def get_quote_database(table, symbol, timerange): ''' table: sqlite3 database table object database primary key: date in mdates ordinal format return: pandas dataframe ''' selection = True if len(timerange) == 1: od1 = int(mdates.date2num(timerange[0])) od2 = od1 + 1 elif len(timerange) == 2: od1 = int(mdates.date2num(timerange[0])) od2 = int(mdates.date2num(timerange[1])) + 1 print 'request range:', [od1, od2] ts1, ts2 = table.get_timestamp_range() print 'available data range: ', [ts1, ts2] if ts1 and ts2: if (od2 < ts1) or (od1 > ts2): selection = False if selection is True: data = table.to_dataframe([od1, od2]) print data.head() return data else: print "no selection available" return pd.DataFrame({})
def quandl_api(userticker,scraped_data): tickers = [userticker]; # api call to quandl, gte and lte are data bounds data = quandl.get_table('WIKI/PRICES', ticker = tickers, qopts = { 'columns': ['ticker', 'date', 'adj_close'] }, date = { 'gte': '2018-01-19', 'lte': '2018-10-20' }, paginate=True) print(data.head(1)) # get most recent entry onedata=data.head(1) onedata = onedata.reset_index() lastdate = onedata[['date'][0]] lastdatevalue = lastdate[0] lastclosing = onedata[['adj_close'][0]] lastclosingvalue = float(lastclosing[0]) #convert date to human readable format readabledate = "{:%B %d, %Y}".format(lastdatevalue) # extract last closing of stock and conver to number stripcomma = scraped_data["Previous Close"] stripcomma = stripcomma.replace(',' , '') currentclose = float(stripcomma) # find difference in closing value diff = currentclose - lastclosingvalue diff = round(diff,2) print(str(userticker), ' has had a change of', str(diff), 'since', readabledate) # add change to scraped data file strwrite = str(diff) + ' from ' + readabledate scraped_data["change"] = strwrite
import pandas as pd from pandas_datareader import data start_date = '2019-01-01' end_date = '2020-01-01' ticker = 'AMZN' data = data.get_data_yahoo(ticker, start_date, end_date) data.head() import matplotlib.pyplot as plt from matplotlib import inline from astropy.utils.tests import data data['Adj Close'].plot(figsize=(10, 7)) plt.title('Adjusted Close Price of %s' % ticker, fontsize=16) plt.ylabel('Price', fontsize=14) plt.xlabel('Year', fontsize=14) plt.grid(which='major', color='k', linestyle='_.', linewidth=0.5) plt.show()
# Rolling Windows rolling = goog.rolling(365, center = True) data = pd.DataFrame({'input': goog, 'one-year rolling_mean': rolling.mean(), 'one-year rolling_std': rolling.std()}) ax = data.plot(style = ['-', '--', ':']) ax.lines[0].set_alpha(0.3) #%% # example: Visualizing Seattle Bycicle Counts data = pd.read_csv('data/Fremont_Bridge.csv', index_col = 'Date', parse_dates =True) #%% print(data.head()) print(data.columns) #%% data.columns = ['Total', 'East', 'West'] #%% data.dropna().describe() #%% # Visualizing the data data.plot() plt.ylabel('Hourly Bicycle Count') #%% resample data to a coarser grid weekly = data.resample('W').sum() weekly.plot(style = [':', '--', '-'])
def get_data_summary(data): print("datasize: ", len(data)) print("No. of columns : ", len(data.columns)) print("\nColumn List:", list(data.columns), "\n") print("\n data glimpse\n") print(data.head())
from datetime import date from sklearn.neural_network import MLPRegressor from sklearn.linear_model import LinearRegression from sklearn.metrics import mean_squared_error from pandas.plotting import scatter_matrix # In[2]: data = pd.read_csv( '/Users/xiangliu/Desktop/CSC560 Data/pollution_us_2000_2016.csv') data.shape # In[3]: data.head(3) # In[4]: le = data['CO AQI'] le[le.isnull()] # In[5]: ##Look Into each value data = data.dropna() data.to_csv("/Users/xiangliu/Desktop/CSC560 Data/pollution_AQI.csv", index=True, sep=',') # In[6]:
import pandas_datareader as pdr df = pdr.get_data_fred('GS10') #https://fred.stlouisfed.org/series/GS10 df.shape df.head() import pandas as pd from pandas_datareader import data # Set the start and end date start_date = '1990-01-01' end_date = '2019-04-27' # Set the ticker ticker = 'AMZN' # Get the data data = data.get_data_yahoo(ticker, start_date, end_date) data.head() data.shape df = data.drop(['Volume'], axis=1) import matplotlib.pyplot as plt data['Adj Close'].plot() df.plot() plt.savefig('pandas_datareader_demo1.png') import yfinance as yf data = yf.download("SPY AAPL", start="2017-01-01", end="2017-04-30") data.shape data.head(10)
# quantrautil is a module specific to Quantra to fetch stock data from quantrautil import get_quantinsti_api_key api_key = get_quantinsti_api_key() data = quandl.get('EOD/AAPL', start_date='2017-1-1', end_date='2018-1-1', api_key= api_key) # Note that you need to know the "Quandl code" of each dataset you download. In the above example, it is 'EOD/AAPL'. # To get your personal API key, sign up for a free Quandl account. Then, you can find your API key on Quandl account settings page. print("________________________") print(data.head())''' import pandas as pd from pandas_datareader import data data = data.get_data_yahoo('AAPL', '2017-01-01', '2018-01-01') data.head() print(data.head()) # Yahoo recently has become an unstable data source. # If it gives an error, you may run the cell again, or try yfinance import pandas as pd from pandas_datareader import data # Set the start and end date start_date = '1990-01-01' end_date = date.today() #'2019-02-01' # Set the ticker ticker = 'AMZN' # Get the data data = data.get_data_yahoo(ticker, start_date, end_date) data.head()