Project 1
Machine Learning Fundamentals In Depth - Challenges --- Project 1
Data cleaning on Automobile 1985 dataset and perform descriptive analytics
In [325]:
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
In [326]:
df=pd.read_csv('auto_dataset.csv')
print(df)
symboling normalized-losses make aspiration num-of-doors \
0 3 122 alfa-romero std two
1 3 122 alfa-romero std two
2 1 122 alfa-romero std two
3 2 164 audi std four
4 2 164 audi std four
.. ... ... ... ... ...
196 -1 95 volvo std four
197 -1 95 volvo turbo four
198 -1 95 volvo std four
199 -1 95 volvo turbo four
200 -1 95 volvo turbo four
body-style drive-wheels engine-location wheel-base length ... \
0 convertible rwd front 88.6 0.811148 ...
1 convertible rwd front 88.6 0.811148 ...
2 hatchback rwd front 94.5 0.822681 ...
3 sedan fwd front 99.8 0.848630 ...
4 sedan 4wd front 99.4 0.848630 ...
.. ... ... ... ... ... ...
196 sedan rwd front 109.1 0.907256 ...
197 sedan rwd front 109.1 0.907256 ...
198 sedan rwd front 109.1 0.907256 ...
199 sedan rwd front 109.1 0.907256 ...
200 sedan rwd front 109.1 0.907256 ...
compression-ratio horsepower peak-rpm city-mpg highway-mpg price \
0 9.0 111.0 5000.0 21 27 13495.0
1 9.0 111.0 5000.0 21 27 16500.0
2 9.0 154.0 5000.0 19 26 16500.0
3 10.0 102.0 5500.0 24 30 13950.0
4 8.0 115.0 5500.0 18 22 17450.0
.. ... ... ... ... ... ...
196 9.5 114.0 5400.0 23 28 16845.0
197 8.7 160.0 5300.0 19 25 19045.0
198 8.8 134.0 5500.0 18 23 21485.0
199 23.0 106.0 4800.0 26 27 22470.0
200 9.5 114.0 5400.0 19 25 22625.0
city-L/100km horsepower-binned diesel gas
0 11.190476 Medium 0 1
1 11.190476 Medium 0 1
2 12.368421 Medium 0 1
3 9.791667 Medium 0 1
4 13.055556 Medium 0 1
.. ... ... ... ...
196 10.217391 Medium 0 1
197 12.368421 High 0 1
198 13.055556 Medium 0 1
199 9.038462 Medium 1 0
200 12.368421 Medium 0 1
[201 rows x 29 columns]
In [327]:
df.isnull().sum()
Out[327]:
symboling 0 normalized-losses 0 make 0 aspiration 0 num-of-doors 0 body-style 0 drive-wheels 0 engine-location 0 wheel-base 0 length 0 width 0 height 0 curb-weight 0 engine-type 0 num-of-cylinders 0 engine-size 0 fuel-system 0 bore 0 stroke 4 compression-ratio 0 horsepower 0 peak-rpm 0 city-mpg 0 highway-mpg 0 price 0 city-L/100km 0 horsepower-binned 1 diesel 0 gas 0 dtype: int64
In [328]:
import missingno as ms
plt.title("Missing Values", fontsize=20);
ms.bar(df)
Out[328]:
<matplotlib.axes._subplots.AxesSubplot at 0x7fd671d6ad50>
In [329]:
ms.heatmap(df,figsize=(10,8), fontsize=12);
plt.title("Missing Number Correlation Plot");
In [330]:
print(df["horsepower-binned"].isnull().sum())
df = df.fillna(0)
1
In [331]:
df = df.fillna(0)
In [332]:
df.isnull().sum()
Out[332]:
symboling 0 normalized-losses 0 make 0 aspiration 0 num-of-doors 0 body-style 0 drive-wheels 0 engine-location 0 wheel-base 0 length 0 width 0 height 0 curb-weight 0 engine-type 0 num-of-cylinders 0 engine-size 0 fuel-system 0 bore 0 stroke 0 compression-ratio 0 horsepower 0 peak-rpm 0 city-mpg 0 highway-mpg 0 price 0 city-L/100km 0 horsepower-binned 0 diesel 0 gas 0 dtype: int64
In [333]:
df.info()
