15m', 'mlag(zillow_median_sale_price_yoy,15)' ],
                  ]

df = DataFrameClient('localhost',8086,'root','root')
if({'name':'Econ'} not in df.get_list_database()):
    df.create_database('Econ')
df.switch_database('Econ')

#add all items in interested list
start = timeit.default_timer()
for item in interest_list:
    if item[0] in df.get_list_series():
        df.delete_series(item[0])
    results = influx_Fred.interpret(item[1])
    results = results.replace(to_replace='NaN',value='.')
    results = DataFrame({'value':results['value']})
    df.write_points({item[0]:results})
    print item
print 'total time in seconds: %.2f' % (timeit.default_timer() - start)

#add all items in processed list
start = timeit.default_timer()

# 需要导入模块: from influxdb.influxdb08 import DataFrameClient [as 别名]
# 或者: from influxdb.influxdb08.DataFrameClient import switch_database [as 别名]
'''
Created on Jul 8, 2015

@author: shaunz
'''

from QuandlAPI import QuandlAPI
from influxdb.influxdb08 import DataFrameClient
from QuandlTicker import Quandl_ticker_list
import timeit

quandl = QuandlAPI()
df = DataFrameClient('localhost', 8086, 'root', 'root')
if({'name':'Quandl'} not in df.get_list_database()):
    df.create_database('Quandl')

df.switch_database('Quandl')

for series in df.get_list_series():
    df.delete_series(series)

start = timeit.default_timer()
for item in Quandl_ticker_list:
    results = quandl.get_series(item[1],item[2],item[3])
    results = results.replace(to_replace='NaN',value='.')
    print item
    df.write_points({item[0]:results})
print 'total time in seconds: %.2f' % (timeit.default_timer() - start)

# 需要导入模块: from influxdb.influxdb08 import DataFrameClient [as 别名]
# 或者: from influxdb.influxdb08.DataFrameClient import switch_database [as 别名]
class InfluxDB(object):
    '''
    Connect to influxdb and pull/write data
    '''
    def __init__(self, db_name=None):
        self.url = 'localhost'
        self.port = 8086
        self.user = 'root'
        self.password = 'root'
        self.db_list = [ 'FRED', 'Quandl', 'Econ', 'ChinaData' ]
        
        self.db = DataFrameClient(self.url, self.port, self.user, self.password)
        if(db_name != None):
            self.db_name = db_name
        self.db.switch_database(db_name)
        
    def _search_db(self,series_name):
        '''
        Search the db name for a series name
        '''
        for db in self.db_list:
            temp_db = DataFrameClient(self.url, self.port, self.user, self.password, db)
            if series_name in temp_db.get_list_series():
                return db
        
        return None
            
    def query(self,series_name,db_name=None):
        '''
        Query a particular series
        ------
        series_name: str
            name of the series, e.g. "CPI_US"
        ------
        return a pandas DataFrame with NaN representing missing values
        ------
        '''
        if(db_name != None):
            self.db.switch_database(db_name)
            results = self.db.query('SELECT * FROM %s' % series_name)
        else:
            db_name = self._search_db(series_name)
            self.db.switch_database(db_name)
            results = self.db.query('SELECT * FROM %s' % series_name)       
        
        if(results['value'].str.contains('.').isnull().sum()!=len(results)):
            results.loc[results['value']=='.','value'] = None
        
        return results.astype(float)
    
    def _is_num(self, s):
        '''
        Determine if a string is a number
        '''
        try:
            float(s)
            return True
        except ValueError:
            return False
    
    def _include(self,expression_list,c):
        '''
        check whether expression_list include basic operator c, and give the index of first occurrence
        ------
        c: str
            the basic operator or parentheses c
        ------
        '''
        for index, item in enumerate(expression_list):
            if(type(item)==type('string')):
                if(item == c):
                    return index
        
        return -1
            
        
    def _get_index(self,expression_list, op_1, op_2):
        '''
        Get the index of first occurrence of op_1 OR op_2, assume expression_list includes op_1 OR op_2
        '''
        index_1 = self._include(expression_list, op_1)
        index_2 = self._include(expression_list, op_2)
        
        if(min(index_1,index_2)==-1):
            return(max(index_1,index_2))
        else:
            return(min(index_1,index_2))
    
    def _close_parentheses(self,expression):
        '''
        Find the closing parentheses to the first opening (
        ------
        expression: str
            str contains an opening (
        ------
        '''
        layer = 0
        for i, char in enumerate(expression):
            if(char=='('):
                layer = layer + 1
#.........这里部分代码省略.........

# 需要导入模块: from influxdb.influxdb08 import DataFrameClient [as 别名]
# 或者: from influxdb.influxdb08.DataFrameClient import switch_database [as 别名]
'''
Created on Jul 2, 2015

@author: shaunz
'''
from influxdb.influxdb08 import DataFrameClient
from pandas import DataFrame
from FredAPI import FredLink
from FredLink.FredTicker import Fred_ticker_list
import timeit

fred = FredLink()
df = DataFrameClient('localhost', 8086, 'root', 'root')
if({'name':'FRED'} not in df.get_list_database()):
    df.create_database('FRED')

df.switch_database('FRED')

for series in df.get_list_series():
    df.delete_series(series)

start = timeit.default_timer()
for item in Fred_ticker_list:
    results = fred.get_series(item[1])
    results = results.replace(to_replace='NaN',value='.')
    data = DataFrame({'value': results})
    print item
    df.write_points({item[0]:data})
print 'total time in seconds: %.2f' % (timeit.default_timer() - start)