def test_plot_month():
dta = sm.datasets.elnino.load_pandas().data
dta['YEAR'] = dta.YEAR.astype(int).apply(str)
dta = dta.set_index('YEAR').T.unstack()
dates = lmap(lambda x: pd.tseries.tools.parse_time_string('1 '+' '.join(x))[0],
dta.index.values)
# test dates argument
fig = month_plot(dta.values, dates=dates, ylabel='el nino')
plt.close(fig)
# test with a TimeSeries DatetimeIndex with no freq
dta.index = pd.DatetimeIndex(dates)
fig = month_plot(dta)
plt.close(fig)
# w freq
dta.index = pd.DatetimeIndex(dates, freq='MS')
fig = month_plot(dta)
plt.close(fig)
# test with a TimeSeries PeriodIndex
dta.index = pd.PeriodIndex(dates, freq='M')
fig = month_plot(dta)
plt.close(fig)
def test_plot_month():
dta = sm.datasets.elnino.load_pandas().data
dta['YEAR'] = dta.YEAR.astype(int).apply(str)
dta = dta.set_index('YEAR').T.unstack()
dates = lmap(
lambda x: pd.datetools.parse_time_string('1 ' + ' '.join(x))[0],
dta.index.values)
# test dates argument
fig = month_plot(dta.values, dates=dates, ylabel='el nino')
plt.close(fig)
# test with a TimeSeries DatetimeIndex with no freq
dta.index = pd.DatetimeIndex(dates)
fig = month_plot(dta)
plt.close(fig)
# w freq
dta.index = pd.DatetimeIndex(dates, freq='M')
fig = month_plot(dta)
plt.close(fig)
# test with a TimeSeries PeriodIndex
dta.index = pd.PeriodIndex(dates, freq='M')
fig = month_plot(dta)
plt.close(fig)
def show_month_plot(self):
if self.has_validation_error:
return
# Month_plot() requires the data to have a monthly (12 or 'M') frequency
# Alternative: quarter_plot() for dataset with a frequency of 4 or 'Q'
fig, ax1 = plt.subplots(1, 1, figsize=(12, 8))
month_plot(self.series, ax=ax1)
plt.title("Month Plot of Vaccine Demand of {} in {}".format(
self.vaccine, self.health_facility))
plt.grid(axis='both')
plt.tight_layout()
plt.show()
def test_plot_month(close_figures):
dta = elnino.load_pandas().data
dta["YEAR"] = dta.YEAR.astype(int).apply(str)
dta = dta.set_index("YEAR").T.unstack()
dates = pd.to_datetime(["-".join([x[1], x[0]]) for x in dta.index.values])
# test dates argument
fig = month_plot(dta.values, dates=dates, ylabel="el nino")
# test with a TimeSeries DatetimeIndex with no freq
dta.index = pd.DatetimeIndex(dates)
fig = month_plot(dta)
# w freq
dta.index = pd.DatetimeIndex(dates, freq="MS")
fig = month_plot(dta)
# test with a TimeSeries PeriodIndex
dta.index = pd.PeriodIndex(dates, freq="M")
fig = month_plot(dta)
# test localized xlabels
try:
with calendar.different_locale("DE_de"):
fig = month_plot(dta)
labels = [_.get_text() for _ in fig.axes[0].get_xticklabels()]
expected = [
"Jan",
"Feb",
("Mär", "Mrz"),
"Apr",
"Mai",
"Jun",
"Jul",
"Aug",
"Sep",
"Okt",
"Nov",
"Dez",
]
for lbl, exp in zip(labels, expected):
if isinstance(exp, tuple):
assert lbl in exp
else:
assert lbl == exp
except locale.Error:
pytest.xfail(reason="Failure due to unsupported locale")
def test_plot_month(close_figures):
dta = sm.datasets.elnino.load_pandas().data
dta['YEAR'] = dta.YEAR.astype(int).apply(str)
dta = dta.set_index('YEAR').T.unstack()
dates = pd.to_datetime(['-'.join([x[1], x[0]]) for x in dta.index.values])
# test dates argument
fig = month_plot(dta.values, dates=dates, ylabel='el nino')
# test with a TimeSeries DatetimeIndex with no freq
dta.index = pd.DatetimeIndex(dates)
fig = month_plot(dta)
# w freq
dta.index = pd.DatetimeIndex(dates, freq='MS')
fig = month_plot(dta)
# test with a TimeSeries PeriodIndex
dta.index = pd.PeriodIndex(dates, freq='M')
fig = month_plot(dta)
def test_plot_month(close_figures):
dta = sm.datasets.elnino.load_pandas().data
dta['YEAR'] = dta.YEAR.astype(int).apply(str)
dta = dta.set_index('YEAR').T.unstack()
dates = pd.to_datetime(['-'.join([x[1], x[0]]) for x in dta.index.values])