<class 'pandas.core.frame.DataFrame'> RangeIndex: 201 entries, 0 to 200 Data columns (total 29 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 symboling 201 non-null int64 1 normalized-losses 201 non-null int64 2 make 201 non-null object 3 aspiration 201 non-null object 4 num-of-doors 201 non-null object 5 body-style 201 non-null object 6 drive-wheels 201 non-null object 7 engine-location 201 non-null object 8 wheel-base 201 non-null float64 9 length 201 non-null float64 10 width 201 non-null float64 11 height 201 non-null float64 12 curb-weight 201 non-null int64 13 engine-type 201 non-null object 14 num-of-cylinders 201 non-null object 15 engine-size 201 non-null int64 16 fuel-system 201 non-null object 17 bore 201 non-null float64 18 stroke 201 non-null float64 19 compression-ratio 201 non-null float64 20 horsepower 201 non-null float64 21 peak-rpm 201 non-null float64 22 city-mpg 201 non-null int64 23 highway-mpg 201 non-null int64 24 price 201 non-null float64 25 city-L/100km 201 non-null float64 26 horsepower-binned 201 non-null object 27 diesel 201 non-null int64 28 gas 201 non-null int64 dtypes: float64(11), int64(8), object(10) memory usage: 45.7+ KB
In [334]:
df.head(5)
Out[334]:
| symboling | normalized-losses | make | aspiration | num-of-doors | body-style | drive-wheels | engine-location | wheel-base | length | ... | compression-ratio | horsepower | peak-rpm | city-mpg | highway-mpg | price | city-L/100km | horsepower-binned | diesel | gas | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 3 | 122 | alfa-romero | std | two | convertible | rwd | front | 88.6 | 0.811148 | ... | 9.0 | 111.0 | 5000.0 | 21 | 27 | 13495.0 | 11.190476 | Medium | 0 | 1 |
| 1 | 3 | 122 | alfa-romero | std | two | convertible | rwd | front | 88.6 | 0.811148 | ... | 9.0 | 111.0 | 5000.0 | 21 | 27 | 16500.0 | 11.190476 | Medium | 0 | 1 |
| 2 | 1 | 122 | alfa-romero | std | two | hatchback | rwd | front | 94.5 | 0.822681 | ... | 9.0 | 154.0 | 5000.0 | 19 | 26 | 16500.0 | 12.368421 | Medium | 0 | 1 |
| 3 | 2 | 164 | audi | std | four | sedan | fwd | front | 99.8 | 0.848630 | ... | 10.0 | 102.0 | 5500.0 | 24 | 30 | 13950.0 | 9.791667 | Medium | 0 | 1 |
| 4 | 2 | 164 | audi | std | four | sedan | 4wd | front | 99.4 | 0.848630 | ... | 8.0 | 115.0 | 5500.0 | 18 | 22 | 17450.0 | 13.055556 | Medium | 0 | 1 |
5 rows × 29 columns
In [335]:
df.tail(5)
Out[335]:
| symboling | normalized-losses | make | aspiration | num-of-doors | body-style | drive-wheels | engine-location | wheel-base | length | ... | compression-ratio | horsepower | peak-rpm | city-mpg | highway-mpg | price | city-L/100km | horsepower-binned | diesel | gas | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 196 | -1 | 95 | volvo | std | four | sedan | rwd | front | 109.1 | 0.907256 | ... | 9.5 | 114.0 | 5400.0 | 23 | 28 | 16845.0 | 10.217391 | Medium | 0 | 1 |
| 197 | -1 | 95 | volvo | turbo | four | sedan | rwd | front | 109.1 | 0.907256 | ... | 8.7 | 160.0 | 5300.0 | 19 | 25 | 19045.0 | 12.368421 | High | 0 | 1 |
| 198 | -1 | 95 | volvo | std | four | sedan | rwd | front | 109.1 | 0.907256 | ... | 8.8 | 134.0 | 5500.0 | 18 | 23 | 21485.0 | 13.055556 | Medium | 0 | 1 |
| 199 | -1 | 95 | volvo | turbo | four | sedan | rwd | front | 109.1 | 0.907256 | ... | 23.0 | 106.0 | 4800.0 | 26 | 27 | 22470.0 | 9.038462 | Medium | 1 | 0 |
| 200 | -1 | 95 | volvo | turbo | four | sedan | rwd | front | 109.1 | 0.907256 | ... | 9.5 | 114.0 | 5400.0 | 19 | 25 | 22625.0 | 12.368421 | Medium | 0 | 1 |
5 rows × 29 columns
In [336]:
df.columns
Out[336]:
Index(['symboling', 'normalized-losses', 'make', 'aspiration', 'num-of-doors',
'body-style', 'drive-wheels', 'engine-location', 'wheel-base', 'length',
'width', 'height', 'curb-weight', 'engine-type', 'num-of-cylinders',
'engine-size', 'fuel-system', 'bore', 'stroke', 'compression-ratio',
