In
[ ]: import pandas as pd
In [ ]: data = pd.read_csv('mushrooms.csv')
data.head()
data.shape
(8124, 23)
Out[ ]:
1. Class distribution
In [ ]: import matplotlib.pyplot as plt
import seaborn as sns
# Count the number of mushrooms in each class
class_counts = data['class'].value_counts()
# Plot a pie chart of the class distribution
plt.pie(class_counts.values, labels=class_counts.index, autopct='%1.1f%%')
plt.title('Class Distribution')
plt.show()
# Plot a bar chart of the class distribution
sns.countplot(data['class'])
plt.xlabel('Class')
plt.ylabel('Number of Mushrooms')
plt.title('Class Distribution')
plt.show()
c:\Users\praty\AppData\Local\Programs\Python\Python310\lib\site-packages\seaborn\_decorators.
py:36: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the
only valid positional argument will be `data`, and passing other arguments without an explici
t keyword will result in an error or misinterpretation.
warnings.warn(
2.Feature distributions:
In [ ]: import matplotlib.pyplot as plt
import seaborn as sns
# Loop over all the features and plot a histogram of their values
for col in data.columns[1:]:
sns.histplot(data=data, x=col, hue='class', multiple='stack', bins=20)
plt.title(col)
plt.show()
3.Feature correlations:
In [ ]: import seaborn as sns
# Compute the correlation matrix
corr = data.corr()
# Check if the correlation matrix is empty
if corr.empty:
print('No correlations found.')
else:
# Plot the correlation matrix as a heatmap
sns.heatmap(corr, cmap='coolwarm', annot=True)
plt.title('Feature Correlations')
plt.show()
No correlations found.
In [ ]: data.head()
Out[ ]: stalk- sta
cap- cap- cap- gill- gill- gill- gill- stalk- stalk- surface- surfa
class bruises odor
shape surface color attachment spacing size color shape root above- belo
ring r
0 p x s n t p f c n k e e s
1 e x s y t a f c b k e c s
2 e b s w t l f c b n e c s
3 p x y w t p f c n n e e s
4 e x s g f n f w b k t e s
In [ ]: import pandas as pd
# Load data
data = pd.read_csv('mushrooms.csv')
# Summarize the dataset
summary = data.describe()
# Print the summary
print(summary)
class cap-shape cap-surface cap-color bruises odor gill-attachment \
count 8124 8124 8124 8124 8124 8124 8124
unique 2 6 4 10 2 9 2
top e x y n f n f
freq 4208 3656 3244 2284 4748 3528 7914
gill-spacing gill-size gill-color stalk-shape stalk-root \
count 8124 8124 8124 8124 8124
unique 2 2 12 2 5
top c b b t b
freq 6812 5612 1728 4608 3776
stalk-surface-above-ring stalk-surface-below-ring \
count 8124 8124
unique 4 4
top s s
freq 5176 4936
stalk-color-above-ring stalk-color-below-ring veil-type veil-color \
count 8124 8124 8124 8124
unique 9 9 1 4
top w w p w
freq 4464 4384 8124 7924
ring-number ring-type spore-print-color population habitat
count 8124 8124 8124 8124 8124
unique 3 5 9 6 7
top o p w v d
freq 7488 3968 2388 4040 3148
In [ ]: import matplotlib.pyplot as plt
# Plot bar chart of categorical variables
data['cap-shape'].value_counts().plot(kind='bar')
plt.title('Cap Shape')
plt.xlabel('Shape')
plt.ylabel('Count')
plt.show()
In [ ]: # Plot histogram of numerical variables
data['bruises'].hist()
plt.title('Bruises')
plt.xlabel('Presence')
plt.ylabel('Count')
plt.show()
In [ ]: pd.set_option('display.max_columns',None)
1. Display Top 5 Rows of The Dataset
In [ ]: data.head()
Out[ ]: stalk- sta
