I'm trying to plot two probability density functions on one figure(so that they overlap).
import matplotlib.pyplot as plt
import numpy
import seaborn as sns
from sklearn.preprocessing import MinMaxScaler
import numpy as np
import pandas as pd
data = [0,0,1,2,2,2,2,1,2,3,0,5,4,5,4,6,2,2,5,4,6,3,2,5,4,3,7,-1,0]
scaler = MinMaxScaler()
df = pd.DataFrame(data, columns=['Numbers'])
X = numpy.asarray(data)
X=X.reshape(-1,1)
standardized_data = scaler.fit_transform(X)
normal_data = np.random.normal(loc=0.0, scale=1.0, size=len(df))
sns.displot(normal_data, kind='kde')
sns.displot(standardized_data, kind='kde')
plt.show()
sns.displot(
{"normal": normal_data, "standardized": standardized_data.squeeze()},
kind='kde'
)
Related
I just learned python, this is literally my first lesson and i was told to make kmeans with python. and while i was doing in and it gives me an error when i use plt.legend() i have read in sov that we should use ax.legend but apparently either it didn't work or i wrote it wrong. so i thought i'll just gave the code before i changed it to the ax. my english is not very good so please bear with it. thank you
import numpy as np
import pandas as pd
from sklearn.cluster import KMeans
from sklearn.preprocessing import MinMaxScaler
import matplotlib.pyplot as plt
import seaborn as sns
df = pd.read_excel("Umur.xlsx")
df.head()
print(df)
a = plt.scatter(df['Umur'],df['Gaji'])
plt.show()
km = KMeans(n_clusters=3)
km
y_predicted = km.fit_predict(df[['Umur','Gaji']])
y_predicted
print(y_predicted)
df['cluster'] = y_predicted
df.head()
print(df)
df1 = df[df.cluster==0]
df2 = df[df.cluster==1]
df3 = df[df.cluster==2]
plt.scatter(df1.Umur,df1['Gaji'],color='green')
plt.scatter(df2.Umur,df2['Gaji'],color='red')
plt.scatter(df3.Umur,df3['Gaji'],color='black')
#plt.scatter(km.cluster_centers_[:,0],km_clusters_centers_[:,1],color='purple',marker='*',label='centroid')
plt.xlabel('Umur')
plt.ylabel('Gaji')
plt.legend ()
I edit three lines and add one line like below:
...
gaji_green = plt.scatter(df1.Umur,df1['Gaji'],color='green')
gaji_red = plt.scatter(df2.Umur,df2['Gaji'],color='red')
gaji_balck = plt.scatter(df3.Umur,df3['Gaji'],color='black')
...
plt.legend((gaji_green, gaji_red, gaji_balck),
('gaji_green', 'gaji_red', 'gaji_balck'),
scatterpoints=1,
loc='lower left',
ncol=1,
fontsize=8)
...
finally, code like below:
import numpy as np
import pandas as pd
from sklearn.cluster import KMeans
from sklearn.preprocessing import MinMaxScaler
import matplotlib.pyplot as plt
import seaborn as sns
df = pd.read_excel("Umur.xlsx")
km = KMeans(n_clusters=3)
y_predicted = km.fit_predict(df[['Umur','Gaji']])
df['cluster'] = y_predicted
df1 = df[df.cluster==0]
df2 = df[df.cluster==1]
df3 = df[df.cluster==2]
gaji_green = plt.scatter(df1.Umur,df1['Gaji'],color='green')
gaji_red = plt.scatter(df2.Umur,df2['Gaji'],color='red')
gaji_balck = plt.scatter(df3.Umur,df3['Gaji'],color='black')
plt.xlabel('Umur')
plt.ylabel('Gaji')
plt.legend ()
plt.legend((gaji_green, gaji_red, gaji_balck),
('gaji_green', 'gaji_red', 'gaji_balck'),
scatterpoints=1,
loc='lower left',
ncol=1,
fontsize=8)
plt.show()
I'm having trouble using the scatter to create a scatter plot. Can someone help me? I've highlighted the line causing the error:
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans
import numpy as np
from sklearn.preprocessing import StandardScaler
data = pd.read_csv('vetl8.csv')
df = pd.DataFrame(data=data)
clusterNum = 3
X = df.iloc[:, 1:].values
X = np.nan_to_num(X)
Clus_dataSet = StandardScaler().fit_transform(X)
k_means = KMeans(init="k-means++", n_clusters=clusterNum, n_init=12)
k_means.fit(X)
labels = k_means.labels_
df["Labels"] = labels
