We Keep Coding

Convert `DataFrame.groupby()` into dictionary (and then reverse it)

Say I have the following DataFrame() where I have repeated observations per individual (column id_ind). Hence, first two rows belong the first individual, the third and fourth rows belong to the second individual, and so forth...
import pandas as pd
X = pd.DataFrame.from_dict({'x1_1': {0: -0.1766214634108258, 1: 1.645852185286492, 2: -0.13348860101031038, 3: 1.9681043689968933, 4: -1.7004428240831382, 5: 1.4580091413853749, 6: 0.06504113741068565, 7: -1.2168493676768384, 8: -0.3071304478616376, 9: 0.07121332925591593}, 'x1_2': {0: -2.4207773498298844, 1: -1.0828751040719462, 2: 2.73533787008624, 3: 1.5979611987152071, 4: 0.08835542172064115, 5: 1.2209786277076156, 6: -0.44205979195950784, 7: -0.692872860268244, 8: 0.0375521181289943, 9: 0.4656030062266639}, 'x1_3': {0: -1.548320898226322, 1: 0.8457342014424675, 2: -0.21250514722879738, 3: 0.5292389938329516, 4: -2.593946520223666, 5: -0.6188958526077123, 6: 1.6949245117526974, 7: -1.0271341091035742, 8: 0.637561891142571, 9: -0.7717170035055559}, 'x2_1': {0: 0.3797245517345564, 1: -2.2364391598508835, 2: 0.6205947900678905, 3: 0.6623865847688559, 4: 1.562036259999875, 5: -0.13081282910947759, 6: 0.03914373833251773, 7: -0.995761652421108, 8: 1.0649494418154162, 9: 1.3744782478849122}, 'x2_2': {0: -0.5052556836786106, 1: 1.1464291788297152, 2: -0.5662380273138174, 3: 0.6875729143723538, 4: 0.04653136473130827, 5: -0.012885303852347407, 6: 1.5893672346098884, 7: 0.5464286050059511, 8: -0.10430829457707284, 9: -0.5441755265313813}, 'x2_3': {0: -0.9762973303149007, 1: -0.983731467806563, 2: 1.465827578266328, 3: 0.5325950414202745, 4: -1.4452121324204903, 5: 0.8148816373643869, 6: 0.470791989780882, 7: -0.17951636294180473, 8: 0.7351814781280054, 9: -0.28776723200679066}, 'x3_1': {0: 0.12751822396637064, 1: -0.21926633684030983, 2: 0.15758799357206943, 3: 0.5885412224632464, 4: 0.11916562911189271, 5: -1.6436210334529249, 6: -0.12444368631987467, 7: 1.4618564171802453, 8: 0.6847234328916137, 9: -0.23177118858569187}, 'x3_2': {0: -0.6452955690715819, 1: 1.052094761527654, 2: 0.20190339195326157, 3: 0.6839430295237913, 4: -0.2607691613858866, 5: 0.3315513026670213, 6: 0.015901139336566113, 7: 0.15243420084881903, 8: -0.7604225072161022, 9: -0.4387652927008854}, 'x3_3': {0: -1.067058994377549, 1: 0.8026914180717286, 2: -1.9868531745912268, 3: -0.5057770735303253, 4: -1.6589569342151713, 5: 0.358172252880764, 6: 1.9238983803281329, 7: 2.2518318810978246, 8: -1.2781475121874357, 9: -0.7103081175166167}})
Y = pd.DataFrame.from_dict({'CHOICE': {0: 1.0, 1: 1.0, 2: 2.0, 3: 2.0, 4: 3.0, 5: 2.0, 6: 1.0, 7: 1.0, 8: 2.0, 9: 2.0}})
Z = pd.DataFrame.from_dict({'z1': {0: 2.4196730570917233, 1: 2.4196730570917233, 2: 2.822802255159467, 3: 2.822802255159467, 4: 2.073171091633643, 5: 2.073171091633643, 6: 2.044165101485163, 7: 2.044165101485163, 8: 2.4001241292606275, 9: 2.4001241292606275}, 'z2': {0: 0.0, 1: 0.0, 2: 0.0, 3: 0.0, 4: 1.0, 5: 1.0, 6: 1.0, 7: 1.0, 8: 0.0, 9: 0.0}, 'z3': {0: 1.0, 1: 1.0, 2: 1.0, 3: 1.0, 4: 2.0, 5: 2.0, 6: 2.0, 7: 2.0, 8: 3.0, 9: 3.0}})