cap- cap- cap- gill- gill- gill- gill- stalk- stalk- surface- surfa
class bruises odor
shape surface color attachment spacing size color shape root above- belo
ring r
0 p x s n t p f c n k e e s
1 e x s y t a f c b k e c s
2 e b s w t l f c b n e c s
3 p x y w t p f c n n e e s
4 e x s g f n f w b k t e s
In [ ]: # Attribute Information: (classes: edible=e, poisonous=p)
# cap-shape: bell=b,conical=c,convex=x,flat=f, knobbed=k,sunken=s
# cap-surface: fibrous=f,grooves=g,scaly=y,smooth=s
# cap-color: brown=n,buff=b,cinnamon=c,gray=g,green=r,pink=p,purple=u,red=e,white=w,yello
# bruises: bruises=t,no=f
# odor: almond=a,anise=l,creosote=c,fishy=y,foul=f,musty=m,none=n,pungent=p,spicy=s
# gill-attachment: attached=a,descending=d,free=f,notched=n
# gill-spacing: close=c,crowded=w,distant=d
# gill-size: broad=b,narrow=n
# gill-color: black=k,brown=n,buff=b,chocolate=h,gray=g, green=r,orange=o,pink=p,purple=u
# stalk-shape: enlarging=e,tapering=t
# stalk-root: bulbous=b,club=c,cup=u,equal=e,rhizomorphs=z,rooted=r,missing=?
# stalk-surface-above-ring: fibrous=f,scaly=y,silky=k,smooth=s
# stalk-surface-below-ring: fibrous=f,scaly=y,silky=k,smooth=s
# stalk-color-above-ring: brown=n,buff=b,cinnamon=c,gray=g,orange=o,pink=p,red=e,white=w,
# stalk-color-below-ring: brown=n,buff=b,cinnamon=c,gray=g,orange=o,pink=p,red=e,white=w,
# veil-type: partial=p,universal=u
# veil-color: brown=n,orange=o,white=w,yellow=y
# ring-number: none=n,one=o,two=t
# ring-type: cobwebby=c,evanescent=e,flaring=f,large=l,none=n,pendant=p,sheathing=s,zone=
# spore-print-color: black=k,brown=n,buff=b,chocolate=h,green=r,orange=o,purple=u,white=w
# population: abundant=a,clustered=c,numerous=n,scattered=s,several=v,solitary=y
# habitat: grasses=g,leaves=l,meadows=m,paths=p,urban=u,waste=w,woods=d
2. Check Last 5 Rows of The Dataset
In [ ]: data.tail()
Out[ ]: stalk-
cap- cap- cap- gill- gill- gill- gill- stalk- stalk- surface- s
class bruises odor
shape surface color attachment spacing size color shape root above-
ring
8119 e k s n f n a c b y e ? s
8120 e x s n f n a c b y e ? s
8121 e f s n f n a c b n e ? s
8122 p k y n f y f c n b t ? s
8123 e x s n f n a c b y e ? s
3. Find Shape of Our Dataset (Number of Rows And Number of
Columns)
In [ ]: data.shape
(8124, 23)
Out[ ]:
In [ ]: print("Number of Rows",data.shape[0])
print("Number of Columns",data.shape[1])
Number of Rows 8124
Number of Columns 23
4. Get Information About Our Dataset Like Total Number Rows, Total
Number of Columns, Datatypes of Each Column And Memory
Requirement
In [ ]: data.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 8124 entries, 0 to 8123
Data columns (total 23 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 class 8124 non-null object
1 cap-shape 8124 non-null object
2 cap-surface 8124 non-null object
3 cap-color 8124 non-null object
4 bruises 8124 non-null object
5 odor 8124 non-null object
6 gill-attachment 8124 non-null object
7 gill-spacing 8124 non-null object
8 gill-size 8124 non-null object
9 gill-color 8124 non-null object
10 stalk-shape 8124 non-null object
11 stalk-root 8124 non-null object
12 stalk-surface-above-ring 8124 non-null object
13 stalk-surface-below-ring 8124 non-null object
14 stalk-color-above-ring 8124 non-null object
15 stalk-color-below-ring 8124 non-null object
16 veil-type 8124 non-null object