df.to_csv('dfkmeans.csv')
plt.scatter(df[2], df[1], c=labels) **#Here**
plt.xlabel('K', fontsize=18)
plt.ylabel('g', fontsize=16)
plt.show()
#data set correct
You are close, just a minor adjustment to access the x-y columns by number should fix it:
plt.scatter(df[df.columns[2]], df[df.columns[1]], c=df["Labels"])
I am trying to utilize k means clustering in Python and I am encountering an error. The dataset that I am working with can be found here:
https://www.fueleconomy.gov/feg/ws/index.shtml#vehicle
import pandas as pd
import seaborn as sns
import numpy as np
#from matplotlib import pyplot as plt
import matplotlib.pyplot as plt
from matplotlib import style
%matplotlib inline
from sklearn.preprocessing import scale, StandardScaler
import sklearn
from sklearn.cluster import KMeans
df = pd.read_csv('vehicles.csv')
df2 = df[['comb08','youSaveSpend']].copy()
scaler = StandardScaler()
scaler.fit(df2)
scaled_array = scaler.transform(df2)
average = np.mean(scaled_array[:,0])
std = np.std(scaled_array[:,0])
df2 = scaled_array
max_clusters = 10
noClusters = range(1, max_clusters + 1)
kmeans = [KMeans(n_clusters = i) for i in noClusters]
score = [kmeans[i].fit(df6).score(df2) for i in range(len(kmeans))]
plt.plot(noClusters, score)
plt.xlabel('Number of Clusters')
plt.ylabel("Score")
plt.title('Elbow Curve')
kmeans = KMeans(n_clusters = 10, random_state = 0)
kmeans = kmeans.fit(scaled_array)
unscaled = scaler.inverse_transform(kmeans.cluster_centers_)
unscaled
centroids = pd.DataFrame({'centroidx':unscaled[:,0],'centroidy':unscaled[:,1]})
df2['label'] = kmeans.labels_.astype(np.int)
df2.head() # <======== Error Occurs Here
plt.scatter(df2['comb08'], df2['youSaveSpend'], c=df2.label) # (x,y,color)
plt.scatter(centroids['centroidx'], \
centroids['centroidy'], c='red') # (x,y,color)
plt.show() <======== Error also Occurs Here
The error I get is the below:
When I try to convert my floats like so:
df2 = df.apply(pd.to_numeric)
I get this error:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.linear_model import RidgeCV
tips = sns.load_dataset('tips')
X = tips.drop(columns=['tip','sex', 'smoker', 'day', 'time'])
y = tips['tip']
alphas = 10**np.linspace(10,-2,100)*0.5
ridge_clf = RidgeCV(alphas=alphas,scoring='r2').fit(X, y)
ridge_clf.score(X, y)
I wanted to plot the following graph for RidgeCV. I don't see any option to do that like GridSearhCV. I appreciate your suggestions!
There is no indication what the colors stand for. I assume they stand for features and we investigate the size of each feature weight as function of alpha. Here is my solution:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.linear_model import RidgeCV
tips = sns.load_dataset('tips')
X = tips.drop(columns=['tip','sex', 'smoker', 'day', 'time'])
y = tips['tip']
alphas = 10**np.linspace(10,-2,100)*0.5
w = list()
for a in alphas:
ridge_clf = RidgeCV(alphas=[a],cv=10).fit(X, y)
w.append(ridge_clf.coef_)
w = np.array(w)
plt.semilogx(alphas,w)
plt.title('Ridge coefficients as function of the regularization')
plt.xlabel('alpha')
plt.ylabel('weights')
plt.legend(X.keys())
Output:
Since you only have two features in X there are only two lines.
Here is the code for generating the plot that you had posted.
Firstly, we need to understand that RidgeCV would not return the coef for each alpha value that we had fed in the alphas param.
The motivation behind having the RidgeCV is that it will try for different alpha values mentioned in alphas param, then based on cross validation scoring, it will return the best alpha along with the fitted model.
Hence, the only way to get the coef for each alpha value using cv is iterate through RidgeCV using each alpha value.