id = pd.DataFrame.from_dict({'id_choice': {0: 1.0, 1: 2.0, 2: 3.0, 3: 4.0, 4: 5.0, 5: 6.0, 6: 7.0, 7: 8.0, 8: 9.0, 9: 10.0}, 'id_ind': {0: 1.0, 1: 1.0, 2: 2.0, 3: 2.0, 4: 3.0, 5: 3.0, 6: 4.0, 7: 4.0, 8: 5.0, 9: 5.0}} )
# Create a dataframe with all the data
data = pd.concat([id, X, Z, Y], axis=1)
print(data.head(4))
# id_choice id_ind x1_1 x1_2 x1_3 x2_1 x2_2 \
# 0 1.0 1.0 -0.176621 -2.420777 -1.548321 0.379725 -0.505256
# 1 2.0 1.0 1.645852 -1.082875 0.845734 -2.236439 1.146429
# 2 3.0 2.0 -0.133489 2.735338 -0.212505 0.620595 -0.566238
# 3 4.0 2.0 1.968104 1.597961 0.529239 0.662387 0.687573
#
# x2_3 x3_1 x3_2 x3_3 z1 z2 z3 CHOICE
# 0 -0.976297 0.127518 -0.645296 -1.067059 2.419673 0.0 1.0 1.0
# 1 -0.983731 -0.219266 1.052095 0.802691 2.419673 0.0 1.0 1.0
# 2 1.465828 0.157588 0.201903 -1.986853 2.822802 0.0 1.0 2.0
# 3 0.532595 0.588541 0.683943 -0.505777 2.822802 0.0 1.0 2.0
I want to perform two operations.
First, I want to convert the DataFrame data into a dictionary of DataFrame()s where the keys are the number of individuals (in this particular case, numbers ranging from 1.0 to 5.0.). I've done this below as suggested here. Unfortunately, I am getting a dictionary of numpy values and not a dictionary of DataFrame()s.
# Create a dictionary with the data for each individual
data_dict = data.set_index('id_ind').groupby('id_ind').apply(lambda x : x.to_numpy().tolist()).to_dict()
print(data_dict.keys())
# dict_keys([1.0, 2.0, 3.0, 4.0, 5.0])
print(data_dict[1.0])
#[[1.0, -0.1766214634108258, -2.4207773498298844, -1.548320898226322, 0.3797245517345564, -0.5052556836786106, -0.9762973303149007, 0.12751822396637064, -0.6452955690715819, -1.067058994377549, 2.4196730570917233, 0.0, 1.0, 1.0], [2.0, 1.645852185286492, -1.0828751040719462, 0.8457342014424675, -2.2364391598508835, 1.1464291788297152, -0.983731467806563, -0.21926633684030983, 1.052094761527654, 0.8026914180717286, 2.4196730570917233, 0.0, 1.0, 1.0]]
Second, I want to recover the original DataFrame data reversing the previous operation. The naive approach is as follows. However, it is, of course, not producing the expected result.
# Naive approach
res = pd.DataFrame.from_dict(data_dict, orient='index')
print(res)
# 0 1
#1.0 [1.0, -0.1766214634108258, -2.4207773498298844... [2.0, 1.645852185286492, -1.0828751040719462, ...
#2.0 [3.0, -0.13348860101031038, 2.73533787008624, ... [4.0, 1.9681043689968933, 1.5979611987152071, ...
#3.0 [5.0, -1.7004428240831382, 0.08835542172064115... [6.0, 1.4580091413853749, 1.2209786277076156, ...
#4.0 [7.0, 0.06504113741068565, -0.4420597919595078... [8.0, -1.2168493676768384, -0.692872860268244,...
#5.0 [9.0, -0.3071304478616376, 0.0375521181289943,... [10.0, 0.07121332925591593, 0.4656030062266639...