'horsepower', 'peak-rpm', 'city-mpg', 'highway-mpg', 'price',
'city-L/100km', 'horsepower-binned', 'diesel', 'gas'],
dtype='object')
In [337]:
df.info()
<class 'pandas.core.frame.DataFrame'> RangeIndex: 201 entries, 0 to 200 Data columns (total 29 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 symboling 201 non-null int64 1 normalized-losses 201 non-null int64 2 make 201 non-null object 3 aspiration 201 non-null object 4 num-of-doors 201 non-null object 5 body-style 201 non-null object 6 drive-wheels 201 non-null object 7 engine-location 201 non-null object 8 wheel-base 201 non-null float64 9 length 201 non-null float64 10 width 201 non-null float64 11 height 201 non-null float64 12 curb-weight 201 non-null int64 13 engine-type 201 non-null object 14 num-of-cylinders 201 non-null object 15 engine-size 201 non-null int64 16 fuel-system 201 non-null object 17 bore 201 non-null float64 18 stroke 201 non-null float64 19 compression-ratio 201 non-null float64 20 horsepower 201 non-null float64 21 peak-rpm 201 non-null float64 22 city-mpg 201 non-null int64 23 highway-mpg 201 non-null int64 24 price 201 non-null float64 25 city-L/100km 201 non-null float64 26 horsepower-binned 201 non-null object 27 diesel 201 non-null int64 28 gas 201 non-null int64 dtypes: float64(11), int64(8), object(10) memory usage: 45.7+ KB
In [338]:
df[["symboling","normalized-losses","horsepower","stroke",'wheel-base',
'engine-size', 'fuel-system', 'bore', 'stroke', 'compression-ratio',
'horsepower', 'peak-rpm', 'city-mpg', 'highway-mpg', 'price',
'city-L/100km', 'diesel', 'gas']].mean()
/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:4: FutureWarning: Dropping of nuisance columns in DataFrame reductions (with 'numeric_only=None') is deprecated; in a future version this will raise TypeError. Select only valid columns before calling the reduction. after removing the cwd from sys.path.
Out[338]:
symboling 0.840796 normalized-losses 122.000000 horsepower 103.405534 stroke 3.192090 wheel-base 98.797015 engine-size 126.875622 bore 3.330692 stroke 3.192090 compression-ratio 10.164279 horsepower 103.405534 peak-rpm 5117.665368 city-mpg 25.179104 highway-mpg 30.686567 price 13207.129353 city-L/100km 9.944145 diesel 0.099502 gas 0.900498 dtype: float64
In [339]:
df[["symboling","normalized-losses","horsepower","stroke",'wheel-base',
'engine-size', 'fuel-system', 'bore', 'stroke', 'compression-ratio',
'horsepower', 'peak-rpm', 'city-mpg', 'highway-mpg', 'price',
'city-L/100km', 'diesel', 'gas']].max()
Out[339]:
symboling 3 normalized-losses 256 horsepower 262.0 stroke 4.17 wheel-base 120.9 engine-size 326 fuel-system spfi bore 3.94 stroke 4.17 compression-ratio 23.0 horsepower 262.0 peak-rpm 6600.0 city-mpg 49 highway-mpg 54 price 45400.0 city-L/100km 18.076923 diesel 1 gas 1 dtype: object
In [340]:
df[["symboling","normalized-losses","horsepower","stroke",'wheel-base', 'length',
'width', 'height', 'curb-weight','engine-size', 'fuel-system', 'bore', 'stroke', 'compression-ratio',
'horsepower', 'peak-rpm', 'city-mpg', 'highway-mpg', 'price',
'city-L/100km', 'diesel', 'gas']].median()
/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:4: FutureWarning: Dropping of nuisance columns in DataFrame reductions (with 'numeric_only=None') is deprecated; in a future version this will raise TypeError. Select only valid columns before calling the reduction. after removing the cwd from sys.path.
