"""
import pandas as pd
import numpy as np
import os
from sklearn.naive_bayes import GaussianNB
from helper_package import helper_functions as hf
from helper_package import feature_set as fs
from helper_package import confusion_matrix_calcs as cm
from helper_package import assign_labels as al
# raises numpy errors/warnings so they can be caught by try/except
np.seterr(all='raise')
# allow df console output to display more columns
hf.show_more_df()
# get DataFrame of stock ticker info from csv file
df = hf.fix_column_names(hf.get_ticker_df())
df = al.assign_color_labels(df) # assign color labels
df = fs.get_feature_set(df) # add mean and std return columns for DF
def nb_predict(df1, df2):
"""
Gaussian Naive Bayesian classification of labels (colors)
:param df1: Training set (DataFrame)
:param df2: Prediction set (DataFrame)
:return: df2 with predicted label (binary) and color columns
"""
5. What is the avg number of days for long position and short position
transactions in year 2?
6. Are these results very different from those in year 1 for this value of W?
"""
import pandas as pd
import numpy as np
import os
import copy
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression
from helper_package import helper_functions as hf
import Assignment4.window_strategy as ws
hf.show_more_df() # allow df output to display more rows/columns
df = hf.fix_column_names(hf.get_ticker_df()) # get DataFrame of ticket file
def create_w_list(w_min, w_max, step=1):
"""
Create list of w values (used as 'windows' for estimation)
:param w_min: Minimum w value
:param w_max: maximum w value
:param step: step for w values in list
:return output_list: list of w values
"""
output_list = [] # list of w values
for i in range(w_min, w_max + 1):
output_list.append(i)
i += step