大数据毕业设计PySpark+Hadoop机票价格行情分析 飞机票航班数据分析可视化大屏 机票预测 航班预测 机票爬虫 飞机票推荐系统 机器学习 深度学习 人工智能 知识图谱 计算机毕业设计

核心算法代码分享如下：

import sys
from db import cnn
import pandas as pd
from sklearn.preprocessing import PolynomialFeatures
from sklearn.linear_model import LinearRegression

def predict1():
    sql = "select `stime`, `num` as value from tables04" \
          "  order by stime asc "
    with cnn.cursor() as cursor:
        cursor.execute(sql)
    print(sql)
    names = []
    y = []
    for line in cursor.fetchall():
        # print(line)
        y.append(line[1])
        names.append(line[0])
    y = y[::-1]
    X = [1, 2, 3, 4, 5]
    X = pd.DataFrame(X)
    X = X.values
    Poly_regressor = PolynomialFeatures(degree=2)
    Poly_X = Poly_regressor.fit_transform(X)
    regressor = LinearRegression()
    regressor.fit(Poly_X, y)
    p1 = regressor.predict(Poly_regressor.fit_transform([[8]]))
    p2 = regressor.predict(Poly_regressor.fit_transform([[9]]))
    p3 = regressor.predict(Poly_regressor.fit_transform([[10]]))
    r = []
    r.append(round(float(p1[0]),2))
    r.append(round(float(p2[0]),2))
    r.append(round(float(p3[0]),2))
    return r

def predict2():
    sql = "select `stime`, `num` as value from tables04" \
          "  order by stime asc "
    with cnn.cursor() as cursor:
        cursor.execute(sql)
    print(sql)
    names = []
    y = []
    for line in cursor.fetchall():
        # print(line)
        y.append(line[1])
        names.append(line[0])
    y = y[::-1]
    X = [1, 2, 3, 4, 5]
    X = pd.DataFrame(X)
    X = X.values
    Poly_regressor = PolynomialFeatures(degree=2)
    Poly_X = Poly_regressor.fit_transform(X)
    regressor = LinearRegression()
    regressor.fit(Poly_X, y)
    p1 = regressor.predict(Poly_regressor.fit_transform([[8]]))
    p2 = regressor.predict(Poly_regressor.fit_transform([[9]]))
    p3 = regressor.predict(Poly_regressor.fit_transform([[10]]))
    r = []
    r.append(round(float(p1[0]),2))
    r.append(round(float(p2[0]),2))
    r.append(round(float(p3[0]),2))
    return r

def predict3():
    sql = "select `stime`, `num` as value from tables04" \
          "  order by stime asc "
    with cnn.cursor() as cursor:
        cursor.execute(sql)
    print(sql)
    names = []
    y = []
    for line in cursor.fetchall():
        # print(line)
        y.append(line[1])
        names.append(line[0])
    y = y[::-1]
    X = [1, 2, 3, 4, 5]
    X = pd.DataFrame(X)
    X = X.values
    Poly_regressor = PolynomialFeatures(degree=2)
    Poly_X = Poly_regressor.fit_transform(X)
    regressor = LinearRegression()
    regressor.fit(Poly_X, y)
    p1 = regressor.predict(Poly_regressor.fit_transform([[8]]))
    p2 = regressor.predict(Poly_regressor.fit_transform([[9]]))
    p3 = regressor.predict(Poly_regressor.fit_transform([[10]]))
    r = []
    r.append(round(float(p1[0]),2))
    r.append(round(float(p2[0]),2))
    r.append(round(float(p3[0]),2))
    return r

def predict4():
    sql = "select `stime`, `num` as value from tables04" \
          "  order by stime asc "
    with cnn.cursor() as cursor:
        cursor.execute(sql)
    print(sql)
    names = []
    y = []
    for line in cursor.fetchall():
        # print(line)
        y.append(line[1])
        names.append(line[0])
    y = y[::-1]
    X = [1, 2, 3, 4, 5]
    X = pd.DataFrame(X)
    X = X.values
    Poly_regressor = PolynomialFeatures(degree=2)
    Poly_X = Poly_regressor.fit_transform(X)
    regressor = LinearRegression()
    regressor.fit(Poly_X, y)
    p1 = regressor.predict(Poly_regressor.fit_transform([[8]]))
    p2 = regressor.predict(Poly_regressor.fit_transform([[9]]))
    p3 = regressor.predict(Poly_regressor.fit_transform([[10]]))
    r = []
    r.append(round(float(p1[0]),2))
    r.append(round(float(p2[0]),2))
    r.append(round(float(p3[0]),2))
    return r

if __name__ == '__main__':
    #name = sys.argv[1]
    ret = []
    r1 = predict1()
    r2 = predict2()
    r3 = predict3()
    r4 = predict4()
    ret.append(r1)
    ret.append(r2)
    ret.append(r3)
    ret.append(r4)
    print(ret)
    print(r1)
    print(int(r1[0]))
    print(int(r1[1]))
    print(int(r1[2]))
    sql_day01="replace into tables04(stime,num) values (%s,%s)"
    data_day01 =('预测1',int(r1[0]))
    sql_day02="replace into tables04(stime,num) values (%s,%s)"
    data_day02 = ('预测2', int(r1[1]))
    sql_day03="replace into tables04(stime,num) values (%s,%s)"
    data_day03 = ('预测3', int(r1[2]))
    cur=cnn.cursor()
    cur.execute(sql_day01,data_day01)
    cur.execute(sql_day02,data_day02)
    cur.execute(sql_day03,data_day03)
    cnn.commit()
    cur.close()

能够准确预测飞机票价格、生成可视化页面，满足用户的需求。具体的预期成果包括

1.高性能的数据处理：利用Hadoop+Hive的分布式计算框架和数据存储技术，预期成果应具有高性能的数据处理能力，能够处理和分析大规模的机票价格数据，提供快速高效的预测和可视化结果。

2.准确的预测结果：通过使用Hadoop+Hive的大数据处理和分析能力，预期成果将提供准确的机票价格预测结果。这将帮助用户在选择出行时间和购买机票时更加明智和高效，从而节省旅行成本。

3.可视化展示：利用可视化技术将机票价格的预测结果以直观的图表、地图等形式展示给用户，使用户更好地理解机票价格的变化趋势和规律，帮助他们选择合适的出行时间和机票购买策略。