Add geyser dataset

geyser.csv

@@ -0,0 +1,273 @@
+duration,waiting,kind
+3.6,79,long
+1.8,54,short
+3.333,74,long
+2.283,62,short
+4.533,85,long
+2.883,55,short
+4.7,88,long
+3.6,85,long
+1.95,51,short
+4.35,85,long
+1.8330000000000002,54,short
+3.917,84,long
+4.2,78,long
+1.75,47,short
+4.7,83,long
+2.167,52,short
+1.75,62,short
+4.8,84,long
+1.6,52,short
+4.25,79,long
+1.8,51,short
+1.75,47,short
+3.45,78,long
+3.0669999999999997,69,long
+4.533,74,long
+3.6,83,long
+1.9669999999999999,55,short
+4.083,76,long
+3.85,78,long
+4.433,79,long
+4.3,73,long
+4.467,77,long
+3.367,66,short
+4.033,80,long
+3.833,74,long
+2.017,52,short
+1.867,48,short
+4.833,80,long
+1.8330000000000002,59,short
+4.783,90,long
+4.35,80,long
+1.883,58,short
+4.567,84,long
+1.75,58,short
+4.533,73,long
+3.3169999999999997,83,long
+3.833,64,short
+2.1,53,short
+4.633,82,long
+2.0,59,short
+4.8,75,long
+4.716,90,long
+1.8330000000000002,54,short
+4.833,80,long
+1.733,54,short
+4.883,83,long
+3.717,71,long
+1.6669999999999998,64,short
+4.567,77,long
+4.317,81,long
+2.233,59,short
+4.5,84,long
+1.75,48,short
+4.8,82,long
+1.817,60,short
+4.4,92,long
+4.167,78,long
+4.7,78,long
+2.0669999999999997,65,short
+4.7,73,long
+4.033,82,long
+1.9669999999999999,56,short
+4.5,79,long
+4.0,71,long
+1.983,62,short
+5.067,76,long
+2.017,60,short
+4.567,78,long
+3.883,76,long
+3.6,83,long
+4.133,75,long
+4.333,82,long
+4.1,70,long
+2.633,65,short
+4.067,73,long
+4.933,88,long
+3.95,76,long
+4.5169999999999995,80,long
+2.167,48,short
+4.0,86,long
+2.2,60,short
+4.333,90,long
+1.867,50,short
+4.817,78,long
+1.8330000000000002,63,short
+4.3,72,long
+4.667,84,long
+3.75,75,long
+1.867,51,short
+4.9,82,long
+2.483,62,short
+4.367,88,long
+2.1,49,short
+4.5,83,long
+4.05,81,long
+1.867,47,short
+4.7,84,long
+1.7830000000000001,52,short
+4.85,86,long
+3.6830000000000003,81,long
+4.7330000000000005,75,long
+2.3,59,short
+4.9,89,long
+4.417,79,long
+1.7,59,short
+4.633,81,long
+2.3169999999999997,50,short
+4.6,85,long
+1.817,59,short
+4.417,87,long
+2.617,53,short
+4.067,69,long
+4.25,77,long
+1.9669999999999999,56,short
+4.6,88,long
+3.767,81,long
+1.9169999999999998,45,short
+4.5,82,long
+2.267,55,short
+4.65,90,long
+1.867,45,short
+4.167,83,long
+2.8,56,short
+4.333,89,long
+1.8330000000000002,46,short
+4.383,82,long
+1.883,51,short
+4.933,86,long
+2.033,53,short
+3.733,79,long
+4.2330000000000005,81,long
+2.233,60,short
+4.533,82,long
+4.817,77,long
+4.333,76,long
+1.983,59,short
+4.633,80,long
+2.017,49,short
+5.1,96,long
+1.8,53,short
+5.033,77,long
+4.0,77,long
+2.4,65,short
+4.6,81,long
+3.5669999999999997,71,long
+4.0,70,long
+4.5,81,long
+4.083,93,long
+1.8,53,short
+3.967,89,long
+2.2,45,short
+4.15,86,long
+2.0,58,short
+3.833,78,long
+3.5,66,short
+4.583,76,long
+2.367,63,short
+5.0,88,long
+1.933,52,short
+4.617,93,long
+1.9169999999999998,49,short
+2.083,57,short
+4.583,77,long
+3.333,68,long
+4.167,81,long
+4.333,81,long
+4.5,73,long
+2.417,50,short
+4.0,85,long
+4.167,74,long
+1.883,55,short
+4.583,77,long
+4.25,83,long
+3.767,83,long
+2.033,51,short
+4.433,78,long
+4.083,84,long
+1.8330000000000002,46,short
+4.417,83,long
+2.1830000000000003,55,short
+4.8,81,long
+1.8330000000000002,57,short
+4.8,76,long
+4.1,84,long
+3.966,77,long
+4.2330000000000005,81,long
+3.5,87,long
+4.3660000000000005,77,long
+2.25,51,short
+4.667,78,long
+2.1,60,short
+4.35,82,long
+4.133,91,long
+1.867,53,short
+4.6,78,long
+1.7830000000000001,46,short
+4.367,77,long
+3.85,84,long
+1.933,49,short
+4.5,83,long
+2.383,71,long
+4.7,80,long
+1.867,49,short
+3.833,75,long
+3.417,64,short
+4.2330000000000005,76,long
+2.4,53,short
+4.8,94,long
+2.0,55,short
+4.15,76,long
+1.867,50,short
+4.2669999999999995,82,long
+1.75,54,short
+4.4830000000000005,75,long
+4.0,78,long
+4.117,79,long
+4.083,78,long
+4.2669999999999995,78,long
+3.917,70,long
+4.55,79,long
+4.083,70,long
+2.417,54,short
+4.183,86,long
+2.217,50,short
+4.45,90,long
+1.883,54,short
+1.85,54,short
+4.283,77,long
+3.95,79,long
+2.333,64,short
+4.15,75,long
+2.35,47,short
+4.933,86,long
+2.9,63,short
+4.583,85,long
+3.833,82,long
+2.083,57,short
+4.367,82,long
+2.133,67,short
+4.35,74,long
+2.2,54,short
+4.45,83,long
+3.5669999999999997,73,long
+4.5,73,long
+4.15,88,long
+3.8169999999999997,80,long
+3.917,71,long
+4.45,83,long
+2.0,56,short
+4.283,79,long
+4.7669999999999995,78,long
+4.533,84,long
+1.85,58,short
+4.25,83,long
+1.983,43,short
+2.25,60,short
+4.75,75,long
+4.117,81,long
+2.15,46,short
+4.417,90,long
+1.817,46,short
+4.467,74,long

process/geyser.py

@@ -0,0 +1,15 @@
+import numpy as np
+import pandas as pd
+from scipy.cluster.vq import kmeans2
+
+if __name__ == "__main__":
+
+    np.random.seed(0)
+
+    df = pd.read_csv("raw/geyser.csv")
+    df.columns = ["duration", "waiting"]
+
+    _, z = kmeans2(df, 2)
+    df["kind"] = np.where(z, "long", "short")
+
+    df.to_csv("geyser.csv", index=False)