Out[340]:
symboling 1.000000 normalized-losses 122.000000 horsepower 95.000000 stroke 3.290000 wheel-base 97.000000 length 0.832292 width 0.909722 height 54.100000 curb-weight 2414.000000 engine-size 120.000000 bore 3.310000 stroke 3.290000 compression-ratio 9.000000 horsepower 95.000000 peak-rpm 5125.369458 city-mpg 24.000000 highway-mpg 30.000000 price 10295.000000 city-L/100km 9.791667 diesel 0.000000 gas 1.000000 dtype: float64
In [341]:
df[["symboling","normalized-losses","horsepower","stroke",'wheel-base',
'engine-size', 'fuel-system', 'bore', 'stroke', 'compression-ratio',
'horsepower', 'peak-rpm', 'city-mpg', 'highway-mpg', 'price',
'city-L/100km', 'diesel', 'gas']].min()
Out[341]:
symboling -2 normalized-losses 65 horsepower 48.0 stroke 0.0 wheel-base 86.6 engine-size 61 fuel-system 1bbl bore 2.54 stroke 0.0 compression-ratio 7.0 horsepower 48.0 peak-rpm 4150.0 city-mpg 13 highway-mpg 16 price 5118.0 city-L/100km 4.795918 diesel 0 gas 0 dtype: object
In [342]:
df[["symboling","normalized-losses","horsepower","stroke",'wheel-base',
'engine-size', 'fuel-system', 'bore', 'stroke', 'compression-ratio',
'horsepower', 'peak-rpm', 'city-mpg', 'highway-mpg', 'price',
'city-L/100km', 'diesel', 'gas']].std()
/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:4: FutureWarning: Dropping of nuisance columns in DataFrame reductions (with 'numeric_only=None') is deprecated; in a future version this will raise TypeError. Select only valid columns before calling the reduction. after removing the cwd from sys.path.
Out[342]:
symboling 1.254802 normalized-losses 31.996250 horsepower 37.365700 stroke 0.554809 wheel-base 6.066366 engine-size 41.546834 bore 0.268072 stroke 0.554809 compression-ratio 4.004965 horsepower 37.365700 peak-rpm 478.113805 city-mpg 6.423220 highway-mpg 6.815150 price 7947.066342 city-L/100km 2.534599 diesel 0.300083 gas 0.300083 dtype: float64
In [343]:
# df[["symboling","normalized-losses","horsepower","stroke",'wheel-base',
# 'engine-size', 'fuel-system', 'bore', 'stroke', 'compression-ratio',
# 'horsepower', 'peak-rpm', 'city-mpg', 'highway-mpg', 'price',
# 'city-L/100km', 'diesel', 'gas']].median_low()
import statistics as st
print(st.median_low(df['price']))
print(st.median_low(df['normalized-losses']))
print(st.median_low(df['horsepower']))
print(st.median_low(df['engine-size']))
print(st.median_low(df['peak-rpm']))
print(st.median_low(df['city-mpg']))
print(st.median_low(df['city-L/100km']))
10295.0 122 95.0 120 5125.369458128079 24 9.791666666666666
In [344]:
print(st.median_high(df['price']))
print(st.median_high(df['normalized-losses']))
print(st.median_high(df['horsepower']))
print(st.median_high(df['engine-size']))
print(st.median_high(df['peak-rpm']))
print(st.median_high(df['city-mpg']))
print(st.median_high(df['city-L/100km']))
10295.0 122 95.0 120 5125.369458128079 24 9.791666666666666
variance() This returns the variance of the sample. This is the second moment about the mean and a larger value denotes a rather spread-out set of data. You can use this when your data is a sample out of a population.
In [345]:
print(st.variance(df['price']))
print(st.variance(df['normalized-losses']))
print(st.variance(df['horsepower']))
print(st.variance(df['engine-size']))
print(st.variance(df['peak-rpm']))
print(st.variance(df['city-mpg']))
print(st.variance(df['city-L/100km']))
63155863.44318408 1023.76 1396.1954992817223 1726.1394527363184 228592.81055048955 41.257761194029854 6.424193415078366
pvariance() This returns the population variance of data. Use this to calculate variance from an entire population.
