流程

1. 导入所要使用的包
2. 引入kaggle的数据集csv文件
3. 查看数据集有无空值
4. 填充这些空值
5. 提取特征
6. 分离训练集和测试集
7. 调用模型

数据资源获取

数据资源获取

导入需要的包

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

引入kaggle的数据集csv文件

数据集有五千万行，就我的笔记本而言，还是用前50万条数据训练个模型

train = pd.read_csv('train1.csv',nrows=50000)
test = pd.read_csv('test.csv')
test_ids = test['key']

train.head()

查看数据集有无空值

train.isnull().sum()#找出空值

空值处理

50万条出现了怎么几条数据，直接删除

# 删除包含空值的行
train = train.dropna(how='any', axis=0)

看一下test中的数据

test = pd.read_csv('test.csv')
test_ids = test['key']
test.head()
test.isnull().sum()
#没有空数据

特征操作

1. 车费的价格肯定要>0

train = train[train.fare_amount>=0]

2. 看一下坐标的范围

# 查看坐标范围
print(min(test.pickup_longitude.min(),test.dropoff_longitude.min()))
print(max(test.pickup_longitude.max(),test.dropoff_longitude.max()))
print(min(test.pickup_latitude.min(),test.dropoff_latitude.min()))
print(max(test.pickup_latitude.max(),test.dropoff_latitude.max()))
#-74.263242
#-72.986532
#40.568973
#41.709555

def select_train(df, fw):
    return (df.pickup_longitude >= fw[0]) & (df.pickup_longitude <= fw[1]) & \
           (df.pickup_latitude >= fw[2]) & (df.pickup_latitude <= fw[3]) & \
           (df.dropoff_longitude >= fw[0]) & (df.dropoff_longitude <= fw[1]) & \
           (df.dropoff_latitude >= fw[2]) & (df.dropoff_latitude <= fw[3])
fw = (-74.2, -73, 40.5, 41.8)
train = train[select_train(train, fw)]

3. 按照时间提取特征

# 根据时间提取新的特征
def deal_time_features(df):
    df['pickup_datetime'] = df['pickup_datetime'].str.slice(0, 16)
    df['pickup_datetime'] = pd.to_datetime(df['pickup_datetime'], utc=True, format='%Y-%m-%d %H:%M')
    df['hour'] = df.pickup_datetime.dt.hour
    df['month'] = df.pickup_datetime.dt.month
    df["year"] = df.pickup_datetime.dt.year
    df["weekday"] = df.pickup_datetime.dt.weekday
    return df
train = deal_time_features(train)
test = deal_time_features(test)

4. 根据坐标计算距离

# 根据坐标转换为距离
def distance(x1, y1, x2, y2):
    p = 0.017453292519943295 
    a = 0.5 - np.cos((x2 - x1) * p)/2 + np.cos(x1 * p) * np.cos(x2 * p) * (1 - np.cos((y2 - y1) * p)) / 2
    dis = 0.6213712 * 12742 * np.arcsin(np.sqrt(a))
    return dis  
train['distance_miles'] = distance(train.pickup_latitude,train.pickup_longitude,train.dropoff_latitude,train.dropoff_longitude)
test['distance_miles'] = distance(test.pickup_latitude, test.pickup_longitude,test.dropoff_latitude,test.dropoff_longitude)
train.head()

5. 去除票价和距离为0的数据

train = train.drop(index= train[(train['distance_miles']==0)&(train['fare_amount']==0)].index, axis=0)

6. 删除fare_amount小于2.5的数据，因为纽约出租车的起步价为2.5

train = train.drop(index= train[train['fare_amount'] < 2.5].index, axis=0)

7. 去除人数大于7的数据

train = train.drop(index= train[train.passenger_count >= 7].index, axis=0)

8. 删除没有用的数据

train = train.drop(columns= ['key','pickup_datetime'], axis= 1).copy()
test = test.drop(columns= ['key','pickup_datetime'], axis= 1).copy()

9. 看特征和标签的关联度

#看一下特征和价格的关联程度
train.corr()['fare_amount']

调用模型

from sklearn.linear_model import LinearRegression

from sklearn.model_selection import train_test_split 
x ,r = train[train.columns.delete(0)], train['fare_amount']

linear_model = LinearRegression()
linear_model.fit(x, r)
prediction = linear_model.predict(test)

res = pd.DataFrame()
res['key'] = test_ids
res['fare_amount'] = prediction
res.to_csv('submission.csv', index=False)
#结果保存