This solution was inspired by #mozway comments.
# Create a dictionary with the data for each individual
data_dict = dict(list(data.groupby('id_ind')))
# Convert the dictionary into a dataframe
res = pd.concat(data_dict, axis=0).reset_index(drop=True)
print(res.head(4))
# id_choice id_ind x1_1 x1_2 x1_3 x2_1 x2_2 \
#0 1.0 1.0 -0.176621 -2.420777 -1.548321 0.379725 -0.505256
#1 2.0 1.0 1.645852 -1.082875 0.845734 -2.236439 1.146429
#2 3.0 2.0 -0.133489 2.735338 -0.212505 0.620595 -0.566238
#3 4.0 2.0 1.968104 1.597961 0.529239 0.662387 0.687573
#
# x2_3 x3_1 x3_2 x3_3 z1 z2 z3 CHOICE
#0 -0.976297 0.127518 -0.645296 -1.067059 2.419673 0.0 1.0 1.0
#1 -0.983731 -0.219266 1.052095 0.802691 2.419673 0.0 1.0 1.0
#2 1.465828 0.157588 0.201903 -1.986853 2.822802 0.0 1.0 2.0
#3 0.532595 0.588541 0.683943 -0.505777 2.822802 0.0 1.0 2.0

Bokeh: remove Hovertool from toolbar in stacked bar chart

In my stacked barchart I have specified which tools I want in the toolbar. But when I add a hovertool this seems to overwrite my command and adds a hovertool for every element in the stacked barchart. How can I remove the hovertool tool in the toolbar?
Data example:
temp=pd.DataFrame( {'bydelsnavn': {0: 'Amager Vest', 1: 'Amager Øst', 2: 'Bispebjerg', 3: 'Brønshøj-Husum', 4: 'Indre By', 5: 'Nørrebro', 6: 'Valby', 7: 'Vanløse', 8: 'Vesterbro', 9: 'Østerbro'}, 'Alder': {0: 53.0, 1: 21.0, 2: 1.0, 3: 9.0, 4: 4.0, 5: 2.0, 6: 3.0, 7: 44.0, 8: 46.0, 9: 59.0}, 'Alderm': {0: 63.0, 1: 32.0, 2: 49.0, 3: 13.0, 4: 45.0, 5: 55.0, 6: 104.0, 7: 0.0, 8: 50.0, 9: 4.0}, 'Apple': {0: 94.0, 1: 109.0, 2: 115.0, 3: 12.0, 4: 22.0, 5: 81.0, 6: 41.0, 7: 3.0, 8: 132.0, 9: 51.0}, 'Alder_p': {0: 21.9, 1: 8.68, 2: 0.41, 3: 3.72, 4: 1.65, 5: 0.83, 6: 1.24, 7: 18.18, 8: 19.01, 9: 24.38}, 'Alderm_p': {0: 15.18, 1: 7.71, 2: 11.81, 3: 3.13, 4: 10.84, 5: 13.25, 6: 25.06, 7: 0.0, 8: 12.05, 9: 0.96}, 'Apple_p': {0: 14.24, 1: 16.52, 2: 17.42, 3: 1.82, 4: 3.33, 5: 12.27, 6: 6.21, 7: 0.45, 8: 20.0, 9: 7.73}})
My code:
treeName = ['Alder','Alderm','Apple']
treeName_p = ['Alder_p','Alderm_p','Apple_p']
colornames = named.__all__
colornames = colornames[:len(treeName)]
# Create an empty figure
p = figure(x_range = temp['bydelsnavn'].values,plot_width = 700, plot_height=400,
title='Tree pr. district', toolbar_sticky = False,
tools = 'pan,wheel_zoom,reset')
# Stacked bar chart
renderers = p.vbar_stack(stackers=treeName,x='bydelsnavn',source=temp,
width=0.8, color = colornames)
# Add the hover tool
for r in renderers:
tree = r.name
hover = HoverTool(tooltips=[
("%s" % tree, "#{%s}" % tree)
], renderers = [r])
p.add_tools(hover)
# remove the grid
p.xgrid.grid_line_color=None
p.ygrid.grid_line_color=None
# Make sure bars stat at 0
p.y_range.start = 0
# remove - y-axis
p.yaxis.visible = False
# Remove the grey box around the plot
p.outline_line_color = None
# Turn the x-labels
p.xaxis.major_label_orientation = 0.5
# Remove tool bar logo
p.toolbar.logo = None
# Move the border of the left side to show "Amager"
p.min_border_left = 30
show(p)
In the picture the tools I would like to aviod are pointed out:

You can hide the tool buttons completely by passing toggleable=False to HoverTool.

plotnine/ggplot - changing legend positions

I have this dataframe:
df = pd.DataFrame({'ymin': {0: 0.0,
1: 0.0,
2: 0.0,
3: 0.0,
4: 0.511,
5: 0.571,
6: 0.5329999999999999,
7: 0.5389999999999999},
'ymax': {0: 0.511,
1: 0.571,
2: 0.533,
3: 0.539,
4: 1.0,
5: 1.0,
6: 1.0,
7: 1.0},
'xmin': {0: 0.0,
1: 0.14799999999999996,
2: 0.22400000000000003,
3: 0.5239999999999999,
4: 0.0,
5: 0.14799999999999996,
6: 0.22400000000000003,
7: 0.5239999999999999},
'xmax': {0: 0.148,
1: 0.22399999999999998,
2: 0.524,
3: 1.001,
4: 0.148,
5: 0.22399999999999998,
6: 0.524,
7: 1.001},
'variable': {0: 'A', 1: 'A', 2: 'A', 3: 'A', 4: 'B', 5: 'B', 6: 'B', 7: 'B'}})
Where I plot this:
(ggplot(df, aes(ymin = "ymin", ymax = "ymax",
xmin = "xmin", xmax = "xmax", fill = "variable"))
+ geom_rect(colour = "grey", alpha=0.7))
I'm looking to change the position of the legends to the same to the positions of the plot: blue-up and red-bottom. And A always will be red and B always will be blue

There might be a more standard way to do it, but here is a quick hack to fix your problem:
Change the order of your variable
Assign colors manually (You could also look for exact color codes and replace it with the color names if it matters in your case)
df = df.assign(variable = pd.Categorical(df['variable'], ['B', 'A']))
(ggplot(df, aes(ymin = "ymin", ymax = "ymax",
xmin = "xmin", xmax = "xmax", fill = "variable"))+
geom_rect(colour = "grey", alpha=0.7)+
scale_fill_manual(values = ["blue", "red"]))
output looks like this:

You could set order of levels with df$variable <- factor(df$variable, levels = c("B","A")

Modify plotly layout y-axis

I am working on two datasets on churn classification, my problem is as you can see below on the two graph the y-axis are not on the same scale. Bank stops at 0.8 and telco-europa at 1, I would like to force the y-axis to always display 0, 0.2, 0.4, 0.6, 0.8, 1.
I have used the following code:
and my histogram is based on this tutorial: https://www.kaggle.com/pavanraj159/telecom-customer-churn-prediction and the bank dataset is this one https://www.kaggle.com/shrutimechlearn/churn-modelling
import plotly.graph_objs as go#visualization
import plotly.offline as py#visualization
def output_tracer(metric,color, model_performances) :
tracer = go.Bar(x = model_performances["Algorithm"] ,
y = model_performances[metric],
orientation = "v",name = metric ,
marker = dict(line = dict(width =.7),
color = color)
)
return tracer
def output_data(model_performances):
trace1 = output_tracer("1-Precision","#6699FF", model_performances)
trace2 = output_tracer('1-Recall',"red", model_performances)
trace3 = output_tracer('1-F1-score',"#33CC99", model_performances)
trace4 = output_tracer('Accuracy',"lightgrey", model_performances)
trace5 = output_tracer('AUC',"#FFCC99", model_performances)
data = [trace1,trace2,trace3,trace4,trace5]
return data
def output_layout(model):
layout = go.Layout(dict(title = model,
plot_bgcolor = "rgb(243,243,243)",
paper_bgcolor = "rgb(243,243,243)",
xaxis = dict(gridcolor = 'rgb(255, 255, 255)',
title = "",
zerolinewidth=1,
ticklen=5,gridwidth=2),
yaxis = dict(gridcolor = 'rgb(255, 255, 255)',
zerolinewidth=1,ticklen=5,gridwidth=2),
margin = dict(l = 250),
height = 400
)
)
return layout
model = "Bank"
model_performances = report_df_scoring[report_df_scoring.Dataset == model]
fig = go.Figure(data=output_data(model_performances),layout=output_layout(model))
py.iplot(fig)
And here you can fin the dataframe as a dictionary "report_df_scoring" for only the "Bank" dataset
{'Dataset': {0: 'Bank',
1: 'Bank',
2: 'Bank',
3: 'Bank',
4: 'Bank',
5: 'Bank',
6: 'Bank'},
'Algorithm': {0: 'LogisticRegressionNoSMOTE',
1: 'Logistic Regression',
2: 'SVM-linear',
3: 'SVM-rbf',
4: 'xgboost',
5: 'GaussianNB',
6: 'RandomForest'},
'W-Precision': {0: 0.8159638339642141,
1: 0.8229500536388679,
2: 0.8243426658647828,
3: 0.7956512785333915,
4: 0.8288351219512194,
5: 0.8302513223140496,
6: 0.8307514249037228},
'W-Recall': {0: 0.8324,
1: 0.7636,
2: 0.7628,
3: 0.8056,
4: 0.836,
5: 0.8176,
6: 0.8408},
'W-F1-score': {0: 0.810103868755423,
1: 0.7811452562742854,
2: 0.7807117770916884,
3: 0.7997335148514852,
4: 0.831622605929424,
5: 0.7598757585104978,
6: 0.8336474053248425},
'0-Precision': {0: 0.8493518104604381,
1: 0.9187236604455148,
2: 0.9206541490006056,
3: 0.8634596695821186,
4: 0.8834146341463415,
5: 0.8152892561983471,
6: 0.8789473684210526},
'0-Recall': {0: 0.958627648839556,
1: 0.7699293642785066,
2: 0.7669021190716448,
3: 0.8965691220988901,
4: 0.9137235116044399,
5: 0.9954591321897074,
6: 0.9268415741675076},
'0-F1-score': {0: 0.9006873666745674,
1: 0.8377710678012626,
2: 0.8367740159647675,
3: 0.8797029702970298,
4: 0.8983134920634921,
5: 0.8964107223989097,
6: 0.9022593320235756},
'1-Precision': {0: 0.6882129277566539,
1: 0.4564958283671037,
2: 0.4558303886925795,
3: 0.5361990950226244,
4: 0.62,
5: 0.8875,
6: 0.6463414634146342},
'1-Recall': {0: 0.34942084942084944,
1: 0.7393822393822393,
2: 0.747104247104247,
3: 0.4575289575289575,
4: 0.5386100386100386,
5: 0.13706563706563707,
6: 0.5115830115830116},
'1-F1-score': {0: 0.4635083226632522,
1: 0.5644804716285925,
2: 0.5662033650329188,
3: 0.49375,
4: 0.5764462809917356,
5: 0.2374581939799331,
6: 0.5711206896551725},
'Accuracy': {0: 0.8324,
1: 0.7636,
2: 0.7628,
3: 0.8056,
4: 0.836,
5: 0.8176,
6: 0.8408},
'AUC': {0: 0.6540242491302027,
1: 0.754655801830373,
2: 0.7570031830879459,
3: 0.6770490398139237,
4: 0.7261667751072393,
5: 0.5662623846276723,
6: 0.7192122928752596},
'SMOTE': {0: 'No',
1: 'Yes',
2: 'Yes',
3: 'Yes',
4: 'Yes',
5: 'Yes',
6: 'Yes'},
'top3var': {0: "['numofproducts_4', 'numofproducts_3', 'geography_germany']",
1: "['numofproducts_4', 'numofproducts_3', 'geography_germany']",
2: "['numofproducts_4', 'numofproducts_3', 'age']",
3: "['empty']",
4: "['numofproducts_2', 'numofproducts_1', 'isactivemember']",
5: "['empty']",
6: "['age', 'numofproducts_2', 'balance']"}}

You can access and edit the range of any axis of your figure using:
fig['layout']['yaxis']['range']
And set the range like:
fig['layout']['yaxis']['range'] = [0, 1]
The same thing goes for your tickvals:
fig['layout']['yaxis']['tickvals'] = [0, 0.2, 0.4, 0.6, 0.8, 1]

You can use:
fig.update_yaxes(tickvals=[0, 0.2, 0.4, 0.6, 0.8, 1])
Your code example does not work for me because "report_df_scoring" is missing.

Number of labels does not match samples on decision tree regression

Trying to run a decision tree regressor on my data, but whenever I try and run my code, I get this error
ValueError: Number of labels=78177 does not match number of samples=312706
#feature selection
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeRegressor
target = ['sale_price']
train, test = train_test_split(housing_data, test_size=0.2)
regression_tree = DecisionTreeRegressor(criterion="entropy",random_state=100,
max_depth=4,min_samples_leaf=5)
regression_tree.fit(train,test)
I have added a sample of my code, hopefully this gives you more context to help better understand my question and problem:
{'Age of House at Sale': {0: 6,
1: 2016,
2: 92,
3: 42,
4: 90,
5: 2012,
6: 89,
7: 3,
8: 2015,
9: 104},
'AreaSource': {0: 2.0,
1: 7.0,
2: 2.0,
3: 2.0,
4: 2.0,
5: 2.0,
6: 2.0,
7: 2.0,
8: 2.0,
9: 2.0},
'AssessLand': {0: 9900.0,
1: 1571850.0,
2: 1548000.0,
3: 36532350.0,
4: 2250000.0,
5: 3110400.0,
6: 2448000.0,
7: 1354500.0,
8: 1699200.0,
9: 1282500.0},
'AssessTot': {0: 34380.0,
1: 1571850.0,
2: 25463250.0,
3: 149792400.0,
4: 27166050.0,
5: 5579990.0,
6: 28309500.0,
7: 23965650.0,
8: 3534300.0,
9: 11295000.0},
'BldgArea': {0: 2688.0,
1: 0.0,
2: 304650.0,
3: 2548000.0,
4: 356000.0,
5: 382746.0,
6: 290440.0,
7: 241764.0,
8: 463427.0,
9: 547000.0},
'BldgClass': {0: 72,
1: 89,
2: 80,
3: 157,
4: 150,
5: 44,
6: 92,
7: 43,
8: 39,
9: 61},
'BldgDepth': {0: 50.0,
1: 0.0,
2: 92.0,
3: 0.0,
4: 100.33,
5: 315.0,
6: 125.0,
7: 100.0,
8: 0.0,
9: 80.92},
'BldgFront': {0: 20.0,
1: 0.0,
2: 335.0,
3: 0.0,
4: 202.0,
5: 179.0,
6: 92.0,
