In [ ]:

import os

In [ ]:

os.environ['KAGGLE_CONFIG_DIR'] = "/content/drive/MyDrive/kaggle"

In [ ]:

!kaggle datasets download -d CooperUnion/cardataset

Downloading cardataset.zip to /content
  0% 0.00/103k [00:00<?, ?B/s]
100% 103k/103k [00:00<00:00, 33.2MB/s]

In [ ]:

!cd drive/MyDrive/kaggle

In [ ]:

!kaggle datasets download -d CooperUnion/cardataset --force

Downloading cardataset.zip to /content/drive/MyDrive/kaggle
  0% 0.00/103k [00:00<?, ?B/s]
100% 103k/103k [00:00<00:00, 13.7MB/s]

In [ ]:

!ls

cardataset.zip	data.csv  kaggle.json

In [ ]:

import numpy as np
import pandas as pd
from matplotlib import pyplot as plt
import seaborn as sns
%matplotlib inline

In [ ]:

df = pd.read_csv("data.csv")

In [ ]:

df.head()

Out[ ]:

	Make	Model	Year	Engine Fuel Type	Engine HP	Engine Cylinders	Transmission Type	Driven_Wheels	Number of Doors	Market Category	Vehicle Size	Vehicle Style	highway MPG	city mpg	Popularity	MSRP
0	BMW	1 Series M	2011	premium unleaded (required)	335.0	6.0	MANUAL	rear wheel drive	2.0	Factory Tuner,Luxury,High-Performance	Compact	Coupe	26	19	3916	46135
1	BMW	1 Series	2011	premium unleaded (required)	300.0	6.0	MANUAL	rear wheel drive	2.0	Luxury,Performance	Compact	Convertible	28	19	3916	40650
2	BMW	1 Series	2011	premium unleaded (required)	300.0	6.0	MANUAL	rear wheel drive	2.0	Luxury,High-Performance	Compact	Coupe	28	20	3916	36350
3	BMW	1 Series	2011	premium unleaded (required)	230.0	6.0	MANUAL	rear wheel drive	2.0	Luxury,Performance	Compact	Coupe	28	18	3916	29450
4	BMW	1 Series	2011	premium unleaded (required)	230.0	6.0	MANUAL	rear wheel drive	2.0	Luxury	Compact	Convertible	28	18	3916	34500

In [ ]:

df.columns = df.columns.str.lower().str.replace(' ', '_')
 string_coloumns = list(df.dtypes[df.dtypes == 'object'].index)
 for col in string_coloumns:
   df[col] = df[col].str.lower().str.replace(' ',' ')

In [ ]:

string_coloumns

Out[ ]:

['make',
 'model',
 'engine_fuel_type',
 'transmission_type',
 'driven_wheels',
 'market_category',
 'vehicle_size',
 'vehicle_style']

In [ ]:

df.head()

Out[ ]:

	make	model	year	engine_fuel_type	engine_hp	engine_cylinders	transmission_type	driven_wheels	number_of_doors	market_category	vehicle_size	vehicle_style	highway_mpg	city_mpg	popularity	msrp
0	bmw	1 series m	2011	premium unleaded (required)	335.0	6.0	manual	rear wheel drive	2.0	factory tuner,luxury,high-performance	compact	coupe	26	19	3916	46135
1	bmw	1 series	2011	premium unleaded (required)	300.0	6.0	manual	rear wheel drive	2.0	luxury,performance	compact	convertible	28	19	3916	40650
2	bmw	1 series	2011	premium unleaded (required)	300.0	6.0	manual	rear wheel drive	2.0	luxury,high-performance	compact	coupe	28	20	3916	36350
3	bmw	1 series	2011	premium unleaded (required)	230.0	6.0	manual	rear wheel drive	2.0	luxury,performance	compact	coupe	28	18	3916	29450
4	bmw	1 series	2011	premium unleaded (required)	230.0	6.0	manual	rear wheel drive	2.0	luxury	compact	convertible	28	18	3916	34500

In [ ]:

sns.distplot(df.msrp,kde = False)

/usr/local/lib/python3.7/dist-packages/seaborn/distributions.py:2557: 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[ ]:

<matplotlib.axes._subplots.AxesSubplot at 0x7f6ffb934790>

In [ ]:

sns.distplot(df.msrp[df.msrp < 100000]  ,kde = False)

/usr/local/lib/python3.7/dist-packages/seaborn/distributions.py:2557: 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[ ]:

<matplotlib.axes._subplots.AxesSubplot at 0x7f6ff1073490>

In [ ]:

log_price = np.log1p(df.msrp)

In [ ]:

sns.distplot(log_price, kde=False)

/usr/local/lib/python3.7/dist-packages/seaborn/distributions.py:2557: 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[ ]:

<matplotlib.axes._subplots.AxesSubplot at 0x7f6ff183b950>

In [ ]:

df.isnull().sum()

Out[ ]:

make                    0
model                   0
year                    0
engine_fuel_type        3
engine_hp              69
engine_cylinders       30
transmission_type       0
driven_wheels           0
number_of_doors         6
market_category      3742
vehicle_size            0
vehicle_style           0
highway_mpg             0
city_mpg                0
popularity              0
msrp                    0
dtype: int64

In [ ]:

n = len(df)

n_test = int(n*0.2)
n_val = int(n*2)
n_train = n - (n_test + n_val)

np.random.seed(2)
idx = np.arange(n)
np.random.shuffle(idx)

df_shuffled = df.iloc[idx]
df_train = df_shuffled[:n_train].copy()
df_val = df_shuffled[n_train:n_train + n_val].copy() 
df_test = df_shuffled[n_train + n_val:].copy()

In [ ]:

y_train = np.log1p(df_train.msrp.values)
y_val = np.log1p(df_val.msrp.values)
y_test = np.log1p(df_test.msrp.values)

To avoid accidentally using the target variable later, let’s remove it from the dataframes:

In [ ]:

del df_train['msrp']
del df_val['msrp']
del df_test['msrp']

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/pandas/core/indexes/base.py in get_loc(self, key, method, tolerance)
   2897             try:
-> 2898                 return self._engine.get_loc(casted_key)
   2899             except KeyError as err:

pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()

pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()

pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()

pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item()

KeyError: 'msrp'

The above exception was the direct cause of the following exception:

KeyError                                  Traceback (most recent call last)
<ipython-input-63-c51c5c6c90df> in <module>()
----> 1 del df_train['msrp']
      2 del df_val['msrp']
      3 del df_test['msrp']

/usr/local/lib/python3.7/dist-packages/pandas/core/generic.py in __delitem__(self, key)
   3711             # there was no match, this call should raise the appropriate
   3712             # exception:
-> 3713             loc = self.axes[-1].get_loc(key)
   3714             self._mgr.idelete(loc)
   3715 

/usr/local/lib/python3.7/dist-packages/pandas/core/indexes/base.py in get_loc(self, key, method, tolerance)
   2898                 return self._engine.get_loc(casted_key)
   2899             except KeyError as err:
-> 2900                 raise KeyError(key) from err
   2901 
   2902         if tolerance is not None:

KeyError: 'msrp'

In [ ]:

/content/result.csv

NeurIPS 2020: Procgen Competition

bookcamp

Content

Comments