17 veil-color 8124 non-null object
18 ring-number 8124 non-null object
19 ring-type 8124 non-null object
20 spore-print-color 8124 non-null object
21 population 8124 non-null object
22 habitat 8124 non-null object
dtypes: object(23)
memory usage: 1.4+ MB
5. Check Null Values In The Dataset
In [ ]: data.isnull().sum()
class 0
Out[ ]:
cap-shape 0
cap-surface 0
cap-color 0
bruises 0
odor 0
gill-attachment 0
gill-spacing 0
gill-size 0
gill-color 0
stalk-shape 0
stalk-root 0
stalk-surface-above-ring 0
stalk-surface-below-ring 0
stalk-color-above-ring 0
stalk-color-below-ring 0
veil-type 0
veil-color 0
ring-number 0
ring-type 0
spore-print-color 0
population 0
habitat 0
dtype: int64
6. Get Overall Statistics About The Dataset
In [ ]: data.describe()
Out[ ]: stalk-
cap- cap- cap- gill- gill- gill- gill- stalk- stalk- surface-
class bruises odor
shape surface color attachment spacing size color shape root above-
ring
count 8124 8124 8124 8124 8124 8124 8124 8124 8124 8124 8124 8124 8124
unique 2 6 4 10 2 9 2 2 2 12 2 5 4
top e x y n f n f c b b t b s
freq 4208 3656 3244 2284 4748 3528 7914 6812 5612 1728 4608 3776 5176
7. Data Manipulation
In [ ]: data.head()
Out[ ]: stalk- sta
cap- cap- cap- gill- gill- gill- gill- stalk- stalk- surface- surfa
class bruises odor
shape surface color attachment spacing size color shape root above- belo
ring r
0 p x s n t p f c n k e e s
1 e x s y t a f c b k e c s
2 e b s w t l f c b n e c s
3 p x y w t p f c n n e e s
4 e x s g f n f w b k t e s
In [ ]: data.info()
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 8124 entries, 0 to 8123
Data columns (total 23 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 class 8124 non-null object
1 cap-shape 8124 non-null object
2 cap-surface 8124 non-null object
3 cap-color 8124 non-null object
4 bruises 8124 non-null object
5 odor 8124 non-null object
6 gill-attachment 8124 non-null object
7 gill-spacing 8124 non-null object
8 gill-size 8124 non-null object
9 gill-color 8124 non-null object
10 stalk-shape 8124 non-null object
11 stalk-root 8124 non-null object
12 stalk-surface-above-ring 8124 non-null object
13 stalk-surface-below-ring 8124 non-null object
14 stalk-color-above-ring 8124 non-null object
15 stalk-color-below-ring 8124 non-null object
16 veil-type 8124 non-null object
17 veil-color 8124 non-null object
18 ring-number 8124 non-null object
19 ring-type 8124 non-null object
20 spore-print-color 8124 non-null object
21 population 8124 non-null object
22 habitat 8124 non-null object
dtypes: object(23)
memory usage: 1.4+ MB
In [ ]: data = data.astype('category')
In [ ]: data.dtypes
class category
Out[ ]:
cap-shape category
cap-surface category
cap-color category
bruises category
odor category
gill-attachment category
gill-spacing category
gill-size category
gill-color category
stalk-shape category
stalk-root category
stalk-surface-above-ring category
stalk-surface-below-ring category
stalk-color-above-ring category
stalk-color-below-ring category
veil-type category
veil-color category
ring-number category
ring-type category
spore-print-color category
population category
habitat category
dtype: object
In [ ]: from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
for column in data.columns:
data[column]=le.fit_transform(data[column])
In [ ]: data.head()
Out[ ]: stalk- sta