7: 500.0,
8: 0.0,
9: 304.0},
'BsmtCode': {0: 5.0,
1: 5.0,
2: 5.0,
3: 5.0,
4: 2.0,
5: 5.0,
6: 2.0,
7: 2.0,
8: 5.0,
9: 5.0},
'CD': {0: 310.0,
1: 302.0,
2: 302.0,
3: 318.0,
4: 302.0,
5: 301.0,
6: 302.0,
7: 301.0,
8: 301.0,
9: 302.0},
'ComArea': {0: 0.0,
1: 0.0,
2: 304650.0,
3: 2548000.0,
4: 30000.0,
5: 11200.0,
6: 290440.0,
7: 27900.0,
8: 4884.0,
9: 547000.0},
'CommFAR': {0: 0.0,
1: 2.0,
2: 2.0,
3: 2.0,
4: 0.0,
5: 0.0,
6: 10.0,
7: 2.0,
8: 0.0,
9: 2.0},
'Council': {0: 41.0,
1: 33.0,
2: 33.0,
3: 46.0,
4: 33.0,
5: 33.0,
6: 33.0,
7: 33.0,
8: 33.0,
9: 35.0},
'Easements': {0: 0.0,
1: 0.0,
2: 0.0,
3: 1.0,
4: 0.0,
5: 0.0,
6: 0.0,
7: 0.0,
8: 0.0,
9: 0.0},
'ExemptLand': {0: 0.0,
1: 1571850.0,
2: 0.0,
3: 0.0,
4: 2250000.0,
5: 0.0,
6: 0.0,
7: 932847.0,
8: 0.0,
9: 0.0},
'ExemptTot': {0: 0.0,
1: 1571850.0,
2: 0.0,
3: 0.0,
4: 27166050.0,
5: 0.0,
6: 11304900.0,
7: 23543997.0,
8: 0.0,
9: 0.0},
'FacilFAR': {0: 0.0,
1: 6.5,
2: 0.0,
3: 0.0,
4: 4.8,
5: 4.8,
6: 10.0,
7: 3.0,
8: 5.0,
9: 4.8},
'FactryArea': {0: 0.0,
1: 0.0,
2: 0.0,
3: 0.0,
4: 0.0,
5: 0.0,
6: 0.0,
7: 0.0,
8: 0.0,
9: 547000.0},
'GarageArea': {0: 0.0,
1: 0.0,
2: 0.0,
3: 1285000.0,
4: 0.0,
5: 0.0,
6: 0.0,
7: 22200.0,
8: 0.0,
9: 0.0},
'HealthArea': {0: 6410.0,
1: 1000.0,
2: 2300.0,
3: 8822.0,
4: 2300.0,
5: 400.0,
6: 2300.0,
7: 700.0,
8: 500.0,
9: 9300.0},
'HealthCent': {0: 35.0,
1: 36.0,
2: 38.0,
3: 35.0,
4: 38.0,
5: 30.0,
6: 38.0,
7: 30.0,
8: 30.0,
9: 36.0},
'IrrLotCode': {0: 1, 1: 1, 2: 0, 3: 0, 4: 1, 5: 1, 6: 0, 7: 1, 8: 0, 9: 0},
'LandUse': {0: 2.0,
1: 10.0,
2: 5.0,
3: 5.0,
4: 8.0,
5: 4.0,
6: 5.0,
7: 3.0,
8: 3.0,
9: 6.0},
'LotArea': {0: 2252.0,
1: 134988.0,
2: 32000.0,
3: 905000.0,
4: 20267.0,
5: 57600.0,
6: 12500.0,
7: 50173.0,
8: 44704.0,
9: 113800.0},
'LotDepth': {0: 100.0,
1: 275.33,
2: 335.92,
3: 859.0,
4: 100.33,
5: 320.0,
6: 125.0,
7: 200.0,
8: 281.86,
9: 204.0},
'LotFront': {0: 24.0,
1: 490.5,
2: 92.42,
3: 930.0,
4: 202.0,
5: 180.0,
6: 100.0,
7: 521.25,
8: 225.08,
9: 569.0},
'LotType': {0: 5.0,
1: 5.0,
2: 3.0,
3: 3.0,
4: 3.0,
5: 3.0,
6: 3.0,
