def get_risk_free_rate_daily():
c()
start = start_date1
end = end_date1
source_two = 'fred'
code = 'DGS10'
rfr = DataReader(code, source_two, start, end)
rfr = rfr.dropna()
rfr = rfr.mean() / 100
d_rfr = rfr / 252
return np.float64(d_rfr)
#avg hourly earnings (Fred: CES0500000003 - from Mar 2006)
from statsmodels.tsa.vector_ar.vecm import select_order
from statsmodels.tsa.vector_ar.vecm import select_coint_rank
from statsmodels.tsa.vector_ar.vecm import VECM
from dateutil.relativedelta import relativedelta
start_data = datetime.now() - relativedelta(years=66)
today = datetime.now()
from pandas_datareader.data import DataReader
consumer_df = DataReader([
'PCE', 'UMCSENT', 'UNRATE', 'LCEAMN01USM189S', 'TOTALSL', 'MRTSSM44X72USS',
'HOUST'
], 'fred', start_data, today)
consumer_df = consumer_df.dropna()
consumer_df.columns = [
'PCE', 'ConConf', 'Unempl', 'HourlyEarning', 'CCredit', 'RetSales',
'HouseStarts'
]
consumer_df = consumer_df.resample('1M').mean()
type(consumer_df)
# lag order selection
lag_order = select_order(data=consumer_df,
maxlags=10,
deterministic="ci",
seasons=12)
print(lag_order.summary())
print(lag_order)
# -*- coding: utf-8 -*-
"""
Created on Tue Oct 31 23:46:25 2017
@author: James
"""
from pandas_datareader.data import DataReader
from datetime import date
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
ty10 = DataReader('DGS10', 'fred', date(1962, 1, 1))
ty10.dropna(inplace=True)
ty10.plot(title='10-year Treasury')
plt.tight_layout()
plt.show()
#using seaborn with Kernal Desnsity Estimate
sns.distplot(ty10)
ax = sns.distplot(ty10)
ax.axvline(ty10['DGS10'].median(), color='blue', ls='-.')
plt.close()
#visualizing international income distributions
#list the poorest and richest countries worldwide
#-----------------------------------------------------------------------------------------------------------------------
# INPUT
TARGET = "sp500"
pDATA = DataReader(TARGET,'fred',datetime(1985,1,1), datetime.today()).dropna(how='any')
# STEP 1.2 Build Target Value
INVEST_HORIZON = 20
pDATA ['TARGET'] = pDATA[TARGET].pct_change(INVEST_HORIZON).shift(-INVEST_HORIZON)
#-----------------------------------------------------------------------------------------------------------------------
# FEATURE EXTRACTOR
#pDATA = pd.concat([pDATA, moving_average(pDATA, 20), moving_average(pDATA, 60), macd(pDATA,20, 60), signal_noise_ratio(pDATA,60)], axis=1)
pDATA = pd.concat([pDATA, macd(pDATA[TARGET].to_frame(),20, 60), signal_noise_ratio(pDATA[TARGET].to_frame(),60)], axis=1)
pDATA2 = pDATA.dropna(how='any')
#Y = pDATA2['TARGET'].apply(lambda x: 1 if x > 0.0 else 0 ).values
Y = pDATA2['TARGET'].apply(lambda x: -1 if x < 0.0 else 1 if x > 0.035 else 0).values
#Y = pDATA2['TARGET'].values
X = pDATA2[pDATA2.columns[2:]].values
#-----------------------------------------------------------------------------------------------------------------------
# STEP 2 - MACHINE LEARNING
DCTree_classifier = DecisionTreeClassifier(max_depth=3, random_state=0)
DCTree_classifier.fit(X, Y)
Y_pred = DCTree_classifier.predict(X)
print('Decision Tree Accuracy: %.2f' % accuracy_score(Y, Y_pred))
export_graphviz(DCTree_classifier, out_file="decision_tree1.dot",
return dataFrame
count_moving_average(df, 5)
df['Moving_Average_5'] = pd.Series(df['close'].rolling(5,
min_periods=5).mean())
df.head(10)
df[['MA_function', 'OBV', 'close']].plot(figsize=(18, 8), title='MU')
df[['ROC', 'Momentum', 'MA_function', 'OBV', 'close']].plot(figsize=(18, 8),
title='Features')
df['label'] = df.close.shift(-1)
df = df.dropna()
df.head()
# %matplotlib inline
# import mpld3
# mpld3.enable_notebook()
from sklearn import model_selection
from sklearn import preprocessing
from sklearn.linear_model import LinearRegression, ElasticNetCV, Ridge
from sklearn.neural_network import MLPRegressor
from sklearn import linear_model
X = np.array(df[['ROC', 'Momentum', 'close']])
Y = np.array(df.label)
