import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression
from sklearn import metrics
from sklearn.preprocessing import PolynomialFeatures
df = pd.read_csv("C:\\Users\\MONSTER\\Desktop\\dosyalar\\datasets\\Auto.csv")
x = df["horsepower"].to_numpy()
y = df["mpg"].to_numpy()
x = x.reshape(-1,1)
poly = PolynomialFeatures(degree = 5)
X_poly = poly.fit_transform(x)
poly.fit(X_poly,y)
lr = LinearRegression()
lr.fit(X_poly, y)
y_pred = lr.predict(X_poly)
plt.scatter(x,y,color="blue",marker=".")
plt.plot(x,y_pred,color="red")
I have tried to draw a polynomial regression curve but I couldn't manage it. Someone told me to sorting values before plotting via "numpy.argsort" but nothing has changed. How can I fix it?
probably scatter is better for you:
plt.scatter(x,y_pred,color="red")
Or with argsort as mentioned:
orders = np.argsort(x.ravel())
plt.plot(x[orders], y[orders], color='red')
Related
I used the ellipticenvelope method to find the anomalies in the iris dataset as below:
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.datasets import load_iris
iris = load_iris()
cols = iris.feature_names
X = pd.DataFrame(iris.data, columns=cols)
X.head()
from sklearn.preprocessing import StandardScaler
from sklearn.covariance import EllipticEnvelope
scaler = StandardScaler()
scaler.fit_transform(X)
cov = EllipticEnvelope(store_precision=True,
assume_centered=True,
support_fraction=None,
contamination=0.01,
random_state=0)
cov.fit(X)
X['Anomaly'] = cov.predict(X)
Now you can find the anomalies in the last column with the value -1.
X[X['Anomaly'] == -1]
Now I want to do a root cause analysis to find the source of the anomaly, so I want to plot the anomalies in the boxplot with red dots for example. Is it possible or not? if yes, how can I add it?
X.boxplot(column=cols, grid=False, rot=45)
# code to plot anomalies on boxplot
plt.show()
Hello I'm having troube trying to predict the Weekly Sales based on the fuel price using polynomial regression. I saw someone else ask the same question and tried the only answer but I still can't get a good graph. Here's what I've done:
from contextlib import redirect_stderr
from turtle import color, pd
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import PolynomialFeatures
df = pd.read_csv (r'Walmart.csv')
df = df.sort_values(by=['Weekly_Sales'])
y = df.loc[:, "Fuel_Price"].sample(n = 50, random_state= 6)
x = df.loc[:, "Weekly_Sales"].sample(n = 50, random_state= 6)
poly = PolynomialFeatures(degree=2)
X_poly = poly.fit_transform(x.values.reshape(-1,1))
poly.fit(X_poly,y)
linreg = LinearRegression()
linreg.fit(X_poly,y)
y_pred = linreg.predict(X_poly)
plt.scatter(x, y, color='red')
plt.plot(x,y_pred, color = 'blue')
plt.show()
Result:
Graph
Your main problem is that x are not in order after randomly sampling them from df. Replace the x and y sampling lines lines with
...
xy = df.sample(n = 50, random_state= 6).sort_values(by=['Weekly_Sales'])
y = df["Fuel_Price"]
x = df["Weekly_Sales"]
...
and it should work. Eg for some made up data:
Alternatively you can plot the blue line as a scatter and it would not matter if the xs are not in order
...
plt.plot(x,y_pred ,'.', color = 'blue')
...
