kperry2215

def hyperbolic_equation(t, qi, b, di):
    """
    Hyperbolic decline curve equation
    Arguments:
        t: Float. Time since the well first came online, 
can be in various units 
        (days, months, etc) so long as they are consistent.
        qi: Float. Initial production rate when well first came online.
        b: Float. Hyperbolic decline constant
        di: Float. Nominal decline rate at time t=0

kperry2215

def hyperbolic_equation(t, qi, b, di):
    """
    Hyperbolic decline curve equation
    Arguments:
        t: Float. Time since the well first came online, can be in various units 
        (days, months, etc) so long as they are consistent.
        qi: Float. Initial production rate when well first came online.
        b: Float. Hyperbolic decline constant
        di: Float. Nominal decline rate at time t=0
    Output: 

kperry2215

def hyperbolic_equation(t, qi, b, di):
    """
    Hyperbolic decline curve equation
    Arguments:
        t: Float. Time since the well first came online, can be in various units 
        (days, months, etc) so long as they are consistent.
        qi: Float. Initial production rate when well first came online.
        b: Float. Hyperbolic decline constant
        di: Float. Nominal decline rate at time t=0
    Output: 

kperry2215

def get_max_initial_production(df, number_first_months, variable_column, date_column):
    """
    This function allows you to look at the first X months of production, and selects 
    the highest production month as max initial production
    Arguments:
        df: Pandas dataframe. 
        number_first_months: float. Number of months from the point the well comes online
        to compare to get the max initial production rate qi (this looks at multiple months
        in case there is a production ramp-up)
        variable_column: String. Column name for the column where we're attempting to get

kperry2215

#Get the highest value of production in the first three months of production, to use as qi value
qi=get_max_initial_production(production_time_series, 3, desired_product_type, 'ReportDate')
#Exponential curve fit the data to get best fit equation
popt_exp, pcov_exp=curve_fit(exponential_equation, production_time_series['Days_Online'], 
                             production_time_series[desired_product_type],
                             bounds=(0, [qi,20]))
print('Exponential Fit Curve-fitted Variables: qi='+str(popt_exp[0])+
      ', di='+str(popt_exp[1]))
#Hyperbolic curve fit the data to get best fit equation
popt_hyp, pcov_hyp=curve_fit(hyperbolic_equation, production_time_series['Days_Online'], 

kperry2215

def plot_actual_vs_predicted_by_equations(df, x_variable, y_variables, plot_title):
    """
    This function is used to map x- and y-variables against each other
    Arguments:
        df: Pandas dataframe.
        x_variable: String. Name of the column that we want to set as the 
        x-variable in the plot
        y_variables: string (single), or list of strings (multiple). Name(s) 
        of the column(s) that we want to set as the y-variable in the plot
    """

kperry2215

#Declare the x- and y- variables that we want to plot against each other
y_variables=[desired_product_type, "Hyperbolic_Predicted", "Exponential_Predicted"]
x_variable='Days_Online'
#Create the plot title
plot_title=desired_product_type+' Production for Well API '+str(api_number)
#Plot the data to visualize the equation fit
plot_actual_vs_predicted_by_equations(production_time_series, x_variable, y_variables, plot_title)
                

kperry2215

import pandas as pd
from scipy.optimize import curve_fit
import numpy as np
import matplotlib.pyplot as plt

def read_in_csv(file_path):
    """
    Read in the specified csv as a pandas dataframe
    Arguments: 
        file_path: String. Path for the csv file that we want to read in

kperry2215

"""
This script is used to query data directly from the EPA's Envirofacts API, and land in
a pandas data frame. In this script, the GHG data tables are pulled and merged together to 
create a master dataframe containing all of the GHG data we'd need for analysis:
facility location, sector, and subsector, and emissions and emission type by year
"""
import pandas as pd
import io
import requests

kperry2215

#Import desired packages 
import requests
import zipfile
import io
import pandas as pd

def pull_zip_file_from_url(url):
    """
    This function pulls a zip file from a URL and generates a ZipFile object
    Arguments: