Move txt data file to arff format.

sksurv/datasets/base.py

@@ -544,17 +544,14 @@ def load_cgvhd():
     .. [2] https://drive.google.com/file/d/1FPM264pE\_-F8DB7lvFeLB1yQ3HDo7c-i/view
            https://sites.google.com/view/melaniapintiliemscstatistics/home/statistics
     """
-    full_path = _get_data_path("cgvhd.txt")
-
-    df = pd.read_csv(full_path)
-    df["ftime"] = df[["survtime", "reltime", "cgvhtime"]].min(axis=1)
-    df["status"] = (
-        ((df["ftime"] == df["cgvhtime"]) & (df["cgvh"] == 1)).astype(int)
-        + 2 * ((df["ftime"] == df["reltime"]) & (df["rcens"] == 1)).astype(int)
-        + 3 * ((df["ftime"] == df["survtime"]) & (df["stat"] == 1)).astype(int)
+    full_path = _get_data_path("cgvhd.arff")
+    data = loadarff(full_path)
+    data["ftime"] = data[["survtime", "reltime", "cgvhtime"]].min(axis=1)
+    data["status"] = (
+        ((data["ftime"] == data["cgvhtime"]) & (data["cgvh"] == "1")).astype(int)
+        + 2 * ((data["ftime"] == data["reltime"]) & (data["rcens"] == "1")).astype(int)
+        + 3 * ((data["ftime"] == data["survtime"]) & (data["stat"] == "1")).astype(int)
     )
-    df = df[["ftime", "status", "tx"]]
-    ftime, event = df["ftime"].values, df["status"].values
+    data = data[["ftime", "status", "dx", "tx", "extent", "age"]]
 
-    #    return get_x_y(data, attr_labels=["status", "ftime"], competing_risks=True)
-    return None, {"ftime": ftime, "status": event}
+    return get_x_y(data, attr_labels=["status", "ftime"], competing_risks=True)

