AVJdataminer

input_url = input("Enter the github url: ")
y = input_url.replace('/blob','')
x = y.replace('github.com','raw.githubusercontent.com')
print("raw url: ", x )

AVJdataminer

# Make a function to find the MSE of a single ARIMA model 
def evaluate_arima_model(data, arima_order):
    # Needs to be an integer because it is later used as an index.
    split=int(len(data) * 0.8) 
    train, test = data[0:split], data[split:len(data)]
    past=[x for x in train]
    # make predictions
    predictions = list()
    for i in range(len(test)):#timestep-wise comparison between test data and one-step prediction ARIMA model. 
        model = ARIMA(past, order=arima_order)

AVJdataminer

import PIL
from PIL import Image
import os
import sys
 
path = "/path/to/file"

dirs = [file for file in os.listdir(path) if file.endswith('.png')]

#pixelsize = 500;

AVJdataminer

def new_dt_split(date_col, X, y, input_date):
    date_col = pd.to_datetime(date_col)
    xw_date=pd.DataFrame(X).merge(date_col, left_index=True, right_index=True)
    X_train = xw_date.loc[xw_date['date'] <= input_date].drop(['date'], axis=1).values
    X_test = xw_date.loc[xw_date['date'] >= input_date].drop(['date'], axis=1).values
    yw_date=pd.DataFrame(y).merge(date_col, left_index=True, right_index=True)
    y_train = yw_date.loc[yw_date['date'] <= input_date].drop(['date'], axis=1).values
    y_test = yw_date.loc[yw_date['date'] >= input_date].drop(['date'], axis=1).values
    return X_train, X_test, y_train, y_test

AVJdataminer

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y,
                                                    stratify=df['Country'], 
                                                    test_size=0.25)

AVJdataminer

from datetime import datetime,timedelta
def dt_splitter(date_col, X, y, test_size):
        xw_date=pd.DataFrame(X).merge(date_col,left_index=True, right_index=True)
        ad = (max(xw_date.date)- min(xw_date.date)).days*test_size
        split_date = min(xw_date.date) + timedelta(days=ad)
        X_train = xw_date.loc[xw_date['date'] <= split_date].drop(['date'], axis=1).values
        X_test = xw_date.loc[xw_date['date'] > split_date].drop(['date'], axis=1).values
        yw_date=pd.DataFrame(y).merge(date_col,left_index=True, right_index=True)
        y_train=yw_date.loc[yw_date['date'] <= split_date].drop(['date'], axis=1).values
        y_test=yw_date.loc[yw_date['date'] > split_date].drop(['date'], axis=1).values

AVJdataminer

def ext_date(df, column):
    df[column] = pd.to_datetime(df[column],format = "%Y-%m-%d")
    df[column] = df[column].dt.strftime('%Y%m%d')

AVJdataminer

filelist = list.files(pattern = ".*.txt")
datalist = lapply(filelist, function(x)read.table(x, header=T)) 

#assuming the same header/columns for all files
datafr = do.call("rbind", datalist)

AVJdataminer

import sklearn.decomposition
pca = sklearn.decomposition.PCA()
pca.fit(X)
variances = pca.explained_variance_ratio_
def select_n_components(var_ratio, goal_var: float) -> int:
    total_variance = 0.0
    n_components = 0
    # For the explained variance of each feature:
    for explained_variance in var_ratio:
        # Add the explained variance to the total

AVJdataminer

import itertools
import numpy as np
import matplotlib.pyplot as plt

from sklearn import svm, datasets
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix

def plot_confusion_matrix(cm, classes,
                          normalize=False,