Example:
# Author: Fabian Pedregosa -- <fabian.pedregosa#inria.fr>
# License: BSD 3 clause
print(__doc__)
import numpy as np
import matplotlib.pyplot as plt
from sklearn import linear_model
# X is the 10x10 Hilbert matrix
X = 1. / (np.arange(1, 11) + np.arange(0, 10)[:, np.newaxis])
y = np.ones(10)
# #############################################################################
# Compute paths
n_alphas = 200
alphas = np.logspace(-10, -2, n_alphas)
coefs = []
for a in alphas:
ridge = linear_model.RidgeCV(alphas=[a], fit_intercept=False, cv=3)
ridge.fit(X, y)
coefs.append(ridge.coef_)
# #############################################################################
# Display results
ax = plt.gca()
ax.plot(alphas, coefs)
ax.set_xscale('log')
ax.set_xlim(ax.get_xlim()[::-1]) # reverse axis
plt.xlabel('alpha')
plt.ylabel('weights')
plt.title('RidgeCV coefficients as a function of the regularization')
plt.axis('tight')
plt.show()
I would like to depict the value of my variables found in a dataset in the form of a boxplot. The dataset is the following:
https://archive.ics.uci.edu/ml/datasets/breast+cancer+wisconsin+(original)
So far my code is the following:
import pandas as pd
import numpy as np
from sklearn.impute import SimpleImputer
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn import preprocessing
df=pd.read_csv(file,names=['id', 'clump_thickness','unif_cell_size',
'unif_cell_shape', 'marg_adhesion', 'single_epith_cell_size',
'bare_nuclei', 'bland_chromatin', 'normal_nucleoli','mitoses','Class'])
#boxplot
plt.figure(figsize=(15,10))
names=list(df.columns)
names=names[:-1]
min_max_scaler=preprocessing.MinMaxScaler()
X = df.drop(["Class"],axis=1)
columnsN=list(X.columns)
x_scaled=min_max_scaler.fit_transform(X) #normalization
X[columnsN]=x_scaled
y = df['Class']
sns.set_context('notebook', font_scale=1.5)
sns.boxplot(x=X['unif_cell_size'],y=y,data=df.iloc[:, :-1],orient="h")
My boxplot returns the following figure:
but I would like to display my information like the following graph:
I know that is from a different dataset, but I can see that they have displayed the diagnosis, at the same time, for each feature with their values. I have tried to do it in different ways, but I am not able to do that graph.
I have tried the following:
data_st = pd.concat([y,X],axis=1)
data_st = pd.melt(data_st,id_vars=columnsN,
var_name="X",
value_name='value')
sns.boxplot(x='value', y="X", data=data_st,hue=y,palette='Set1')
plt.legend(loc='best')
but still no results. Any help?
Thanks
Reshape the data with pandas.DataFrame.melt:
Most of the benign (class 2) boxplots are at 0 (scaled) or 1 (unscaled), as they should be
print(df_scaled_melted.groupby(['Class', 'Attributes', 'Values'])['Values'].count().unstack()) after melt, to understand the counts
MinMaxScaler has been used, but is unnecessary in this case, because all of the data values are very close together. If you plot the data without scaling, the plot will look the same, except the y-axis range will be 1 - 10 instead.
This should really only be used in cases when the data is widely diverging, where an attribute will have too much influence with some ML algorithm.
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from pathlib import Path
import numpy as np
from sklearn.preprocessing import MinMaxScaler
# path to file
p = Path(r'c:\some_path_to_file\breast-cancer-wisconsin.data')
# create dataframe
df = pd.read_csv(p, names=['id', 'clump_thickness','unif_cell_size',
'unif_cell_shape', 'marg_adhesion', 'single_epith_cell_size',
'bare_nuclei', 'bland_chromatin', 'normal_nucleoli','mitoses','Class'])
# replace ? with np.NaN
df.replace('?', np.NaN, inplace=True)
# scale the data
min_max_scaler = MinMaxScaler()
df_scaled = pd.DataFrame(min_max_scaler.fit_transform(df.iloc[:, 1:-1]))
df_scaled.columns = df.columns[1:-1]
df_scaled['Class'] = df['Class']
# melt the dataframe
df_scaled_melted = df_scaled.iloc[:, 1:].melt(id_vars='Class', var_name='Attributes', value_name='Values')
# plot the data
plt.figure(figsize=(12, 8))
g = sns.boxplot(x='Attributes', y='Values', hue='Class', data=df_scaled_melted)
for item in g.get_xticklabels():
item.set_rotation(90)
plt.legend(loc='center left', bbox_to_anchor=(1, 0.5))
plt.show()
Without scaling:
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from pathlib import Path
import numpy as np
p = Path.cwd() / r'data\breast_cancer\breast-cancer-wisconsin.data'
df = pd.read_csv(p, names=['id', 'clump_thickness','unif_cell_size',
'unif_cell_shape', 'marg_adhesion', 'single_epith_cell_size',
'bare_nuclei', 'bland_chromatin', 'normal_nucleoli','mitoses','Class'])
df.replace('?', np.NaN, inplace=True)
df.dropna(inplace=True)
df = df.astype('int')
df_melted = df.iloc[:, 1:].melt(id_vars='Class', var_name='Attributes', value_name='Values')
plt.figure(figsize=(12, 8))
g = sns.boxplot(x='Attributes', y='Values', hue='Class', data=df_melted)
for item in g.get_xticklabels():
item.set_rotation(90)
plt.legend(loc='center left', bbox_to_anchor=(1, 0.5))
plt.show()