MIT xPRO: DSx Data Science and Big Data Analytics: Making Data-Driven Decisions - Challenger Case Study

main.py

import numpy as np
import statsmodels.discrete.discrete_model as sm
import matplotlib as mpl
import pandas as pd

from patsy import dmatrices
from matplotlib import pyplot as plt

data = pd.read_csv("challenger-data.csv")

# subsetting data
failures = data.loc[(data.Y == 1)]
no_failures = data.loc[(data.Y == 0)]

# frequencies
failures_freq = failures.X.value_counts()
no_failures_freq = no_failures.X.value_counts()

# plotting
plt.scatter(failures_freq.index, failures_freq, c="red", s=40)
plt.scatter(no_failures_freq.index, np.zeros(
	len(no_failures_freq)), c="blue", s=40)
plt.xlabel("X: Temperature")
plt.ylabel("Number of Failures")
plt.show()

# get the data in correct format
y, X = dmatrices("Y ~ X", data, return_type="dataframe")

# build the model
logit = sm.Logit(y, X)
result = logit.fit()

# summarize the model
print(result.summary())

requirements.txt

matplotlib==3.3.4
numpy==1.18.0
pandas==1.2.2
patsy==0.5.1
statsmodels==0.12.2