cap- cap- cap- gill- gill- gill- gill- stalk- stalk- surface- surfa
class bruises odor
shape surface color attachment spacing size color shape root above- belo
ring r
0 1 5 2 4 1 6 1 0 1 4 0 3 2
1 0 5 2 9 1 0 1 0 0 4 0 2 2
2 0 0 2 8 1 3 1 0 0 5 0 2 2
3 1 5 3 8 1 6 1 0 1 5 0 3 2
4 0 5 2 3 0 5 1 1 0 4 1 3 2
8. Store Feature Matrix In X and Response(Target) In Vector y
In [ ]: X = data.drop('class',axis=1)
y = data['class']
9. Applying PCA
In [ ]: from sklearn.decomposition import PCA
pca1 = PCA(n_components = 7)
pca_fit1 = pca1.fit_transform(X)
10. Splitting The Dataset Into The Training Set And Test Set
In [ ]: from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test=train_test_split(pca_fit1,y,test_size=0.20,
random_state=42)
11. Import the models
In [ ]: from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import GradientBoostingClassifier
12. Model Training
In [ ]: lr = LogisticRegression()
lr.fit(X_train,y_train)
knn = KNeighborsClassifier()
knn.fit(X_train,y_train)
svc = SVC()
svc.fit(X_train,y_train)
dt = DecisionTreeClassifier()
dt.fit(X_train,y_train)
rm = RandomForestClassifier()
rm.fit(X_train,y_train)
gb = GradientBoostingClassifier()
gb.fit(X_train,y_train)
GradientBoostingClassifier()
Out[ ]:
13. Prediction on Test Data
In [ ]: y_pred1 = lr.predict(X_test)
y_pred2 = knn.predict(X_test)
y_pred3 = svc.predict(X_test)
y_pred4 = dt.predict(X_test)
y_pred5 = rm.predict(X_test)
y_pred6 = gb.predict(X_test)
In [ ]: import numpy as np
from sklearn.metrics import confusion_matrix
import seaborn as sns
import matplotlib.pyplot as plt
cm = confusion_matrix(y_test,y_pred3)
#Plot the confusion matrix.
sns.heatmap(cm,
annot=True,
fmt='g',
xticklabels=['poisonous','eadible'],
yticklabels=['poisonous','eadible'])
plt.ylabel('Prediction',fontsize=13)
plt.xlabel('Actual',fontsize=13)
plt.title('Confusion Matrix',fontsize=17)
plt.show()
In [ ]: from sklearn.metrics import classification_report
print(classification_report(y_test, y_pred3, target_names=['poisonous', 'edible']))
precision recall f1-score support
poisonous 0.94 0.97 0.95 843
edible 0.97 0.93 0.95 782
accuracy 0.95 1625
macro avg 0.95 0.95 0.95 1625
weighted avg 0.95 0.95 0.95 1625
14. Evaluating the Algorithm
In [ ]: from sklearn.metrics import accuracy_score
In [ ]: print("ACC LR",accuracy_score(y_test,y_pred1))
print("ACC KNN",accuracy_score(y_test,y_pred2))
print("ACC SVC",accuracy_score(y_test,y_pred3))
print("ACC DT",accuracy_score(y_test,y_pred4))
print("ACC RM",accuracy_score(y_test,y_pred5))
print("ACC GBC",accuracy_score(y_test,y_pred6))
ACC LR 0.8344615384615385
ACC KNN 0.9833846153846154
ACC SVC 0.952
ACC DT 0.9784615384615385
ACC RM 0.9975384615384615
ACC GBC 0.9384615384615385
In [ ]:
In [ ]: final_data = pd.DataFrame({'Models':['LR','KNN','SVC','DT','RM','GBC'],
'ACC': [accuracy_score(y_test,y_pred1)*100,
accuracy_score(y_test,y_pred2)*100,
accuracy_score(y_test,y_pred3)*100,
accuracy_score(y_test,y_pred4)*100,
accuracy_score(y_test,y_pred5)*100,
accuracy_score(y_test,y_pred6)*100]})
In [ ]: final_data
Out[ ]: Models ACC
0 LR 83.446154
1 KNN 98.338462
2 SVC 95.200000
3 DT 97.846154
4 RM 99.753846
5 GBC 93.846154
In [ ]: import seaborn as sns
sns.barplot(final_data['Models'],final_data['ACC'])
c:\Users\praty\AppData\Local\Programs\Python\Python310\lib\site-packages\seaborn\_decorators.
