dataset.py

import pandas as pd
import numpy as np

# Exact dataset reconstructed from Autonomous_Choke_Control_Simulated_Dataset.csv
DATASET_RAW = """Time_hr,Choke_pct,OilRate_bbl_hr,WHP_psi,FLP_psi,BHP_psi
0,30,90,250,180,3000
1,30,91.12,252.54,181.72,3017.37
2,30,91.45,254.71,183.67,3031.08
3,30,91.53,257.17,184.33,3040
4,30,92.17,257.61,184.26,3047.91
5,30,91.69,259.56,184.61,3052.64
6,30,93.28,260.89,185.4,3056.96
7,30,92.97,262.3,185.47,3066.33
8,30,92.68,263.26,185.8,3079.38
9,30,92.9,263.57,186.8,3082.16
10,30,93.27,263.21,186.58,3088.98
11,30,93.99,264.38,187,3093.76
12,30,92.81,264.79,187.19,3102.23
13,30,93.3,264.42,187.75,3105.7
14,30,92.88,265.76,188.58,3112.84
15,30,92.41,266.29,188.94,3119.53
16,30,92.32,266.85,188.54,3119.18
17,30,93.27,268.42,188.71,3125.46
18,30,93.69,268.39,189.07,3132.84
19,30,93.72,269.92,187.89,3137.48
20,40,93.84,269.96,188.23,3133.31
21,40,96.93,268.54,187.82,3127.49
22,40,99,266.68,187.18,3124.68
23,40,100.91,265.76,186.22,3124.01
24,40,102.35,264.36,185.16,3116.1
25,40,104.32,263.54,184.44,3112.51
26,40,104.57,262.34,183.64,3107.5
27,40,105.78,261.86,184.08,3105.83
28,40,107.11,261.11,182.55,3103.68
29,40,108.03,262.22,182.09,3102.69
30,40,108.72,260.65,182.37,3103.13
31,40,109.94,259.46,182.74,3097.07
32,40,110.78,260.58,181.86,3094.01
33,40,111.08,259.67,180.83,3093.09
34,40,110.4,259.57,180.25,3096.7
35,40,110.06,258.91,180.62,3091.67
36,40,110.59,259.48,179.73,3091.29
37,40,111.05,259.61,179.15,3086.42
38,40,111.64,259.38,179.4,3086.95
39,40,111.16,259.14,179.63,3084.25
40,55,112.8,259.09,179.08,3085.88
41,55,116.74,256.39,177.69,3073.35
42,55,121.52,253.76,176.32,3069.97
43,55,124.47,250.62,174.29,3058.73
44,55,127.02,248.62,173.13,3053.31
45,55,129.19,247.64,171.86,3054
46,55,131.46,245.17,170.37,3047.93
47,55,132.63,244.09,169.85,3040.68
48,55,133.1,241.58,168.95,3036.79
49,55,134.34,239.56,168.48,3031.81
50,55,134.47,238.76,168.02,3022.63
51,55,135.57,238.34,168.14,3020.78
52,55,135.09,236.92,167.96,3017.46
53,55,136.2,239.03,167.83,3016.27
54,55,137.47,238.64,167.28,3014.05
55,55,137.13,237.68,166.72,3009.97
56,55,139.32,235.69,166.82,3001.13
57,55,138.88,236.01,166.6,2994.61
58,55,138.33,236,166.01,2992.49
59,55,138.49,235.07,166.94,2991.79
60,55,136.96,234.83,166.34,2991.81
61,55,136.69,234.41,166.4,2991.86
62,55,136.15,233.89,165.97,2987.35
63,55,138.07,233.94,165.2,2987.92
64,55,139.94,234.43,164.41,2984.23
65,55,140.78,233.65,164.72,2984.62
66,55,139.72,233.41,163.14,2979.57
67,55,139.39,232.36,164.21,2973.72
68,55,138.97,232.41,165.04,2968.31
69,55,139.9,232.37,164.55,2969.03
70,45,139.9,231.91,164.65,2967.15
71,45,136.59,234.3,166.89,2969.27
72,45,135.49,234.58,167.95,2976.69
73,45,133.11,235.75,168.83,2980.28
74,45,130.46,237.82,169.87,2982.98
75,45,129.47,239.25,171,2989.43
76,45,127.28,239.91,171.93,2995.3
77,45,126.14,240.96,173,2997.11
78,45,125.65,241.67,173.17,3003.83
79,45,125.47,243,174.08,3006.79
80,45,125.21,243.38,174.37,3009.06
81,45,124.53,244.35,174.05,3017.81
82,45,123.09,243.94,174.76,3021.96
83,45,123.21,244.87,174.79,3020.71
84,45,122.88,244.77,175.31,3021.81
85,45,121.88,244.93,175.47,3021.58
86,45,121.06,245.47,175.53,3021.53
87,45,120.67,245.94,174.73,3018.78
88,45,120.16,246.03,174.92,3024.91
89,45,121,246.16,174.92,3023.11
90,65,120.98,246.18,175.1,3021.98
91,65,127.88,243.63,172.23,3011.82
92,65,133.67,240.03,169.93,3001.32
93,65,137.95,236.61,167.85,2993.1
94,65,142.54,234.81,167.13,2981.75
95,65,145.84,232.68,166.52,2971.19
96,65,147.18,230.26,163.85,2962.32
97,65,148.34,228.65,162.78,2961.36
98,65,150.66,226.73,161.24,2956.33
99,65,150.74,226.72,160.96,2948.81
100,65,150.5,226.38,160.07,2947.02
101,65,150.39,224.72,159.36,2941.8
102,65,151.22,224.11,158.22,2936.43
103,65,152.36,223.5,158.12,2928.54
104,65,151.97,223.49,157.85,2922.41
105,65,154.11,222.67,158.04,2919.22
106,65,156.28,223.1,157.49,2919
107,65,156.93,223.21,156.66,2917.94
108,65,157.79,221.11,155.84,2908.78
109,65,157.43,221,156.47,2906.7
110,65,158.66,219.43,155.41,2904.4
111,65,158.66,219,154.32,2902.18
112,65,157.32,219.11,154.6,2897.59
113,65,156.85,217.99,154.62,2899.05
114,65,156.09,218.11,154.41,2895.14
115,65,156.17,217.13,154.22,2890.34
116,65,157.89,217.02,153.98,2890.15
117,65,157.64,216.74,154.43,2891.61
118,65,157.1,216.25,154.37,2883.78
119,65,155.87,217.18,155.28,2882.73
"""

def load_dataset():
    from io import StringIO
    df = pd.read_csv(StringIO(DATASET_RAW))
    return df

if __name__ == "__main__":
    df = load_dataset()
    print("Dataset loaded successfully!")
    print(df.head())
    print(f"Total rows: {len(df)}")