kperry2215

def plot_data(df, x_variable, y_variable, title):
    """
    Plot the x- and y- variables against each other, where the variables are columns in
    a pandas dataframe
    df: Pandas dataframe. 
    x_variable: String. Name of x-variable column
    y_variable: String. Name of y-variable column
    title: String. Desired title name
    """
    fig, ax = plt.subplots()

kperry2215

#Pull the day of month for each reading
electricity_demand_df['Day_Of_Month']=electricity_demand_df['Date_Time'].dt.day
#Pull the month of the year
electricity_demand_df['Month']=electricity_demand_df['Date_Time'].dt.month.apply(lambda x: calendar.month_abbr[x])
#Pull the year
electricity_demand_df['Year']=electricity_demand_df['Date_Time'].dt.year
    
#Calculate the hour with max demand for each date in the data set
electricity_demand_df['Peak_Demand_Hour_MWh_For_Day']=electricity_demand_df.groupby(['Day_Of_Month', 
                                                        'Month', 

kperry2215

#Create a histogram of counts by hour
ax=peak_demand_hour_df['Peak_Demand_Hour'].value_counts().plot(kind='bar', 
                                            title='Peak Demand Hour by Number of Occurrences')
ax.set_xlabel("Demand Hour (0-23 hour)")
ax.set_ylabel("Number of Occurrences")

kperry2215

def generate_histogram_of_aggregated_counts(df, 
                                            peak_demand_hour_column, 
                                            group_by_column):
    """
    Generate a histogram of peak demand hour counts, grouped by a column
    Arguments:
        df: Pandas dataframe
        peak_demand_hour_column: String. Name of the column for peak demand hour
        group_by_column: String. Name of column to group by 
    """

kperry2215

#Subset the dataframe to only include the features and labels that we're going to use 
#in the model
peak_demand_hour_model=peak_demand_hour_df[['Peak_Demand_Hour',
                                                      'Day_Of_Week', 
                                                      'Week',
                                                      'Month']]
#Convert the Week, Year, and Peak_Demand_Your variables into categorical string variables (from numeric)
peak_demand_hour_model.loc[:,'Week']=peak_demand_hour_model['Week'].apply(str)
peak_demand_hour_model.loc[:,'Peak_Demand_Hour']='Hour '+peak_demand_hour_model['Peak_Demand_Hour'].apply(str)
 

kperry2215

# Split the data into training and testing sets
train_features, test_features, train_labels, test_labels = train_test_split(features, 
                                                                            labels, 
                                                                            test_size = 0.25, 
                                                                            random_state = 5)  

kperry2215

def grid_search_rf(parameter_grid, train_features, train_labels):
    """
    Perform Grid Search on the random forest classifier model, in order to optimize model 
    parameters
    parameter_grid: grid parameters to test against to determine optimal parameters
    train_features: Numpy array, containing training set features
    train_labels: Numpy array, containing training set labels
    """
    # Create a random forest classifier model
    rf = RandomForestClassifier()

kperry2215

#Plug in optimized model parameters into final RF model 
rf = RandomForestClassifier(n_estimators=1100, 
                                max_depth=100,
                                random_state = 1500)
#Fit the model 
rf.fit(train_features, train_labels)
# Use the forest's predict method on the test data
print(confusion_matrix(test_labels, 
                           rf.predict(test_features),
                           labels=['Hour 8', 'Hour 9', 'Hour 10', 

kperry2215

#Obtain feature importances in the model
feature_importances = pd.DataFrame(rf.feature_importances_,
                                   index = feature_list,
                                   columns=['importance']).sort_values('importance', 
                                   ascending=False)
print(feature_importances)

kperry2215

def retrieve_time_series(api, series_ID):
    """
    Return the time series dataframe, based on API and unique Series ID
    api: API that we're connected to
    series_ID: string. Name of the series that we want to pull from the EIA API
    """
    #Retrieve Data By Series ID 
    series_search = api.data_by_series(series=series_ID)
    ##Create a pandas dataframe from the retrieved time series
    df = pd.DataFrame(series_search)