JohnDeJesus22

def jb_test_statistic(column):
    
    """
    Function for creating JB test statistic equation from pandas dataframe column
    """
    # have all nulls removed, get the data length, and convert column values to an array
    column = column.dropna()
    n = column.shape[0]
    column_values = column.values
    

JohnDeJesus22

# apply Jarque-Bera Test to baby_counts for each year
years = baby_names["Year of Birth"].sort_values().unique().tolist()

for year in years:
    baby_year = baby_names[baby_names["Year of Birth"] == year]
    
    jb_results = jarque_bera(baby_year["Count"])
    print(f"Jarque-Bera Count Results for {year}: {jb_results}")

JohnDeJesus22

# compute jarque_bera for Counts column
jarque_bera(baby_names["Count"])

JohnDeJesus22

# import libraries
import pandas as pd
from scipy.stats import jarque_bera

# load data
baby_names = pd.read_csv("Popular_Baby_Names.csv")

# inspect data
baby_names.info()

JohnDeJesus22

recall = cm[1,1]/(cm[1,1] + cm[1,0])
precision = cm[1,1]/(cm[1,1] + cm[0, 1])
fmi = sqrt(precision * recall)

JohnDeJesus22

recall = cm[1,1]/(cm[1,1] + cm[1,0])
specificity = cm[0,0]/(cm[0,0] + cm[0,1])

numerator = sqrt(recall * (-specificity+1)) + specificity - 1
denominator = recall + specificity - 1

prevalence_threshold = numerator/denominator

JohnDeJesus22

numerator = (cm[1,1] * cm[0,0]) - (cm[0,1] * cm[1,0])
denominator = sqrt((cm[1,1] + cm[0,1]) * (cm[1,1] + cm[1,0]) * (cm[0,0] + cm[0,1]) * (cm[0,0] + cm[1,0]))
mcc = numerator/denominator

JohnDeJesus22

precision = cm[1, 1]/(cm[1,1] + cm[0, 1])
negative_predictive_value = cm[0, 0]/(cm[0,0] + cm[1,0])
markedness = precision + negative_predictive_value - 1

JohnDeJesus22

recall = cm[1, 1]/(cm[1,1] + cm[1,0])
specificity = cm[0, 0]/(cm[0,0] + cm[0,1])
informedness = recall + specificity - 1

JohnDeJesus22

precision = cm[1,1]/(cm[1,1] + cm[0,1])
recall = cm[1,1]/(cm[1,1] + cm[1,0])
numerator = precision*recall
denominator = precision + recall
f1_score = 2* numerator/denominator