# Linear Regression
import matplotlib.pyplot as plt
from scipy import stats
x = [0,1,2,3,4]
y = [3,5,5,6,7]
slope, intercept, r, p, std_err = stats.linregress(x, y)
print("slope: ", slope)
print("intercept: ", intercept)
def myfunc(x):
return slope * x + intercept
Defines a linear function called myfunc()
mymodel = list(map(myfunc, x))
plt.scatter(x, y)
plt.plot(x, mymodel)
plt.show()
#Linear Regression using Statsmodels Library
import matplotlib.pyplot as plt
import numpy as np
import statsmodels.api as sm
x = [0,1,2,3,4]
y = [3,5,5,6,7]
Creates two arrays for x and y values
x1 = sm.add_constant(x)
model = sm.OLS(y,x1)
results = model.fit()
print (results.params)
print (results.summary())
y_pred = results.predict(x1)
plt.scatter(x,y)
plt.xlabel("X")
plt.ylabel("Y")
plt.plot(x,y_pred, "r")
plt.show()
# Polynomial Regression
import matplotlib.pyplot as plt
from scipy import stats
import numpy as np
x = [0,1,2,3,4,5]
y = [3,8,6,6,7,3]
mymodel = np.poly1d(np.polyfit(x, y, 3))
print(mymodel)
myline = np.linspace(0, 5, 100)
plt.scatter(x, y)
plt.plot(myline, mymodel(myline))
plt.show()
#Python Least Squares Fitting
import numpy as np
import scipy.optimize as optimization
x = np.array([0,1,2,3,4,5])
y = np.array([100,90,60,30,10,1])
def func(x, a, b, c):
return a * np.exp(-b* x) + c
popt, pcov = optimization.curve_fit(func, x, y)
print ("Best fit a b c: ",popt)
print ("Best fit covariance: ",pcov)
# Contoh pake CalCofl
import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn import preprocessing, svm
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
Step 2: Reading the dataset
df = pd.read_csv('bottle.csv')
df_binary = df[['Salnty', 'T_degC']]
# Taking only the selected two attributes from the dataset
df_binary.columns = ['Sal', 'Temp']
#display the first 5 rows
df_binary.head()
Step 3: Exploring the data scatter
#plotting the Scatter plot to check relationship between Sal and Temp
sns.lmplot(x ="Sal", y ="Temp", data = df_binary, order = 2, ci = None)
plt.show()
Step 4: Data cleaning
# Eliminating NaN or missing input numbers
df_binary.fillna(method ='ffill', inplace = True)
Step 5: Training our model
X = np.array(df_binary['Sal']).reshape(-1, 1)
y = np.array(df_binary['Temp']).reshape(-1, 1)
# Separating the data into independent and dependent variables
# Converting each dataframe into a numpy array
# since each dataframe contains only one column
df_binary.dropna(inplace = True)
# Dropping any rows with Nan values
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25)
# Splitting the data into training and testing data
regr = LinearRegression()
regr.fit(X_train, y_train)
print(regr.score(X_test, y_test))
Step 6: Exploring our results
y_pred = regr.predict(X_test)
plt.scatter(X_test, y_test, color ='b')
plt.plot(X_test, y_pred, color ='k')
plt.show()
# Data scatter of predicted values
Working with a smaller dataset
Artificial Intelligence
59
df_binary500.fillna(method ='ffill', inplace = True)
X = np.array(df_binary500['Sal']).reshape(-1, 1)
y = np.array(df_binary500['Temp']).reshape(-1, 1)
df_binary500.dropna(inplace = True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25)
regr = LinearRegression()
regr.fit(X_train, y_train)
print(regr.score(X_test, y_test))
Working with a smaller dataset
y_pred = regr.predict(X_test)
plt.scatter(X_test, y_test, color ='b')
plt.plot(X_test, y_pred, color ='k')
plt.show()