In [346]:
print(st.pvariance(df['price']))
print(st.pvariance(df['normalized-losses']))
print(st.pvariance(df['horsepower']))
print(st.pvariance(df['engine-size']))
print(st.pvariance(df['peak-rpm']))
print(st.pvariance(df['city-mpg']))
print(st.pvariance(df['city-L/100km']))
62841655.16734734 1018.6666666666666 1389.2492530166392 1717.5516942649933 227455.53288605926 41.05249870052722 6.392232253809319
stdev() This returns the standard deviation for the sample. This is equal to the square root of the sample variance.
In [347]:
print(st.stdev(df['price']))
print(st.stdev(df['normalized-losses']))
print(st.stdev(df['horsepower']))
print(st.stdev(df['engine-size']))
print(st.stdev(df['peak-rpm']))
print(st.stdev(df['city-mpg']))
print(st.stdev(df['city-L/100km']))
7947.066341939274 31.996249780247684 37.3656995021065 41.54683444904459 478.1138050197772 6.423220469050541 2.5345992612400026
pstdev() This returns the population standard deviation. This is the square root of population variance.
In [348]:
print(st.pstdev(df['price']))
print(st.pstdev(df['normalized-losses']))
print(st.pstdev(df['horsepower']))
print(st.pstdev(df['engine-size']))
print(st.pstdev(df['peak-rpm']))
print(st.pstdev(df['city-mpg']))
print(st.pstdev(df['city-L/100km']))
7927.272870751161 31.91655787622886 37.27263410354357 41.4433552486402 476.92298422917224 6.4072223857555635 2.5282864263784117
skew
In [349]:
df.skew()
/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:1: FutureWarning: Dropping of nuisance columns in DataFrame reductions (with 'numeric_only=None') is deprecated; in a future version this will raise TypeError. Select only valid columns before calling the reduction. """Entry point for launching an IPython kernel.
Out[349]:
symboling 0.197370 normalized-losses 0.846546 wheel-base 1.031261 length 0.154446 width 0.875029 height 0.029173 curb-weight 0.705804 engine-size 1.979144 bore -0.032730 stroke -3.860477 compression-ratio 2.584462 horsepower 1.146517 peak-rpm 0.107770 city-mpg 0.680433 highway-mpg 0.549507 price 1.809675 city-L/100km 0.592383 diesel 2.696072 gas -2.696072 dtype: float64
In [350]:
df.describe()
Out[350]:
| symboling | normalized-losses | wheel-base | length | width | height | curb-weight | engine-size | bore | stroke | compression-ratio | horsepower | peak-rpm | city-mpg | highway-mpg | price | city-L/100km | diesel | gas | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| count | 201.000000 | 201.00000 | 201.000000 | 201.000000 | 201.000000 | 201.000000 | 201.000000 | 201.000000 | 201.000000 | 201.000000 | 201.000000 | 201.000000 | 201.000000 | 201.000000 | 201.000000 | 201.000000 | 201.000000 | 201.000000 | 201.000000 |
| mean | 0.840796 | 122.00000 | 98.797015 | 0.837102 | 0.915126 | 53.766667 | 2555.666667 | 126.875622 | 3.330692 | 3.192090 | 10.164279 | 103.405534 | 5117.665368 | 25.179104 | 30.686567 | 13207.129353 | 9.944145 | 0.099502 | 0.900498 |
| std | 1.254802 | 31.99625 | 6.066366 | 0.059213 | 0.029187 | 2.447822 | 517.296727 | 41.546834 | 0.268072 | 0.554809 | 4.004965 | 37.365700 | 478.113805 | 6.423220 | 6.815150 | 7947.066342 | 2.534599 | 0.300083 | 0.300083 |
| min | -2.000000 | 65.00000 | 86.600000 | 0.678039 | 0.837500 | 47.800000 | 1488.000000 | 61.000000 | 2.540000 | 0.000000 | 7.000000 | 48.000000 | 4150.000000 | 13.000000 | 16.000000 | 5118.000000 | 4.795918 | 0.000000 | 0.000000 |
