survival 1.1.29

A high-performance survival analysis library written in Rust with Python bindings
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189

#!/usr/bin/env python3
"""
Test that survival functions accept various array-like inputs:
- Python lists
- NumPy arrays
- Pandas Series
- Polars Series
"""

import os
import sys

import numpy as np

sys.path.insert(0, os.path.dirname(__file__))

from helpers import setup_survival_import

survival = setup_survival_import()
print("Successfully imported survival module")

print("\n=== Testing survfitkm with different input types ===")

time_list = [1.0, 2.0, 3.0, 4.0, 5.0]
status_list = [1.0, 1.0, 0.0, 1.0, 0.0]

print("\n1. Testing with Python lists...")
result = survival.survfitkm(time_list, status_list)
assert hasattr(result, "estimate"), "Should have estimate attribute"
assert len(result.estimate) > 0, "Should have estimates"
print(f"   Passed - estimates: {result.estimate}")

print("\n2. Testing with NumPy arrays...")
time_np = np.array(time_list)
status_np = np.array(status_list)
result = survival.survfitkm(time_np, status_np)
assert hasattr(result, "estimate"), "Should have estimate attribute"
assert len(result.estimate) > 0, "Should have estimates"
print(f"   Passed - estimates: {result.estimate}")

try:
    import pandas as pd

    print("\n3. Testing with Pandas Series...")
    df = pd.DataFrame({"time": time_list, "status": status_list})
    result = survival.survfitkm(df["time"], df["status"])
    assert hasattr(result, "estimate"), "Should have estimate attribute"
    assert len(result.estimate) > 0, "Should have estimates"
    print(f"   Passed - estimates: {result.estimate}")

    print("\n4. Testing with Pandas DataFrame columns (via .values)...")
    result = survival.survfitkm(df["time"].values, df["status"].values)
    assert hasattr(result, "estimate"), "Should have estimate attribute"
    print("   Passed")

except ImportError:
    print("\n3-4. Skipping Pandas tests (pandas not installed)")

try:
    import polars as pl

    print("\n5. Testing with Polars Series...")
    df = pl.DataFrame({"time": time_list, "status": status_list})
    result = survival.survfitkm(df["time"], df["status"])
    assert hasattr(result, "estimate"), "Should have estimate attribute"
    assert len(result.estimate) > 0, "Should have estimates"
    print(f"   Passed - estimates: {result.estimate}")

except ImportError:
    print("\n5. Skipping Polars tests (polars not installed)")


print("\n=== Testing logrank_test with different input types ===")

time_list = [1.0, 2.0, 3.0, 4.0, 5.0, 1.5, 2.5, 3.5, 4.5, 5.5]
status_list = [1, 1, 0, 1, 0, 1, 1, 1, 0, 1]
group_list = [0, 0, 0, 0, 0, 1, 1, 1, 1, 1]

print("\n1. Testing with Python lists...")
result = survival.logrank_test(time_list, status_list, group_list)
assert hasattr(result, "statistic"), "Should have statistic"
assert hasattr(result, "p_value"), "Should have p_value"
print(f"   Passed - statistic: {result.statistic:.4f}, p-value: {result.p_value:.4f}")

print("\n2. Testing with NumPy arrays...")
time_np = np.array(time_list)
status_np = np.array(status_list, dtype=np.int32)
group_np = np.array(group_list, dtype=np.int32)
result = survival.logrank_test(time_np, status_np, group_np)
assert hasattr(result, "statistic"), "Should have statistic"
print(f"   Passed - statistic: {result.statistic:.4f}")

print("\n3. Testing with NumPy int64 arrays (should auto-convert)...")
status_np64 = np.array(status_list, dtype=np.int64)
group_np64 = np.array(group_list, dtype=np.int64)
result = survival.logrank_test(time_np, status_np64, group_np64)
assert hasattr(result, "statistic"), "Should have statistic"
print(f"   Passed - statistic: {result.statistic:.4f}")

try:
    import pandas as pd

    print("\n4. Testing with Pandas Series...")
    df = pd.DataFrame({"time": time_list, "status": status_list, "group": group_list})
    result = survival.logrank_test(df["time"], df["status"], df["group"])
    assert hasattr(result, "statistic"), "Should have statistic"
    print(f"   Passed - statistic: {result.statistic:.4f}")

except ImportError:
    print("\n4. Skipping Pandas tests (pandas not installed)")

try:
    import polars as pl

    print("\n5. Testing with Polars Series...")
    df = pl.DataFrame({"time": time_list, "status": status_list, "group": group_list})
    result = survival.logrank_test(df["time"], df["status"], df["group"])
    assert hasattr(result, "statistic"), "Should have statistic"
    print(f"   Passed - statistic: {result.statistic:.4f}")

except ImportError:
    print("\n5. Skipping Polars tests (polars not installed)")


print("\n=== Testing cv_cox_concordance with different input types ===")

time_list = [1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0]
status_list = [1, 1, 0, 1, 0, 1, 1, 0, 1, 0]
covariates = [[0.5], [0.3], [0.8], [0.2], [0.9], [0.4], [0.6], [0.1], [0.7], [0.5]]

print("\n1. Testing with Python lists...")
result = survival.cv_cox_concordance(time_list, status_list, covariates, n_folds=2)
assert hasattr(result, "mean_score"), "Should have mean_score"
print(f"   Passed - mean C-index: {result.mean_score:.4f}")

print("\n2. Testing with NumPy arrays...")
time_np = np.array(time_list)
status_np = np.array(status_list, dtype=np.int32)
result = survival.cv_cox_concordance(time_np, status_np, covariates, n_folds=2)
assert hasattr(result, "mean_score"), "Should have mean_score"
print(f"   Passed - mean C-index: {result.mean_score:.4f}")

try:
    import pandas as pd

    print("\n3. Testing with Pandas Series...")
    df = pd.DataFrame({"time": time_list, "status": status_list})
    result = survival.cv_cox_concordance(df["time"], df["status"], covariates, n_folds=2)
    assert hasattr(result, "mean_score"), "Should have mean_score"
    print(f"   Passed - mean C-index: {result.mean_score:.4f}")

except ImportError:
    print("\n3. Skipping Pandas tests (pandas not installed)")


print("\n=== Testing optional parameters with different types ===")

print("\n1. Testing survfitkm with optional weights as numpy array...")
weights_np = np.array([1.0, 1.0, 2.0, 1.0, 1.5])
result = survival.survfitkm(
    np.array([1.0, 2.0, 3.0, 4.0, 5.0]),
    np.array([1.0, 1.0, 0.0, 1.0, 0.0]),
    weights=weights_np,
)
assert hasattr(result, "estimate"), "Should have estimate"
print("   Passed")

try:
    import pandas as pd

    print("\n2. Testing survfitkm with optional weights as Pandas Series...")
    df = pd.DataFrame(
        {
            "time": [1.0, 2.0, 3.0, 4.0, 5.0],
            "status": [1.0, 1.0, 0.0, 1.0, 0.0],
            "weights": [1.0, 1.0, 2.0, 1.0, 1.5],
        }
    )
    result = survival.survfitkm(df["time"], df["status"], weights=df["weights"])
    assert hasattr(result, "estimate"), "Should have estimate"
    print("   Passed")

except ImportError:
    print("\n2. Skipping Pandas optional weights test")


print("\n" + "=" * 50)
print("All array input tests passed!")
print("=" * 50)