py:36: FutureWarning: Pass the following variables as keyword args: x, y. From version 0.12,
the only valid positional argument will be `data`, and passing other arguments without an exp
licit keyword will result in an error or misinterpretation.
warnings.warn(
<AxesSubplot:xlabel='Models', ylabel='ACC'>
Out[ ]:
Save The Model
In [ ]: rf_model = RandomForestClassifier()
rf_model.fit(pca_fit1,y)
RandomForestClassifier()
Out[ ]:
In [ ]: import joblib
In [ ]: joblib.dump(rf_model,"Mushroom_prediction")
['Mushroom_prediction']
Out[ ]:
In [ ]: model = joblib.load('Mushroom_prediction')
In [ ]:
In [ ]: p =model.predict(pca1.transform([[5,2,4,1,6,1,0,1,4,0,3,2,2,7,7,0,2,1,4,2,3,5]]))
c:\Users\praty\AppData\Local\Programs\Python\Python310\lib\site-packages\sklearn\base.py:450:
UserWarning: X does not have valid feature names, but PCA was fitted with feature names
warnings.warn(
In [ ]: if p[0]==1:
print('Poissonous')
else:
print('Edible')
Poissonous
GUI
In [ ]: from tkinter import *
import joblib
In [ ]: def show_entry_fields():
p1=int(e1.get())
p2=int(e2.get())
p3=int(e3.get())
p4=int(e4.get())
p5=int(e5.get())
p6=int(e6.get())
p7=int(e7.get())
p8=int(e8.get())
p9=int(e9.get())
p10=int(e10.get())
p11=int(e11.get())
p12=int(e12.get())
p13=int(e13.get())
p14=int(e14.get())
p15=int(e15.get())
p16=int(e16.get())
p17=int(e17.get())
p18=int(e18.get())
p19=int(e19.get())
p20=int(e20.get())
p21=int(e21.get())
p22=int(e22.get())
model = joblib.load('Mushroom_prediction')
result=model.predict(pca1.transform([[p1,p2,p3,p4,p5,p6,
p7,p8,p9,p10,p11,p12,p13,p14,p15,
p16,p17,p18,p19,p20,p21,p22]]))
if result[0] == 0:
Label(master, text="Edible").grid(row=31)
else:
Label(master, text="Poisonous").grid(row=31)
master = Tk()
master.title("Mushroom Classification Using Machine Learning")
label = Label(master, text = "Mushroom Classification Using Machine Learning"
, bg = "black", fg = "white"). \
grid(row=0,columnspan=2)
Label(master,text="cap-shape :(cap-shape: bell=0,conical=1,convex=5,flat=2, knobbed=3,sunken=
Label(master, text="cap-surface:(fibrous=0,grooves=1,scaly=3,smooth=2)").grid(row=2)
Label(master, text="cap-color:(brown=4,buff=0,cinnamon=1,gray=3,green=r, \
pink=5,purple=6,red=2,white=7,yellow=8)").grid(row=3)
Label(master, text="bruises:(bruises=1,no=0)").grid(row=4)
Label(master, text="odor:(almond=0,anise=3,creosote=1,fishy=8,foul=2,\
musty=4,none=5,pungent=6,spicy=7 \
)").grid(row=5)
Label(master, text="gill-attachment:(attached=0,descending=1,free=2,notched=3)").grid(row=6)
Label(master, text="gill-spacing:(close=0,crowded=2,distant=1 \
)").grid(row=7)
Label(master, text="gill-size:(road=0,narrow=1)").grid(row=8)
Label(master, text="gill-color:(black=4,brown=5,buff=0,chocolate=3,gray=2,green=8,orange=6,pi
Label(master, text="stalk-shape:(enlarging=0,tapering=1)").grid(row=10)
Label(master,text="stalk-root:( bulbous=0,club=1,cup=5,equal=2,rhizomorphs=4, \
rooted=3,missing=6)").grid(row=11)
Label(master,text="stalk-surface-above-ring:(fibrous=0,scaly=3,silky=1,smooth=2)").grid(row=1
Label(master,text="stalk-surface-below-ring:(fibrous=0,scaly=3,silky=1,smooth=2 \