| 25% | 0.000000 | 101.00000 | 94.500000 | 0.801538 | 0.890278 | 52.000000 | 2169.000000 | 98.000000 | 3.150000 | 3.100000 | 8.600000 | 70.000000 | 4800.000000 | 19.000000 | 25.000000 | 7775.000000 | 7.833333 | 0.000000 | 1.000000 |
| 50% | 1.000000 | 122.00000 | 97.000000 | 0.832292 | 0.909722 | 54.100000 | 2414.000000 | 120.000000 | 3.310000 | 3.290000 | 9.000000 | 95.000000 | 5125.369458 | 24.000000 | 30.000000 | 10295.000000 | 9.791667 | 0.000000 | 1.000000 |
| 75% | 2.000000 | 137.00000 | 102.400000 | 0.881788 | 0.925000 | 55.500000 | 2926.000000 | 141.000000 | 3.580000 | 3.410000 | 9.400000 | 116.000000 | 5500.000000 | 30.000000 | 34.000000 | 16500.000000 | 12.368421 | 0.000000 | 1.000000 |
| max | 3.000000 | 256.00000 | 120.900000 | 1.000000 | 1.000000 | 59.800000 | 4066.000000 | 326.000000 | 3.940000 | 4.170000 | 23.000000 | 262.000000 | 6600.000000 | 49.000000 | 54.000000 | 45400.000000 | 18.076923 | 1.000000 | 1.000000 |
In [351]:
print(df.describe(include=['object']))
make aspiration num-of-doors body-style drive-wheels \
count 201 201 201 201 201
unique 22 2 2 5 3
top toyota std four sedan fwd
freq 32 165 115 94 118
engine-location engine-type num-of-cylinders fuel-system \
count 201 201 201 201
unique 2 6 7 8
top front ohc four mpfi
freq 198 145 157 92
horsepower-binned
count 201
unique 4
top Low
freq 115
In [352]:
plt.figure(figsize=(8,7))
sns.distplot(df['price'])
plt.title("Distribution plot for price:")
sns.catplot(x="price", y="make",
kind="violin", data=df, height=12);
plt.title("Distribution plot for price:")
/usr/local/lib/python3.7/dist-packages/seaborn/distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms). warnings.warn(msg, FutureWarning)
Out[352]:
Text(0.5, 1.0, 'Distribution plot for price:')
In [353]:
plt.figure(figsize=(8,7))
sns.distplot(df['normalized-losses'])
plt.title("Distribution plot for normalized-losses:")
sns.catplot(x="normalized-losses", y="make",
kind="violin", data=df, height=12);
plt.title("Distribution plot for normalized-losses:")
/usr/local/lib/python3.7/dist-packages/seaborn/distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms). warnings.warn(msg, FutureWarning)
Out[353]:
Text(0.5, 1.0, 'Distribution plot for normalized-losses:')
In [354]:
plt.figure(figsize=(8,7))
sns.distplot(df['curb-weight'])
plt.title("Distribution plot for curb-weight:")
sns.catplot(x="curb-weight", y="make",
kind="violin", data=df, height=12);
plt.title("Distribution plot for curb-weight:")
/usr/local/lib/python3.7/dist-packages/seaborn/distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms). warnings.warn(msg, FutureWarning)
Out[354]:
Text(0.5, 1.0, 'Distribution plot for curb-weight:')
In [355]:
plt.figure(figsize=(8,7))
sns.distplot(df['engine-size'])
plt.title("Distribution plot for engine-size:")
sns.catplot(x="engine-size", y="make",
kind="violin", data=df, height=12);
plt.title("Distribution plot for engine-size:")
/usr/local/lib/python3.7/dist-packages/seaborn/distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms). warnings.warn(msg, FutureWarning)
Out[355]:
Text(0.5, 1.0, 'Distribution plot for engine-size:')
In [356]:
plt.figure(figsize=(8,7))
sns.distplot(df['compression-ratio'])
plt.title("Distribution plot for compression-ratio:")
sns.catplot(x="compression-ratio", y="make",
kind="violin", data=df, height=12);
plt.title("Distribution plot for compression-ratio:")
/usr/local/lib/python3.7/dist-packages/seaborn/distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms). warnings.warn(msg, FutureWarning)
Out[356]:
Text(0.5, 1.0, 'Distribution plot for compression-ratio:')