sksurv/datasets/data/cgvhd.arff

@@ -0,0 +1,118 @@
+@RELATION CGVHD
+
+@ATTRIBUTE dx {CML, AML}
+@ATTRIBUTE tx {PB, BM}
+@ATTRIBUTE extent {L, E}
+@ATTRIBUTE agvhdgd NUMERIC
+@ATTRIBUTE age NUMERIC
+@ATTRIBUTE survtime NUMERIC
+@ATTRIBUTE reltime NUMERIC
+@ATTRIBUTE agvhtime NUMERIC
+@ATTRIBUTE cgvhtime NUMERIC
+@ATTRIBUTE stat {0, 1}
+@ATTRIBUTE rcens {0, 1}
+@ATTRIBUTE agvh {1, 0}
+@ATTRIBUTE cgvh {1, 0}
+@ATTRIBUTE stnum NUMERIC
+
+@DATA
+CML,PB,L,1,36,4.895,4.895,0.099,0.52,0,0,1,1,1
+AML,PB,L,3,57,3.474,0.753,0.101,0.408,1,1,1,1,2
+CML,PB,L,0,48,4.95,4.95,4.95,0.348,0,0,0,1,3
+AML,PB,L,2,52,4.643,4.643,0.057,0.482,0,0,1,1,4
+AML,PB,L,3,45,4.066,4.066,0.137,0.378,0,0,1,1,5
+AML,PB,L,3,47,1.558,0.416,0.055,1.558,1,1,1,0,6
+CML,PB,L,1,40,4.512,4.512,0.09,0.381,0,0,1,1,7
+AML,PB,L,3,38,4.041,4.041,0.082,0.914,0,0,1,1,8
+AML,PB,L,2,41,4.164,4.164,0.055,0.923,0,0,1,1,9
+CML,PB,L,0,50,4.011,4.011,4.011,0.397,0,0,0,1,10
+CML,PB,L,1,56,3.945,3.945,0.047,0.479,0,0,1,1,11
+CML,PB,L,2,56,4.361,4.361,0.079,0.991,0,0,1,1,12
+AML,PB,L,1,54,0.841,0.654,0.077,0.474,1,1,1,1,13
+CML,PB,L,3,25,2.951,2.951,0.164,0.339,0,0,1,1,14
+CML,PB,L,4,40,0.586,0.586,0.055,0.277,1,0,1,1,15
+CML,PB,L,0,41,3.559,3.559,3.559,0.367,0,0,0,1,16
+CML,PB,L,2,57,3.422,3.422,0.131,0.742,0,0,1,1,17
+CML,PB,L,3,62,0.408,0.408,0.408,0.408,0,0,1,1,18
+CML,PB,L,1,29,3.428,3.428,0.09,0.958,0,0,1,1,19
+AML,PB,L,1,44,0.063,0.063,0.014,0.063,1,0,1,0,20
+CML,PB,L,2,40,1.572,1.572,0.09,0.282,1,0,1,1,21
+CML,PB,L,1,54,1.013,1.013,0.093,0.413,1,0,1,1,22
+AML,PB,L,2,37,3.023,3.023,0.074,0.394,0,0,1,1,23
+AML,PB,L,1,58,2.979,2.979,0.079,0.342,0,0,1,1,24
+CML,PB,L,3,39,2.817,2.817,0.049,0.367,0,0,1,1,25
+CML,PB,L,2,31,2.804,2.804,0.137,0.277,0,0,1,1,26
+CML,PB,L,2,45,2.609,2.609,0.252,0.367,0,0,1,1,27
+AML,PB,L,0,48,2.508,2.508,2.508,0.331,0,0,0,1,28
+CML,PB,L,0,53,0.665,0.665,0.665,0.32,1,0,0,1,29
+CML,PB,L,0,29,2.497,2.497,2.497,0.329,0,0,0,1,30
+CML,PB,L,0,27,1.799,1.799,1.799,0.444,1,0,0,1,31
+AML,PB,L,3,45,0.471,0.438,0.071,0.471,1,1,1,0,32
+CML,PB,L,1,39,2.031,2.031,0.112,0.964,0,0,1,1,33
+CML,PB,L,3,49,2.073,2.073,0.063,0.564,0,0,1,1,34
+AML,PB,L,1,37,0.999,0.75,0.274,0.402,1,1,1,1,35
+AML,PB,L,3,53,0.427,0.427,0.055,0.277,1,0,1,1,36
+CML,PB,L,1,48,1.766,1.766,0.216,0.4,0,0,1,1,37
+AML,PB,L,1,59,1.555,1.555,0.178,0.446,0,0,1,1,38
+CML,PB,L,2,33,1.67,1.67,0.11,0.474,0,0,1,1,39
+CML,PB,L,0,38,1.607,1.607,1.607,0.329,0,0,0,1,40
+CML,PB,L,4,37,1.511,1.511,0.055,0.323,0,0,1,1,41
+AML,PB,L,3,41,1.287,1.287,0.049,0.392,0,0,1,1,42
+AML,PB,E,1,64,1.227,1.227,0.23,0.496,0,0,1,1,43
+CML,PB,L,3,32,1.3,1.3,0.063,0.63,0,0,1,1,44
+CML,PB,L,0,41,1.27,1.27,1.27,0.383,0,0,0,1,45
+AML,PB,E,1,56,1.205,1.205,0.074,1.205,0,0,1,0,46
+CML,PB,L,1,50,1.147,1.147,0.131,0.361,0,0,1,1,47
+CML,PB,L,3,37,1.109,1.109,0.055,0.277,0,0,1,1,48
+CML,PB,L,0,27,0.994,0.994,0.994,0.287,0,0,0,1,49
+CML,BM,L,3,45,4.572,4.572,0.066,0.619,0,0,1,1,50
+AML,BM,L,3,45,4.616,4.616,0.101,0.452,0,0,1,1,51
+AML,BM,L,2,42,4.0,4.0,0.027,0.29,0,0,1,1,52
+CML,BM,L,0,22,4.238,4.238,4.238,0.479,0,0,0,1,53
+AML,BM,L,4,47,0.11,0.11,0.074,0.11,1,0,1,0,54
+AML,BM,L,2,48,4.03,4.03,0.101,0.857,0,0,1,1,55
+AML,BM,L,2,49,3.124,2.527,0.115,1.993,1,1,1,1,56
+CML,BM,L,2,38,0.515,0.515,0.079,0.463,1,0,1,1,57
+CML,BM,L,1,39,4.222,3.149,0.085,0.496,0,1,1,1,58
+CML,BM,L,3,41,4.027,4.027,0.104,0.422,0,0,1,1,59
+CML,BM,L,2,46,1.969,1.969,0.038,0.307,1,0,1,1,60
+AML,BM,L,0,24,3.792,3.792,3.792,0.701,0,0,0,1,61
+AML,BM,L,3,32,0.427,0.427,0.041,0.279,1,0,1,1,62
+CML,BM,L,0,36,3.34,3.34,3.34,0.419,0,0,0,1,63
+CML,BM,L,1,53,3.504,0.72,0.112,0.616,0,1,1,1,64
+CML,BM,L,0,52,3.685,3.685,3.685,0.331,0,0,0,1,65
+CML,BM,L,1,59,0.181,0.181,0.049,0.181,1,0,1,0,66
+CML,BM,L,3,42,0.736,0.736,0.09,0.567,1,0,1,1,67
+CML,BM,L,1,65,0.287,0.287,0.052,0.287,1,0,1,0,68
+CML,BM,E,0,60,0.057,0.057,0.057,0.057,0,0,0,0,69
+CML,BM,L,2,61,3.107,3.107,0.088,0.764,0,0,1,1,70
+CML,BM,L,1,55,3.088,3.088,0.11,0.381,0,0,1,1,71
+AML,BM,E,0,48,0.446,0.274,0.446,0.446,1,1,0,0,72
+AML,BM,E,0,49,2.776,2.776,2.776,2.776,0,0,0,0,73
+CML,BM,L,0,36,0.693,0.172,0.693,0.635,1,1,0,1,74
+AML,BM,L,1,48,2.01,2.01,0.077,0.553,0,0,1,1,75
+CML,BM,L,0,47,2.374,2.374,2.374,0.287,0,0,0,1,76
+AML,BM,L,3,43,1.079,1.079,0.088,0.345,1,0,1,1,77
+CML,BM,L,0,56,2.604,2.604,2.604,0.375,0,0,0,1,78
+CML,BM,L,1,56,2.478,2.478,0.17,0.517,0,0,1,1,79
+CML,BM,L,0,36,2.338,2.338,2.338,0.457,0,0,0,1,80
+CML,BM,L,2,52,2.3,2.3,0.049,0.345,0,0,1,1,81
+CML,BM,E,1,44,0.219,0.219,0.145,0.219,1,0,1,0,82
+AML,BM,L,3,32,2.127,2.127,0.118,0.422,0,0,1,1,83
+AML,BM,L,1,44,2.034,2.034,0.096,0.479,0,0,1,1,84
+CML,BM,L,0,45,2.034,2.034,2.034,0.29,0,0,0,1,85
+AML,BM,L,3,48,2.007,2.007,0.088,0.35,0,0,1,1,86
+CML,BM,L,0,48,1.183,1.183,1.183,0.372,0,0,0,1,87
+AML,BM,L,3,42,0.375,0.375,0.096,0.277,1,0,1,1,88
+AML,BM,E,2,24,0.353,0.301,0.096,0.353,1,1,1,0,89
+CML,BM,L,2,26,1.566,1.566,0.137,0.474,0,0,1,1,90
+CML,BM,L,2,34,1.588,1.588,0.129,0.465,0,0,1,1,91
+CML,BM,L,0,57,1.243,1.243,1.243,0.433,0,0,0,1,92
+CML,BM,L,3,51,1.555,1.555,0.09,0.359,0,0,1,1,93
+AML,BM,L,2,54,1.202,1.202,0.192,1.202,0,0,1,0,94
+AML,BM,E,0,20,1.251,1.251,1.251,0.408,0,0,0,1,95
+AML,BM,L,2,39,1.114,1.114,0.074,0.402,0,0,1,1,96
+AML,BM,L,0,49,1.15,1.15,1.15,0.35,0,0,0,1,97
+CML,BM,L,1,42,0.997,0.997,0.142,0.411,0,0,1,1,98
+CML,BM,L,0,44,1.057,1.057,1.057,0.301,0,0,0,1,99
+CML,BM,L,1,56,1.125,1.125,0.129,0.32,0,0,1,1,100

