# Python code to demonstrate SQL to fetch data.
# importing the module
import sqlite3
import numpy as np
import pandas as pd
from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt
from scipy.stats import chisquare
# connect withe the myTable database
connection = sqlite3.connect(r"C:\Users\Aidan\Desktop\CEP_DB.db")
# cursor object
crsr = connection.cursor()
dog= crsr.execute("Select s, ei, ki FROM cep_db_lite1_vc WHERE s IN ('d')")
ans= crsr.fetchall()
dogData = np.array(ans)
FdogData= dogData[:, [1,2]]
x, y = FdogData[:,0], FdogData[:,1]
# Reshaping
x, y = x.reshape(-1,1), y.reshape(-1, 1)
# Linear Regression Object
lin_regression = LinearRegression()
# Fitting linear model to the data
lin_regression.fit(x,y)
# Get slope of fitted line
m = lin_regression.coef_
# Get y-Intercept of the Line
b = lin_regression.intercept_
# Get Predictions for original x values
# you can also get predictions for new data
predictions = lin_regression.predict(x)
chi= chisquare(predictions, y)
# following slope intercept form
print ("formula: y = {0}x + {1}".format(m, b))
print(chi)
# Plot the Original Model (Black) and Predictions (Blue)
plt.scatter(x, y, color='black')
plt.plot(x, predictions, color='blue',linewidth=3)
plt.show()
存储在数组中的数据:
[['d' '-72.70' '3.20']
['d' '-74.81' '']
['d' '-87.60' '5.50']
['d' '-91.38' '']
['d' '-71.80' '']
['d' '-73.10' '']
['d' '-81.20' '']
['d' '-81.40' '']
['d' '-75.70' '5.70']
['d' '-83.50' '5.10']
['d' '-73.90' '']
['d' '-82.60' '']
['d' '-77.30' '']
['d' '-85.10' '']
['d' '-79.70' '']
['d' '-78.70' '']
['d' '-77.90' '']
['d' '-76.80' '']
['d' '-83.80' '']
['d' '-83.90' '']
['d' '-82.00' '4.90']
['d' '-80.00' '4.80']]
错误输出/回溯
runfile('C:/Users/Aidan/.spyder-py3/temp.py', wdir ='C:/Users/Aidan/.spyder-py3')追溯(最近一次通话结束):
文件“”,第1行,在 运行文件('C:/Users/Aidan/.spyder-py3/temp.py',wdir ='C:/Users/Aidan/.spyder-py3')
文件 “ C:\ Users \ Aidan \ Anaconda3 \ lib \ site-packages \ spyder \ utils \ site \ sitecustomize.py”, 运行文件中的第705行 execfile(文件名,命名空间)
文件 “ C:\ Users \ Aidan \ Anaconda3 \ lib \ site-packages \ spyder \ utils \ site \ sitecustomize.py”, 第102行,在execfile中 exec(compile(f.read(),文件名,'exec'),命名空间)
文件“ C:/Users/Aidan/.spyder-py3/temp.py”,第32行,在 lin_regression.fit(x,y)
文件 “ C:\ Users \ Aidan \ Anaconda3 \ lib \ site-packages \ sklearn \ linear_model \ base.py”, 489号线,适合 copy = self.copy_X,sample_weight = sample_weight)
文件 “ C:\ Users \ Aidan \ Anaconda3 \ lib \ site-packages \ sklearn \ linear_model \ base.py”, _preprocess_data中的第169行 y = np.asarray(y,dtype = X.dtype)
文件 “ C:\ Users \ Aidan \ Anaconda3 \ lib \ site-packages \ numpy \ core \ numeric.py”, 492行,呈数组形式 返回数组(a,dtype,copy = False,order = order)
ValueError:无法将字符串转换为浮点数:
如何解决浮动错误?
答案 0 :(得分:0)
问题是''
无法转换为浮点数。您需要先清除数据,然后再应用lin_regression.fit(x,y)
。