In [357]:
plt.figure(figsize=(8,7))
sns.distplot(df['horsepower'])
plt.title("Distribution plot for horsepower:")
sns.catplot(x="horsepower", y="make",
kind="violin", data=df, height=12);
plt.title("Distribution plot for horsepower:")
/usr/local/lib/python3.7/dist-packages/seaborn/distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms). warnings.warn(msg, FutureWarning)
Out[357]:
Text(0.5, 1.0, 'Distribution plot for horsepower:')
In [358]:
plt.figure(figsize=(8,7))
sns.distplot(df['peak-rpm'])
plt.title("Distribution plot for peak-rpm:")
sns.catplot(x="peak-rpm", y="make",
kind="violin", data=df, height=12);
plt.title("Distribution plot for peak-rpm:")
/usr/local/lib/python3.7/dist-packages/seaborn/distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms). warnings.warn(msg, FutureWarning)
Out[358]:
Text(0.5, 1.0, 'Distribution plot for peak-rpm:')
In [359]:
plt.figure(figsize=(8,7))
sns.distplot(df['city-mpg'])
plt.title("Distribution plot for city-mpg:")
sns.catplot(x="city-mpg", y="make",
kind="violin", data=df, height=12);
plt.title("Distribution plot for price:")
/usr/local/lib/python3.7/dist-packages/seaborn/distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms). warnings.warn(msg, FutureWarning)
Out[359]:
Text(0.5, 1.0, 'Distribution plot for price:')
In [360]:
plt.figure(figsize=(8,7))
sns.distplot(df['city-L/100km'])
plt.title("Distribution plot for city-L/100km :")
sns.catplot(x="city-L/100km", y="make",
kind="violin", data=df, height=12);
plt.title("Distribution plot for city-L/100km:")
/usr/local/lib/python3.7/dist-packages/seaborn/distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms). warnings.warn(msg, FutureWarning)
Out[360]:
Text(0.5, 1.0, 'Distribution plot for city-L/100km:')
In [361]:
plt.figure(figsize=(8,7))
sns.distplot(df['diesel'])
plt.title("Distribution plot for diesel:")
sns.catplot(x="diesel", y="make",
kind="violin", data=df, height=12);
plt.title("Distribution plot for diesel:")
/usr/local/lib/python3.7/dist-packages/seaborn/distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms). warnings.warn(msg, FutureWarning)
Out[361]:
Text(0.5, 1.0, 'Distribution plot for diesel:')
In [362]:
plt.figure(figsize=(8,7))
sns.distplot(df['gas'])
plt.title("Distribution plot for gas:")
sns.catplot(x="gas", y="make",
kind="violin", data=df, height=12);
plt.title("Distribution plot for gas:")
/usr/local/lib/python3.7/dist-packages/seaborn/distributions.py:2619: FutureWarning: `distplot` is a deprecated function and will be removed in a future version. Please adapt your code to use either `displot` (a figure-level function with similar flexibility) or `histplot` (an axes-level function for histograms). warnings.warn(msg, FutureWarning)
Out[362]:
Text(0.5, 1.0, 'Distribution plot for gas:')
In [363]:
plt.figure(figsize=(15,7))
sns.boxplot(x = "price", data = df, showmeans=True)
plt.title("Boxplot for Price")
plt.show()
In [364]:
plt.figure(figsize=(15,7))
sns.boxplot(x = "normalized-losses", data = df, showmeans=True)
plt.title("Boxplot for normalized-losses")
plt.show()
In [365]:
plt.figure(figsize=(15,7))
sns.boxplot(x = "curb-weight", data = df, showmeans=True)
plt.title("Boxplot for curb-weight")
plt.show()
In [366]:
plt.figure(figsize=(15,7))
sns.boxplot(x = "engine-size", data = df, showmeans=True)
plt.title("Boxplot for engine-size")
plt.show()
In [367]:
plt.figure(figsize=(15,7))
sns.boxplot(x = "horsepower", data = df, showmeans=True)
plt.title("Boxplot for horsepower")
plt.show()