)").grid(row=13)
Label(master,text="stalk-color-above-ring:(brown=4,buff=0,cinnamon=1,gray=3, \
orange=5,pink=6,red=2,white=7,yellow=8)").grid(row=14)
Label(master,text="stalk-color-below-ring:(brown=4,buff=0,cinnamon=1,gray=3, \
orange=5,pink=6,red=2,white=7,yellow=8)").grid(row=15)
Label(master,text="veil-type:(partial=0,universal=1)").grid(row=16)
Label(master,text="veil-color:(brown=0,orange=1,white=2,yellow=3)").grid(row=17)
Label(master,text="ring-number:(none=0,one=1,two=2)").grid(row=18)
Label(master,text="ring-type:(cobwebby=0,evanescent=1,flaring=2,large=3,\
none=4,pendant=5,sheathing=6,zone=7)").grid(row=19)
Label(master,text="spore-print-color:(black=2,brown=3,buff=0,chocolate=1, \
green=5,orange=4,purple=6,white=7,yellow=8 \
)").grid(row=20)
Label(master,text="population:(abundant=0,clustered=1,numerous=2,scattered=3, \
# several=4,solitary=5)").grid(row=21)
Label(master,text="habitat:(grasses=1,leaves=2,meadows=3,paths=4,urban=5,\
# waste=6,woods=0)").grid(row=22)
e1 = Entry(master)
e2 = Entry(master)
e3 = Entry(master)
e4 = Entry(master)
e5 = Entry(master)
e6 = Entry(master)
e7 = Entry(master)
e8 = Entry(master)
e9 = Entry(master)
e10 = Entry(master)
e11 = Entry(master)
e12 = Entry(master)
e13 = Entry(master)
e14 = Entry(master)
e15 = Entry(master)
e16 = Entry(master)
e17 = Entry(master)
e18 = Entry(master)
e19 = Entry(master)
e20 = Entry(master)
e21 = Entry(master)
e22 = Entry(master)
e1.grid(row=1, column=1)
e2.grid(row=2, column=1)
e3.grid(row=3, column=1)
e4.grid(row=4, column=1)
e5.grid(row=5, column=1)
e6.grid(row=6, column=1)
e7.grid(row=7, column=1)
e8.grid(row=8, column=1)
e9.grid(row=9, column=1)
e10.grid(row=10,column=1)
e11.grid(row=11,column=1)
e12.grid(row=12,column=1)
e13.grid(row=13,column=1)
e14.grid(row=14,column=1)
e15.grid(row=15,column=1)
e16.grid(row=16,column=1)
e17.grid(row=17,column=1)
e18.grid(row=18,column=1)
e19.grid(row=19,column=1)
e20.grid(row=20,column=1)
e21.grid(row=21,column=1)
e22.grid(row=22,column=1)
Button(master, text='Predict', command=show_entry_fields).grid()
mainloop()
Exception in Tkinter callback
Traceback (most recent call last):
File "c:\Users\praty\AppData\Local\Programs\Python\Python310\lib\tkinter\__init__.py", line
1921, in __call__
return self.func(*args)
File "C:\Users\praty\AppData\Local\Temp\ipykernel_32056\2331790229.py", line 2, in show_ent
ry_fields
p1=int(e1.get())
ValueError: invalid literal for int() with base 10: ''
Exception in Tkinter callback
Traceback (most recent call last):
File "c:\Users\praty\AppData\Local\Programs\Python\Python310\lib\tkinter\__init__.py", line
1921, in __call__
return self.func(*args)
File "C:\Users\praty\AppData\Local\Temp\ipykernel_32056\2331790229.py", line 2, in show_ent
ry_fields
p1=int(e1.get())
ValueError: invalid literal for int() with base 10: ''
c:\Users\praty\AppData\Local\Programs\Python\Python310\lib\site-packages\sklearn\base.py:450:
UserWarning: X does not have valid feature names, but PCA was fitted with feature names
warnings.warn(
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
