Bulldozer Price : Regression

import numpy as np # linear algebra import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv) import matplotlib.pyplot as plt import seaborn as sns

df = pd.read_csv('./TrainAndValid.csv', low_memory=False)

df.head()

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 412698 entries, 0 to 412697
Data columns (total 53 columns):
 #   Column                    Non-Null Count   Dtype  
---  ------                    --------------   -----  
 0   SalesID                   412698 non-null  int64  
 1   SalePrice                 412698 non-null  float64
 2   MachineID                 412698 non-null  int64  
 3   ModelID                   412698 non-null  int64  
 4   datasource                412698 non-null  int64  
 5   auctioneerID              392562 non-null  float64
 6   YearMade                  412698 non-null  int64  
 7   MachineHoursCurrentMeter  147504 non-null  float64
 8   UsageBand                 73670 non-null   object 
 9   saledate                  412698 non-null  object 
 10  fiModelDesc               412698 non-null  object 
 11  fiBaseModel               412698 non-null  object 
 12  fiSecondaryDesc           271971 non-null  object 
 13  fiModelSeries             58667 non-null   object 
 14  fiModelDescriptor         74816 non-null   object 
 15  ProductSize               196093 non-null  object 
 16  fiProductClassDesc        412698 non-null  object 
 17  state                     412698 non-null  object 
 18  ProductGroup              412698 non-null  object 
 19  ProductGroupDesc          412698 non-null  object 
 20  Drive_System              107087 non-null  object 
 21  Enclosure                 412364 non-null  object 
 22  Forks                     197715 non-null  object 
 23  Pad_Type                  81096 non-null   object 
 24  Ride_Control              152728 non-null  object 
 25  Stick                     81096 non-null   object 
 26  Transmission              188007 non-null  object 
 27  Turbocharged              81096 non-null   object 
 28  Blade_Extension           25983 non-null   object 
 29  Blade_Width               25983 non-null   object 
 30  Enclosure_Type            25983 non-null   object 
 31  Engine_Horsepower         25983 non-null   object 
 32  Hydraulics                330133 non-null  object 
 33  Pushblock                 25983 non-null   object 
 34  Ripper                    106945 non-null  object 
 35  Scarifier                 25994 non-null   object 
 36  Tip_Control               25983 non-null   object 
 37  Tire_Size                 97638 non-null   object 
 38  Coupler                   220679 non-null  object 
 39  Coupler_System            44974 non-null   object 
 40  Grouser_Tracks            44875 non-null   object 
 41  Hydraulics_Flow           44875 non-null   object 
 42  Track_Type                102193 non-null  object 
 43  Undercarriage_Pad_Width   102916 non-null  object 
 44  Stick_Length              102261 non-null  object 
 45  Thumb                     102332 non-null  object 
 46  Pattern_Changer           102261 non-null  object 
 47  Grouser_Type              102193 non-null  object 
 48  Backhoe_Mounting          80712 non-null   object 
 49  Blade_Type                81875 non-null   object 
 50  Travel_Controls           81877 non-null   object 
 51  Differential_Type         71564 non-null   object 
 52  Steering_Controls         71522 non-null   object 
dtypes: float64(3), int64(5), object(45)
memory usage: 166.9+ MB

fig, ax = plt.subplots() ax.scatter(df['saledate'][:1000], df["SalePrice"][:1000])

df.saledate[:1000]

df.saledate.dtype

df.SalePrice.plot.hist()

df = pd.read_csv('./TrainAndValid.csv', low_memory=False, parse_dates=["saledate"]) df.saledate.dtype

df['saledate'][:1000]

fig, ax = plt.subplots() ax.scatter(df['saledate'][:1000], df['SalePrice'][:1000])

df.head()

df.head().T

df.saledate.head(20)

df.sort_values(by=["saledate"], inplace=True,ascending=True) df.saledate.head(20)

## Make a copy of the original DataFrame df_tmp = df.copy()

## Add datetime parameter for saledate column df_tmp["SaleYear"] = df_tmp.saledate.dt.year df_tmp["SaleMonth"] = df_tmp.saledate.dt.month df_tmp["SaleDay"] = df_tmp.saledate.dt.day df_tmp["SaleDayOfWeek"] = df_tmp.saledate.dt.dayofweek df_tmp["SaleDayOfYear"] = df_tmp.saledate.dt.dayofyear

df_tmp.head().T

# Now we enriched out DataFrame df_tmp.drop("saledate", axis=1, inplace=True)

df_tmp.state.value_counts()

len(df_tmp)

df_tmp.head()

from sklearn.ensemble import RandomForestRegressor model = RandomForestRegressor(n_jobs=1, random_state=42) model.fit(df_tmp.drop("SalePrice", axis=1), df_tmp["SalePrice"])

There’s an error in this block

Try running the app again, or contact the app’s creator

df_tmp.info()