In [368]:
plt.figure(figsize=(15,7))
sns.boxplot(x = "compression-ratio", data = df, showmeans=True)
plt.title("Boxplot for compression-ratio")
plt.show()
In [369]:
plt.figure(figsize=(15,7))
sns.boxplot(x = "city-mpg", data = df, showmeans=True)
plt.title("Boxplot for city-mpg")
plt.show()
In [370]:
plt.figure(figsize=(15,7))
sns.boxplot(x = "city-L/100km", data = df, showmeans=True)
plt.title("Boxplot for city-L/100km")
plt.show()
In [371]:
plt.figure(figsize=(15,7))
sns.boxplot(x = "diesel", data = df, showmeans=True)
plt.title("Boxplot for diesel")
plt.show()
In [372]:
plt.figure(figsize=(15,7))
sns.boxplot(x = "gas", data = df, showmeans=True)
plt.title("Boxplot for gas")
plt.show()
In [373]:
correlation = df.corr().round(2) # creating a 2-D Matrix with correlation plots
correlation
plt.figure(figsize = (15,8)) #figsize=(width,height)
sns.heatmap(correlation, annot=True, cmap='vlag_r', vmin=-1, vmax=1)
Out[373]:
<matplotlib.axes._subplots.AxesSubplot at 0x7fd6721c8310>
In [373]:
In [374]:
plt.figure(figsize=(7,5))
plt.hist(df["city-mpg"])
Out[374]:
(array([11., 45., 24., 56., 18., 31., 13., 0., 1., 2.]), array([13. , 16.6, 20.2, 23.8, 27.4, 31. , 34.6, 38.2, 41.8, 45.4, 49. ]), <a list of 10 Patch objects>)
In [375]:
pair=df[["horsepower","price","normalized-losses","engine-size","peak-rpm","city-mpg","highway-mpg","wheel-base","city-L/100km","make","aspiration","num-of-doors","body-style","engine-type"]]
In [376]:
print(df["aspiration"].unique())
print(df["num-of-doors"].unique())
print(df["body-style"].unique())
print(df["engine-type"].unique())
print(df["make"].unique())
print(df["horsepower-binned"].unique())
['std' 'turbo'] ['two' 'four'] ['convertible' 'hatchback' 'sedan' 'wagon' 'hardtop'] ['dohc' 'ohcv' 'ohc' 'l' 'rotor' 'ohcf'] ['alfa-romero' 'audi' 'bmw' 'chevrolet' 'dodge' 'honda' 'isuzu' 'jaguar' 'mazda' 'mercedes-benz' 'mercury' 'mitsubishi' 'nissan' 'peugot' 'plymouth' 'porsche' 'renault' 'saab' 'subaru' 'toyota' 'volkswagen' 'volvo'] ['Medium' 'Low' 'High' 0]
In [377]:
sns.pairplot(pair, hue ='make')
plt.show()
In [378]:
sns.pairplot(pair, hue ='aspiration')
plt.show()
In [379]:
sns.pairplot(pair, hue ="num-of-doors")
plt.show()
In [380]:
sns.pairplot(pair, hue ="engine-type")
plt.show()
In [381]:
df.hist(figsize=(15,15))
df.plot(kind='box',layout=(6,5),subplots=True,sharex=False,sharey=False,figsize=(15,15))
Out[381]:
symboling AxesSubplot(0.125,0.772143;0.133621x0.107857) normalized-losses AxesSubplot(0.285345,0.772143;0.133621x0.107857) wheel-base AxesSubplot(0.44569,0.772143;0.133621x0.107857) length AxesSubplot(0.606034,0.772143;0.133621x0.107857) width AxesSubplot(0.766379,0.772143;0.133621x0.107857) height AxesSubplot(0.125,0.642714;0.133621x0.107857) curb-weight AxesSubplot(0.285345,0.642714;0.133621x0.107857) engine-size AxesSubplot(0.44569,0.642714;0.133621x0.107857) bore AxesSubplot(0.606034,0.642714;0.133621x0.107857) stroke AxesSubplot(0.766379,0.642714;0.133621x0.107857) compression-ratio AxesSubplot(0.125,0.513286;0.133621x0.107857) horsepower AxesSubplot(0.285345,0.513286;0.133621x0.107857) peak-rpm AxesSubplot(0.44569,0.513286;0.133621x0.107857) city-mpg AxesSubplot(0.606034,0.513286;0.133621x0.107857) highway-mpg AxesSubplot(0.766379,0.513286;0.133621x0.107857) price AxesSubplot(0.125,0.383857;0.133621x0.107857) city-L/100km AxesSubplot(0.285345,0.383857;0.133621x0.107857) diesel AxesSubplot(0.44569,0.383857;0.133621x0.107857) gas AxesSubplot(0.606034,0.383857;0.133621x0.107857) dtype: object