# test dates argument
fig = month_plot(dta.values, dates=dates, ylabel='el nino')
# test with a TimeSeries DatetimeIndex with no freq
dta.index = pd.DatetimeIndex(dates)
fig = month_plot(dta)
# w freq
dta.index = pd.DatetimeIndex(dates, freq='MS')
fig = month_plot(dta)
# test with a TimeSeries PeriodIndex
dta.index = pd.PeriodIndex(dates, freq='M')
fig = month_plot(dta)
from statsmodels.tsa.stattools import grangercausalitytests
grangercausalitytests(df3[['a', 'd']], maxlag=5)
grangercausalitytests(df3[['b', 'd']], maxlag=5)
np.random.seed(42)
df = pd.DataFrame(np.random.randint(20, 30, (50, 2)),
columns=['test', 'predictions'])
df.head()
df.plot(figsize=(12, 8))
from statsmodels.tools.eval_measures import mse, rmse, meanabs
mse(df['test'], df['predictions'])
rmse(df['test'], df['predictions'])
meanabs(df['test'], df['predictions'])
df1.head()
df1.index
from statsmodels.graphics.tsaplots import month_plot, quarter_plot
month_plot(df1['Pass_K'])
df1q = df1['Pass_K'].resample(rule='Q').sum()
quarter_plot(df1q)
print("Weak evidence against the null hypothesis - do not reject")
print("Data is NON-stationary")
print('*******************************')
# --- |||
# now run the test on the specific series
adf_run1 = adf_test(df1['Thousands of Passengers'])
print(adf_run1)
adf_run2 = adf_test(df2['Births'])
print(adf_run2)
#Granger causality test
#load a new dataset
df3 = pd.read_csv('data/samples.csv', index_col=0, parse_dates=True)
df3.index.freq='MS'
# run the test after inputing a guessed maxlag
granger1 = grangercausalitytests(df3[['a', 'd']], maxlag=2)
# seasonality check
month_plot(df1['Thousands of Passengers'])
#if we have quarterly data, we can resample the data
quarterly_data = df1['Thousands of Passengers'].resample(rule='Q').mean()
quarter_plot(quarterly_data)
# plt.show()
def main():
# IN THE SIDEBAR
ticker = sl.sidebar.text_input("Ticker:")
input = sl.sidebar.date_input("Startdatum:", datetime.datetime.now())
output = sl.sidebar.date_input("Einddatum:", datetime.datetime.now())
try:
df = Load_data(1000000, ticker=ticker)
df = df.loc[str(input):str(output)]
df1 = df.copy()
except Exception as e:
sl.write("Please typ in a ticker")
sl.title("Stockdata analyzer")
sl.write("___________________________________________")
multi = sl.multiselect("Choose your graph",
("Close", "Open", "Adj Close", "High", "Low"))
print(multi)
sl.write("___________________________________________")
img = Image.open("machine-learning-840x485.png")
sl.image(img, width=650, caption="Machine learning")
sl.markdown("""
""")
sl.markdown("""
""")
sl.markdown("""
""")
sl.markdown("""
""")
sl.markdown("""
""")
sl.markdown("""
""")
sl.subheader("Graphs")
sl.write("___________________________________________")
sl.write("Line chart of " + ticker)
if not sl.line_chart(df[multi]):
sl.error("please select a ticker")
sl.write("Bar chart of " + ticker)
sl.bar_chart(df[multi])
df1 = df1.resample("M").mean()
sl.write("Month chart of " + ticker)
plot = month_plot(df1["change"])
sl.write(plot)
sl.subheader("Data")
sl.write("___________________________________________")
sl.write(df, width=1000)
dftest = adfuller(df1['Thousands of Passengers'])
from statsmodels.tools.eval_measures import mse, rmse, meanabs
mse(df['test'],df['predictions']) #: 17.02
df4 = pd.read_csv('airline_passengers.csv', index_col = 'Month',parse_dates= True )
df4.index.freq = 'MS'
from statsmodels.graphics.tsaplots import month_plot, quarter_plot
month_plot(df4['Thousands of Passengers']);
dfq = df4['Thousands of Passengers'].resample(rule = 'Q').mean()
quarter_plot(dfq)
dfout = pd.Series(dftest[0:4], index =['ADF Test Statisctics','p-value','#lags used','# Observations'] )
