# https://www.cnblogs.com/vachester/p/7202793.html import matplotlib.pyplot as plt import numpy as np import pandas as pd from sklearn import datasets, linear_model def get_data(file_name): # data = pd.read_csv(file_name, header = None) # data = pd.read_excel(file_name) # X_parameter = [] # Y_parameter = [] # for single_square_feet, single_price_value in zip(data['square_feet'], data['price']): # X_parameter.append([float(single_square_feet)]) # Y_parameter.append(float(single_price_value)) row = list(range(340, 340 + 300)) wave = [399.959, 401.958, 403.958, 405.957, 407.957, 409.957, 411.956, 413.956, 415.955, 417.955, 419.954, 421.954, 423.954, 425.953, 427.953, 429.952, 431.952, 433.951, 435.951, 437.951, 439.95, 441.95, 443.949, 445.949, 447.948, 449.948, 451.947, 453.947, 455.947, 457.946, 459.946, 461.945, 463.945, 465.944, 467.944, 469.944, 471.943, 473.943, 475.942, 477.942, 479.941, 481.941, 483.94, 485.94, 487.94, 489.939, 491.939, 493.938, 495.938, 497.937, 499.937, 501.937, 503.936, 505.936, 507.935, 509.935, 511.934, 513.934, 515.933, 517.933, 519.933, 521.932, 523.932, 525.931, 527.931, 529.93, 531.93, 533.93, 535.929, 537.929, 539.928, 541.928, 543.927, 545.927, 547.927, 549.926, 551.926, 553.925, 555.925, 557.924, 559.924, 561.923, 563.923, 565.923, 567.922, 569.922, 571.921, 573.921, 575.92, 577.92, 579.92, 581.919, 583.919, 585.918, 587.918, 589.917, 591.917, 593.917, 595.916, 597.916, 599.915, 601.915, 603.914, 605.914, 607.913, 609.913, 611.913, 613.912, 615.912, 617.911, 619.911, 621.91, 623.91, 625.909, 627.909, 629.909, 631.908, 633.908, 635.907, 637.907, 639.906, 641.906, 643.906, 645.905, 647.905, 649.904, 651.904, 653.903, 655.903, 657.903, 659.902, 661.902, 663.901, 665.901, 667.9, 669.9, 671.899, 673.899, 675.899, 677.898, 679.898, 681.897, 683.897, 685.896, 687.896, 689.896, 691.895, 693.895, 695.894, 697.894, 699.893, 701.893, 703.893, 705.892, 707.892, 709.891, 711.891, 713.89, 715.89, 717.889, 719.889, 721.889, 723.888, 725.888, 727.887, 729.887, 731.886, 733.886, 735.886, 737.885, 739.885, 741.884, 743.884, 745.883, 747.883, 749.883, 751.882, 753.882, 755.881, 757.881, 759.88, 761.88, 763.879, 765.879, 767.879, 769.878, 771.878, 773.877, 775.877, 777.876, 779.876, 781.876, 783.875, 785.875, 787.874, 789.874, 791.873, 793.873, 795.872, 797.872, 799.872, 801.871, 803.871, 805.87, 807.87, 809.869, 811.869, 813.869, 815.868, 817.868, 819.867, 821.867, 823.866, 825.866, 827.866, 829.865, 831.865, 833.864, 835.864, 837.863, 839.863, 841.862, 843.862, 845.862, 847.861, 849.861, 851.86, 853.86, 855.859, 857.859, 859.858, 861.858, 863.858, 865.857, 867.857, 869.856, 871.856, 873.855, 875.855, 877.855, 879.854, 881.854, 883.853, 885.853, 887.852, 889.852, 891.852, 893.851, 895.851, 897.85, 899.85, 901.849, 903.849, 905.848, 907.848, 909.848, 911.847, 913.847, 915.846, 917.846, 919.845, 921.845, 923.845, 925.844, 927.844, 929.843, 931.843, 933.842, 935.842, 937.841, 939.841, 941.841, 943.84, 945.84, 947.839, 949.839, 951.838, 953.838, 955.838, 957.837, 959.837, 961.836, 963.836, 965.835, 967.835, 969.835, 971.834, 973.834, 975.833, 977.833, 979.832, 981.832, 983.831, 985.831, 987.831, 989.83, 991.83, 993.829, 995.829, 997.828] row_bin2 = list(range(170, 170 + 150)) wave_bin2 = [] for i in range(0, len(wave), 2): # print(i) # print(wave[i:i + 2]) wave_bin2.append((wave[i] + wave[i+1])/2) X_parameter = [] Y_parameter = [] for single_square_feet, single_price_value in zip(row_bin2, wave_bin2): X_parameter.append([float(single_square_feet)]) Y_parameter.append(float(single_price_value)) return X_parameter, Y_parameter def plot(x, y, regre): plt.scatter(x, y, color='blue') plt.plot(x, regre.predict(x), color='red', linewidth=4) # plt.xticks(()) # plt.yticks(()) plt.show() def linearRegression(X_parameters, Y_parameters):# regr = linear_model.LinearRegression() regr.fit(X_parameters, Y_parameters) # 绘图 plot(X_parameters, Y_parameters, regr) return regr if __name__ == "__main__": x, y = get_data(r'D:\PycharmProjects\linear_regression\123.xlsx') regr = linearRegression(x, y) yPredicted = [] for i in x: xxxx = regr.predict(i[0]) yPredicted.append(xxxx[0]) print("Intercept value ", regr.intercept_) print("coefficient", regr.coef_)