and it would look like this:
I'm running a linear regression simulation, each model according to a different value of the "label" variable. I can print metrics for each model, but I'm not able to run a different scatterplot por each model. All the graphs are reproduced in a single scatterplot. I would like to run a metric and a different scatterplot for each model
import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.metrics import r2_score
from scipy.stats import binom
from scipy.stats import norm
import numpy as np
from scipy.stats import norm
# generate random numbers from N(0,1)
x = norm.rvs(size=10000,loc=0,scale=1)
y = norm.rvs(size=10000,loc=0,scale=1)
z = binom.rvs(n=10,p=0.8,size=10000)
df = pd.DataFrame(data={'v1':x.flatten(),'target':y.flatten(),'label':z.flatten()})
classes=df.label.unique().tolist()
results = []
for name in classes:
df_subset=df.loc[df['label']==name]
reg = LinearRegression()
reg.fit(df_subset['v1'].values.reshape(-1, 1), df_subset["target"].values.reshape(-1, 1))
predictions = reg.predict(df_subset['v1'].values.reshape(-1, 1))
res=np.mean((predictions - df_subset["target"].values.reshape(-1, 1)) ** 2)
results.append(res)
msg = "Metric model %s: %f " % (name, res)
print(msg)
df_subset['pred']=predictions
sns.scatterplot(data=df_subset, x='pred', y="target")
Just create a new figure before sns plot.
plt.figure() <---
after sns plot do plt.show() so that you can show print statement(model metric) before each plot.
import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.metrics import r2_score
from scipy.stats import binom
from scipy.stats import norm
import numpy as np
import seaborn as sns
from scipy.stats import norm
# generate random numbers from N(0,1)
x = norm.rvs(size=10000,loc=0,scale=1)
y = norm.rvs(size=10000,loc=0,scale=1)
z = binom.rvs(n=10,p=0.8,size=10000)
df = pd.DataFrame(data={'v1':x.flatten(),'target':y.flatten(),'label':z.flatten()})
classes=df.label.unique().tolist()
results = []
for name in classes:
df_subset=df.loc[df['label']==name]
reg = LinearRegression()
reg.fit(df_subset['v1'].values.reshape(-1, 1), df_subset["target"].values.reshape(-1, 1))
predictions = reg.predict(df_subset['v1'].values.reshape(-1, 1))
res=np.mean((predictions - df_subset["target"].values.reshape(-1, 1)) ** 2)
results.append(res)
msg = "Metric model %s: %f " % (name, res)
print(msg)
plt.figure() #<-----------here
df_subset['pred']=predictions
sns.scatterplot(data=df_subset, x='pred', y="target")
plt.show() #<------------ here
I would recommend installing matplotlib library and then
import matplotlib.pyplot as plt
y = 0
.
.
.
#inside your for loop
plot = sns.scatterplot(data=df_subset, x='pred', y="target")
plt.savefig('plot_' + str(y))
plt.clf()
I run this code for polynomial regression using sklearn but my plot is not what i was expecting. As you can see here i'm not getting a smooth line but it's jumping from one point to another. From my understanding i have to sort X, but when i do that all i get is an empty plot with a linear line.
import operator
import numpy as np
from sklearn.cluster import KMeans
from sklearn.linear_model import LinearRegression
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import PolynomialFeatures
from sklearn.preprocessing import StandardScaler
import matplotlib.pyplot as plt
import pandas as pd
from sklearn.metrics import mean_squared_error, r2_score
import statsmodels.formula.api as smf
df = pd.read_csv('D:\Mall_Customers.csv', usecols = ['Age', 'Annual Income (k$)','Spending Score (1-100)'])
x = StandardScaler().fit_transform(df)
kmeans = KMeans(n_clusters=3, max_iter=100)
y_kmeans= kmeans.fit_predict(x)
mydict = {i: np.where(kmeans.labels_ == i)[0] for i in range(kmeans.n_clusters)}
dictlist = []
for key, value in mydict.items():
temp = [key,value]
dictlist.append(temp)
df0 = df[df.index.isin(mydict[0].tolist())]
X = df0[['Age', 'Annual Income (k$)']]
Y = df0['Spending Score (1-100)']
poly_reg = PolynomialFeatures(degree=2)
X_poly = poly_reg.fit_transform(X)
model = LinearRegression()
model.fit(X_poly, Y)
y_poly_pred = model.predict(X_poly)
r2 = r2_score(Y,y_poly_pred)
print(r2)
model = make_pipeline(PolynomialFeatures(degree=2), LinearRegression(fit_intercept = False))
model.fit(X,Y)
plt.scatter(X.iloc[:, 1], Y, color='red')
plt.plot(X, Y, color='blue')
plt.xlabel('Age. Annual income')
plt.ylabel('Spending Score')
plt.show()
TLDR; the data is not linear dependent.
