Skip to content

Instantly share code, notes, and snippets.

@ifnull

ifnull/main.py

Last active February 10, 2021 06:26
Show Gist options
  • Save ifnull/859454d076791c99a52510af4bcf6088 to your computer and use it in GitHub Desktop.
Save ifnull/859454d076791c99a52510af4bcf6088 to your computer and use it in GitHub Desktop.
Download ZIP
MIT xPRO: DSx Data Science and Big Data Analytics: Making Data-Driven Decisions - Challenger Case Study
Raw
challenger-data.csv
Observation Y X
1 1 53
2 1 53
3 1 53
4 0 53
5 0 53
6 1 57
7 0 57
8 0 57
9 0 57
10 0 57
11 1 58
12 0 58
13 0 58
14 0 58
15 0 58
16 1 63
17 0 63
18 0 63
19 0 63
20 0 63
21 0 66
22 0 66
23 0 66
24 0 66
25 0 66
26 0 67
27 0 67
28 0 67
29 0 67
30 0 67
31 0 67
32 0 67
33 0 67
34 0 67
35 0 67
36 0 67
37 0 67
38 0 67
39 0 67
40 0 67
41 0 68
42 0 68
43 0 68
44 0 68
45 0 68
46 0 69
47 0 69
48 0 69
49 0 69
50 0 69
51 1 70
52 0 70
53 0 70
54 0 70
55 0 70
56 1 70
57 0 70
58 0 70
59 0 70
60 0 70
61 0 70
62 0 70
63 0 70
64 0 70
65 0 70
66 0 70
67 0 70
68 0 70
69 0 70
70 0 70
71 0 72
72 0 72
73 0 72
74 0 72
75 0 72
76 0 73
77 0 73
78 0 73
79 0 73
80 0 73
81 1 75
82 1 75
83 0 75
84 0 75
85 0 75
86 0 75
87 0 75
88 0 75
89 0 75
90 0 75
91 0 76
92 0 76
93 0 76
94 0 76
95 0 76
96 0 76
97 0 76
98 0 76
99 0 76
100 0 76
101 0 78
102 0 78
103 0 78
104 0 78
105 0 78
106 0 79
107 0 79
108 0 79
109 0 79
110 0 79
111 0 80
112 0 80
113 0 80
114 0 80
115 0 80
116 0 81
117 0 81
118 0 81
119 0 81
120 0 81
Raw
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())
Raw
requirements.txt
matplotlib==3.3.4
numpy==1.18.0
pandas==1.2.2
patsy==0.5.1
statsmodels==0.12.2
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment