kperry2215

import pandas as pd 
import matplotlib.pyplot as plt 

class fracfocus_data_search:
    """
    This class generates an object that is used the filter the master
    fracfocus dataframe so it only contains a certain state/state abbreviation,
    county (list), and/or operator
    """

kperry2215

def generate_bar_graph(df, title):
    """
    This function creates a bar graph from pandas dataframe columns.
    Arguments:
        df: Pandas dataframe. Index will be x-axis. Categories and 
        associated amounts are from columns
        title: String. Name of the bar graph
    Outputs:
        Bar graph in console.
    """

kperry2215

def generate_boxplot(df, x_variable):
    """
    This function generates a basic histogram of a column's data, with
    outliers removed
    Arguments:
        df: Pandas dataframe
        x_variable: String. Name of the column that we want to generate 
        boxplot from
    Outputs:
        Box plot in console.

kperry2215

#Plot the 'TotalBaseNonWaterVolume' variable over time
generate_plot(dataframe, x_variable='JobStartDate', 
              y_variables=['TotalBaseNonWaterVolume'], 
              plot_title='Total Base Non-Water Volume for Fracs over Time')

kperry2215

def generate_plot(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
    Outputs:

kperry2215

#Pull all of the fracfocus data from a csv
fracfocus_registry=pd.read_csv('fracfocus_data_example.csv', low_memory=False)
#Make all of the state column lowercase
fracfocus_filter=fracfocus_data_search(state='Texas', state_abbreviation='TX',
                          county_list=['Andrews', 'Borden', 'Crane', 'Dawson',
                                       'Ector', 'Eddy', 'Gaines', 'Glasscock'], operator='XTO')
#Filter dataframe by its parameters
subsetted_df=fracfocus_filter.filter_dataframe(fracfocus_registry, column_state='StateName', 
                        column_county='CountyName', column_operator='OperatorName')

kperry2215

class fracfocus_data_search:
    """
    This class generates an object that is used the filter the master
    fracfocus dataframe so it only contains a certain state/state abbreviation,
    county (list), and/or operator
    """

    def __init__(self, state=None, state_abbreviation=None, county_list=None,
                 operator=None):
        #All data in initialize def optional depending on what kind of filtering

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:

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 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