The reason the graph got so messy is because you plotted the X (train data) with the Y (the actual prediction data) and the fact that you were plotting this data while:
the data was messy and not really linear dependent
is what made the result this messy graph.
I suggest you to:
split to the train data into train, test and then after you train the model check the error with the test and maybe create 2 plots, 1 with the model results according to the test data and one with the actual result for the test data.
and change plot code to this:
.
plt.scatter(X, Y)
plt.plot(X, Y_pred, color='red')
plt.show()
In python 2.7.6, matlablib, scikit learn 0.17.0, When I make a polynomial regression lines on a scatter plot, the polynomial curve will be really messy like this:
The script is like this: it will read two columns of floating data and make a scatter plot and regression
import pandas as pd
import scipy.stats as stats
import pylab
import numpy as np
import matplotlib.pyplot as plt
import statsmodels.api as sm
import pylab as pl
import sklearn
from sklearn import preprocessing
from sklearn.cross_validation import train_test_split
from sklearn import datasets, linear_model
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import PolynomialFeatures
from sklearn.pipeline import make_pipeline
from sklearn.linear_model import Ridge
df=pd.read_csv("boston_real_estate_market_clean.csv")
LSTAT = df['LSTAT'].as_matrix()
LSTAT=LSTAT.reshape(LSTAT.shape[0], 1)
MEDV=df['MEDV'].as_matrix()
MEDV=MEDV.reshape(MEDV.shape[0], 1)
# Train test set split
X_train1, X_test1, y_train1, y_test1 = train_test_split(LSTAT,MEDV,test_size=0.3,random_state=1)
# Ploynomial Regression-nst order
plt.scatter(X_test1, y_test1, s=10, alpha=0.3)
for degree in [1,2,3,4,5]:
model = make_pipeline(PolynomialFeatures(degree), Ridge())
model.fit(X_train1,y_train1)
y_plot = model.predict(X_test1)
plt.plot(X_test1, y_plot, label="degree %d" % degree
+'; $q^2$: %.2f' % model.score(X_train1, y_train1)
+'; $R^2$: %.2f' % model.score(X_test1, y_test1))
plt.legend(loc='upper right')
plt.show()
I guess the reason is because the "X_test1, y_plot" are not sorted properly?
X_test1 is a numpy array like this:
[[ 5.49]
[ 16.65]
[ 17.09]
....
[ 25.68]
[ 24.39]]
yplot is a numpy array like this:
[[ 29.78517812]
[ 17.16759833]
[ 16.86462359]
[ 23.18680265]
...[ 37.7631725 ]]
I try to sort with this:
[X_test1, y_plot] = zip(*sorted(zip(X_test1, y_plot), key=lambda y_plot: y_plot[0]))
plt.plot(X_test1, y_plot, label="degree %d" % degree
+'; $q^2$: %.2f' % model.score(X_train1, y_train1)
+'; $R^2$: %.2f' % model.score(X_test1, y_test1))
The curve looks normal now but the result is weird with a negative R^2.
Could any guru show me the real issue is or how to sort here properly? Thank you!
While the plot is now correct, you messed up the pairing of X_test1 to y_test1 while sorting because you forgot to also sort y_test1 in the same way.
The best solution is to sort right after the split. Then y_plot, which is computed later, will be automatically correct: (Here untested example using numpy as np)
X_train1, X_test1, y_train1, y_test1 = train_test_split(LSTAT,MEDV,test_size=0.3,random_state=1)
sorted_index = np.argsort(X_test1)
X_test1 = X_test1[sorted_index]
y_test1 = y_test1[sorted_index]