erykml

import pandas as pd
from fbprophet import Prophet
from neuralprophet import NeuralProphet
from sklearn.metrics import mean_squared_error

# plotting
import matplotlib.pyplot as plt

# settings
plt.style.use('seaborn')

erykml

class GroupImputer(BaseEstimator, TransformerMixin):
    '''
    Class used for imputing missing values in a pd.DataFrame using either mean or median of a group.
    
    Parameters
    ----------    
    group_cols : list
        List of columns used for calculating the aggregated value 
    target : str
        The name of the column to impute

erykml

import quandl

# authentication ----
quandl_key = 'key' # paste your own API key here :)
quandl.ApiConfig.api_key = quandl_key
df = quandl.get('WIKI/MSFT', start_date="2000-01-01", end_date="2017-12-31")
df = df.loc[:, ['Adj. Close']]
df.columns = ['adj_close']

# create simple and log returns, multiplied by 100 for convenience

erykml

import pandas as pd
import numpy as np
from sklearn.linear_model import LinearRegression
from statsmodels.graphics.tsaplots import plot_acf, plot_pacf
from statsmodels.tsa.stattools import acf, pacf
from statsmodels.tsa.tsatools import lagmat

import matplotlib.pyplot as plt

# settings

erykml

class FrameExtractor():
    '''
    Class used for extracting frames from a video file.
    '''
    def __init__(self, video_path):
        self.video_path = video_path
        self.vid_cap = cv2.VideoCapture(video_path)
        self.n_frames = int(self.vid_cap.get(cv2.CAP_PROP_FRAME_COUNT))
        self.fps = int(self.vid_cap.get(cv2.CAP_PROP_FPS))
        

erykml

# for reproducibility
np.random.seed(42)
# generate the DataFrame with dates
range_of_dates = pd.date_range(
    start="2017-01-01",
    end="2020-12-30"
)
X = pd.DataFrame(index=range_of_dates)
# create a sequence of day numbers
X["day_nr"] = range(len(X))

erykml

assets = ['TSLA', 'MSFT', 'FB']

yahoo_financials = YahooFinancials(assets)

data = yahoo_financials.get_historical_price_data(start_date='2019-01-01', 
                                                  end_date='2019-12-31', 
                                                  time_interval='weekly')

prices_df = pd.DataFrame({
    a: {x['formatted_date']: x['adjclose'] for x in data[a]['prices']} for a in assets

erykml

theilsen = TheilSenRegressor(random_state=42).fit(X, y)
fit_df["theilsen_regression"] = theilsen.predict(plotline_X)
coef_list.append(["theilsen_regression", theilsen.coef_[0]])

erykml

plt.scatter(X[inlier_mask], y[inlier_mask], color="blue", label="Inliers")
plt.scatter(X[outlier_mask], y[outlier_mask], color="red", label="Outliers")
plt.title("RANSAC - outliers vs inliers");

erykml

inlier_mask = ransac.inlier_mask_
outlier_mask = ~inlier_mask
print(f"Total outliers: {sum(outlier_mask)}")
print(f"Outliers we have added ourselves: {sum(outlier_mask[:N_OUTLIERS])} / {N_OUTLIERS}")