def start():
"""Start the Data Analyzer"""
engine = create_engine('sqlite:///' + word_to_analyze + '.sqlite')
session = sessionmaker()
session.configure(bind=engine)
Base.metadata.create_all(engine)
s = session()
if count_words:
positive_counter = 0
negative_counter = 0
for positive_words, negative_words in s.query(Tweet.positive_words,
Tweet.negative_words):
positive_counter += positive_words
negative_counter += negative_words
print(word_to_analyze + " had " + str(positive_counter) +
" positive words and " + str(negative_counter) +
" negative words.")
if count_rows:
print("Number of tweets used from " + word_to_analyze + ": ")
print(helpers.countRows(s, Tweet))
norm_Xt_dict = helpers.getXFromData(s, Tweet, True)
norm_Rt_dict = helpers.getRFromCSV(
'2017/10/01', '2017/12/31',
'data/stock/' + word_to_analyze + '-stock-data' + '.csv', True)
combined_2d_results_log = helpers.combineRtandXt(norm_Xt_dict,
norm_Rt_dict)
# VAR
if test_var:
pd_data = pd.DataFrame(combined_2d_results_log, columns=['Rt', 'Xt'])
var_result = VAR(pd_data).fit(maxlag)
print(var_result.summary())
var_result.test_causality('Rt', 'Xt')
# VOORBEELD VAN HOE BESCHRIJVENDE STATESTIEK KAN WORDEN GEPLOT:
# fig = plt.subplots()
# fig = var_result.plot_sample_acorr()
# ax.set_ylabel("Y lable")
# ax.set_xlabel("X lable")
# ax.set_title("Title")
# plt.show()
# GRANGER CAUSALITY ANALYSIS
if test_granger:
result = sm.tsa.stattools.grangercausalitytests(
combined_2d_results_log, maxlag, addconst=True, verbose=True)
# PLOT DATA
if plot_figure:
Xt_dict = helpers.getXFromData(s, Tweet)
Rt_dict = helpers.getRFromCSV(
'2017/10/01', '2017/12/31',
'data/stock/' + word_to_analyze + '-stock-data' + '.csv')
Xt_df = pd.DataFrame(list(Xt_dict.items()), columns=['Date', 'Xt'])
Xt_df['Date'] = pd.to_datetime(Xt_df['Date'])
Rt_df = pd.DataFrame(list(Rt_dict.items()), columns=['Date', 'Rt'])
Rt_df['Date'] = pd.to_datetime(Rt_df['Date'])
Xt_df = Xt_df.sort_values('Date', ascending=True)
plt.plot(Xt_df['Date'],
Xt_df['Xt'],
label='Twitter sentiment',
color='black')
plt.xticks(rotation='horizontal')
Rt_df = Rt_df.sort_values('Date', ascending=True)
plt.plot(Rt_df['Date'],
Rt_df['Rt'],
label='Stock return',
dashes=[6, 2],
color='black')
plt.legend([Xt_df, Rt_df], ['Twitter sentiment', 'Stock return'])
plt.xticks(rotation='horizontal')
if word_to_analyze is 'ibm':
plt.suptitle(word_to_analyze.upper(), fontsize=20)
else:
plt.suptitle(word_to_analyze.title(), fontsize=20)
plt.show()
# VAR fit (no constant term)
results = VAR(mdata).fit(ic='bic', verbose=True, trend='nc')
results.plot()
print(results.summary())
# Selected lag order
print('Selected Order:', results.k_ar)
# AIC & BIC of different lags
for p in range(8):
res = VAR(mdata).fit(p, trend='nc')
print(res.k_ar, '&', round(res.aic, 6), '&', round(res.bic, 6), '\\\\')
# Stability
print(results.is_stable(True))
# Residual normality
print(results.test_normality().summary())
# Granger causality
names = ['r', 'IndProd', 'Unemp']
for n in names:
print('Granger for', n)
# Factor `n` caused by its complement
print(results.test_causality(n, list(set(names) - set(n))).summary())
# Impulse Response Analysis
irf = results.irf(10)
irf.plot(orth=False)
plt.show()