sksurv/nonparametric.py

@@ -740,11 +740,11 @@ def cumulative_incidence_competing_risks(
         return uniq_times, cum_inc
 
     if var_type == "Dinse":
-        var = var_dinse(n_events_cr, kpe_prime, n_at_risk, cum_inc)
+        var = _var_dinse(n_events_cr, kpe_prime, n_at_risk, cum_inc)
     elif var_type == "Dinse_Approx":
-        var = var_dinse_approx(n_events_cr, kpe_prime, n_at_risk, cum_inc)
+        var = _var_dinse_approx(n_events_cr, kpe_prime, n_at_risk, cum_inc)
     elif var_type == "Aalen":
-        var = var_aalen(n_events_cr, kpe_prime, n_at_risk, cum_inc)
+        var = _var_aalen(n_events_cr, kpe_prime, n_at_risk, cum_inc)
     else:
         raise ValueError(f"{var_type=} not implemented.")
 
@@ -756,11 +756,11 @@ def cumulative_incidence_competing_risks(
     return uniq_times, cum_inc, ci
 
 
-def var_dinse_approx(n_events_cr, kpe_prime, n_at_risk, cum_inc):
+def _var_dinse_approx(n_events_cr, kpe_prime, n_at_risk, cum_inc):
     """
     Variance estimator from Dinse and Larson, Biometrika (1986), 379
     See Section 4, Eqs. 6.
-    This is an approximation from the var_dinse, so that one should be preferred.
+    This is an approximation from the _var_dinse, so that one should be preferred.
     However, this seems to be more common in the literature.
     """
     dr = n_events_cr[:, 0]
@@ -776,7 +776,7 @@ def var_dinse_approx(n_events_cr, kpe_prime, n_at_risk, cum_inc):
     return var
 
 
-def var_dinse(n_events_cr, kpe_prime, n_at_risk):
+def _var_dinse(n_events_cr, kpe_prime, n_at_risk):
     """
     Variance estimator from Dinse and Larson, Biometrika (1986), 379
     See Section 4, Eqs. 4 and 5
@@ -804,7 +804,7 @@ def var_dinse(n_events_cr, kpe_prime, n_at_risk):
     return var
 
 
-def var_aalen(n_events_cr, kpe_prime, n_at_risk, cum_inc):
+def _var_aalen(n_events_cr, kpe_prime, n_at_risk, cum_inc):
     """
     Variance estimator from Aalen
     Aalen, O. (1978a). Nonparametric estimation of partial transition