Question

Question 1:

Please fetch the ‘Price’ column of the ford_escort.csv dataset.

Count the number of rows, and calculate the max, min, stdv and average of this column.

Show me the cars that their price is above the average.

Here is the link to download ford_escort.csv: https://www.dropbox.com/s/qczaguno5hfdico/ford_escort.csv?dl=0

Question 2:

The followings are the attributes of the wine quality dataset:

Input variables (based on physicochemical tests):

1. fixed acidity
2. volatile acidity
3. citric acid
4. residual sugar
5. chlorides
6. free sulfur dioxide
7. total sulfur dioxide
8. density
9. pH
10. sulphates
11. alcohol

Output variable (based on sensory data):

12. quality (score between 0 and 10)

Please split the dataset into 80% for training and 20% for testing. Use two different machine learning algorithms to predict the labels for the testing segment (the 20% that you have separated for the testing).

Calculate the accuracy and see which algorithm provides better accuracy. You can use any ML algorithm, such as the decision tree, KNN, or any others.

Here is the link to download wine.csv:

https://www.dropbox.com/s/v0t9tb4gq8tiqh8/wine.csv?dl=0

Answer 1

Answers for Question 1 :

import pandas as pd
df = pd.read_csv (r'ford_escort.csv')
mean_price = df['Price'].mean()
max_price = df['Price'].max()
min_price = df['Price'].min()
count = df['Price'].count()
std_price = df['Price'].std()

print ('No. of Rows : ' + str(count))
print ('Max Price : ' + str(max_price))
print ('Min Price : ' + str(min_price))
print ('Stdv Price : ' + str(std_price))
print ('Average of Price : ' + str(mean_price))

print("\nCars that are above average price are :\n")
cars = df [['Year','Mileage','Price']][df.Price>df['Price'].mean()]
print(cars)

Answer for Question 2 :

import numpy as np
import pandas as pd
import matplotlib as plt
import seaborn as sns

df = pd.read_csv("wine.csv")
print("Rows, columns: " + str(df.shape))

O/p : Rows, columns: (1599, 12)

df.head()

o/p:
fixed acidity   volatile acidity   citric acid   residual sugar   chlorides   free sulfur dioxide   total sulfur dioxide   density   pH   sulphates   alcohol   quality
0   7.4   0.70   0.00   1.9   0.076   11   34   0.9978   3.51   0.56   9.4   5
1   7.8   0.88   0.00   2.6   0.098   25   67   0.9968   3.20   0.68   9.8   5
2   7.8   0.76   0.04   2.3   0.092   15   54   0.9970   3.26   0.65   9.8   5
3   11.2   0.28   0.56   1.9   0.075   17   60   0.9980   3.16   0.58   9.8   6
4   7.4   0.70   0.00   1.9   0.076   11   34   0.9978   3.51   0.56   9.4   5
In [41]:
print(df.isna().sum())
fixed acidity 0
volatile acidity 0
citric acid 0
residual sugar 0
chlorides 0
free sulfur dioxide 0
total sulfur dioxide 0
density 0
pH 0
sulphates 0
alcohol 0
quality 0
dtype: int64
In [42]:
# Create Classification version of target variable
df['goodquality'] = [1 if x >= 7 else 0 for x in df['quality']]
In [43]:
# Separate feature variables and target variable
X = df.drop(['quality','goodquality'], axis = 1)
y = df['goodquality']
In [44]:
# See proportion of good vs bad wines
df['goodquality'].value_counts()
Out[44]:
0 1382
1 217
Name: goodquality, dtype: int64
In [45]:
# Normalize feature variables
from sklearn.preprocessing import StandardScaler
X_features = X
X = StandardScaler().fit_transform(X)
In [46]:
# Splitting the data
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.2, random_state=0)
In [47]:
# Decision Tree
from sklearn.metrics import classification_report
from sklearn.tree import DecisionTreeClassifier

model1 = DecisionTreeClassifier(random_state=1)
model1.fit(X_train, y_train)
y_pred1 = model1.predict(X_test)

print(classification_report(y_test, y_pred1))
precision recall f1-score support

0 0.97 0.91 0.94 290
1 0.48 0.77 0.59 30

accuracy 0.90 320
macro avg 0.73 0.84 0.77 320
weighted avg 0.93 0.90 0.91 320

In [48]:
#Random Forest
from sklearn.ensemble import RandomForestClassifier

model2 = RandomForestClassifier(random_state=1)
model2.fit(X_train, y_train)
y_pred2 = model2.predict(X_test)

print(classification_report(y_test, y_pred2))
precision recall f1-score support

0 0.95 0.97 0.96 290
1 0.65 0.50 0.57 30

accuracy 0.93 320
macro avg 0.80 0.74 0.76 320
weighted avg 0.92 0.93 0.92 320

C:\Users\Dell\Anaconda3\lib\site-packages\sklearn\ensemble\forest.py:245: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.
"10 in version 0.20 to 100 in 0.22.", FutureWarning)
In [49]:
#AdaBoost
from sklearn.ensemble import AdaBoostClassifier

model3 = AdaBoostClassifier(random_state=1)
model3.fit(X_train, y_train)
y_pred3 = model3.predict(X_test)

print(classification_report(y_test, y_pred3))
precision recall f1-score support

0 0.94 0.96 0.95 290
1 0.52 0.43 0.47 30

accuracy 0.91 320
macro avg 0.73 0.70 0.71 320
weighted avg 0.90 0.91 0.91 320

In [50]:
#Gradient Boosting
from sklearn.ensemble import GradientBoostingClassifier

model4 = GradientBoostingClassifier(random_state=1)
model4.fit(X_train, y_train)
y_pred4 = model4.predict(X_test)

print(classification_report(y_test, y_pred4))
precision recall f1-score support

0 0.95 0.95 0.95 290
1 0.53 0.57 0.55 30

accuracy 0.91 320
macro avg 0.74 0.76 0.75 320
weighted avg 0.92 0.91 0.91 320

In [51]:
#XGBoost
import xgboost as xgb

model5 = xgb.XGBClassifier(random_state=1)
model5.fit(X_train, y_train)
y_pred5 = model5.predict(X_test)

print(classification_report(y_test, y_pred5))
precision recall f1-score support

0 0.97 0.93 0.95 290
1 0.52 0.73 0.61 30

accuracy 0.91 320
macro avg 0.75 0.83 0.78 320
weighted avg 0.93 0.91 0.92 320

By comparing the five models, the random forest and XGBoost seems to yield the highest level of accuracy.

However, since XGBoost has a better f1-score for predicting good quality wines, I’m concluding that the XGBoost is the best of all Models