7: 1.0,
8: 5.0,
9: 3.0},
'NumBldgs': {0: 1.0,
1: 0.0,
2: 1.0,
3: 4.0,
4: 1.0,
5: 1.0,
6: 1.0,
7: 1.0,
8: 2.0,
9: 13.0},
'NumFloors': {0: 2.0,
1: 0.0,
2: 13.0,
3: 2.0,
4: 15.0,
5: 0.0,
6: 37.0,
7: 6.0,
8: 20.0,
9: 8.0},
'OfficeArea': {0: 0.0,
1: 0.0,
2: 264750.0,
3: 0.0,
4: 30000.0,
5: 1822.0,
6: 274500.0,
7: 4200.0,
8: 0.0,
9: 0.0},
'OtherArea': {0: 0.0,
1: 0.0,
2: 39900.0,
3: 0.0,
4: 0.0,
5: 0.0,
6: 0.0,
7: 0.0,
8: 0.0,
9: 0.0},
'PolicePrct': {0: 70.0,
1: 84.0,
2: 84.0,
3: 63.0,
4: 84.0,
5: 90.0,
6: 84.0,
7: 94.0,
8: 90.0,
9: 88.0},
'ProxCode': {0: 0.0,
1: 0.0,
2: 0.0,
3: 0.0,
4: 0.0,
5: 0.0,
6: 0.0,
7: 1.0,
8: 0.0,
9: 0.0},
'ResArea': {0: 2172.0,
1: 0.0,
2: 0.0,
3: 0.0,
4: 0.0,
5: 371546.0,
6: 0.0,
7: 213864.0,
8: 458543.0,
9: 0.0},
'ResidFAR': {0: 2.0,
1: 7.2,
2: 0.0,
3: 0.0,
4: 2.43,
5: 2.43,
6: 10.0,
7: 3.0,
8: 5.0,
9: 0.0},
'RetailArea': {0: 0.0,
1: 0.0,
2: 0.0,
3: 1263000.0,
4: 0.0,
5: 9378.0,
6: 15940.0,
7: 0.0,
8: 4884.0,
9: 0.0},
'SHAPE_Area': {0: 2316.8863224,
1: 140131.577176,
2: 34656.4472405,
3: 797554.847834,
4: 21360.1476315,
5: 58564.8643115,
6: 12947.145471,
7: 50772.624868800005,
8: 47019.5677861,
9: 118754.78573699998},
'SHAPE_Leng': {0: 249.41135038849998,
1: 1559.88914353,
2: 890.718521021,
3: 3729.78685686,
4: 620.761169374,
5: 1006.33799946,
6: 460.03168012300006,
7: 1385.27352839,
8: 992.915660585,
9: 1565.91477261},
'SanitDistr': {0: 10.0,
1: 2.0,
2: 2.0,
3: 18.0,
4: 2.0,
5: 1.0,
6: 2.0,
7: 1.0,
8: 1.0,
9: 2.0},
'SanitSub': {0: 21,
1: 23,
2: 31,
3: 22,
4: 31,
5: 21,
6: 23,
7: 7,
8: 12,
9: 22},
'SchoolDist': {0: 19.0,
1: 13.0,
2: 13.0,
3: 22.0,
4: 13.0,
5: 14.0,
6: 13.0,
7: 14.0,
8: 14.0,
9: 14.0},
'SplitZone': {0: 1, 1: 1, 2: 1, 3: 1, 4: 1, 5: 1, 6: 1, 7: 1, 8: 0, 9: 1},
'StrgeArea': {0: 0.0,
1: 0.0,
2: 0.0,
3: 0.0,
4: 0.0,
5: 0.0,
6: 0.0,
7: 1500.0,
8: 0.0,
9: 0.0},
'UnitsRes': {0: 2.0,
1: 0.0,
2: 0.0,
3: 0.0,
4: 0.0,
5: 522.0,
6: 0.0,
7: 234.0,
8: 470.0,
9: 0.0},
'UnitsTotal': {0: 2.0,
1: 0.0,
2: 0.0,
3: 123.0,
4: 1.0,
5: 525.0,
6: 102.0,
7: 237.0,
8: 472.0,
9: 1.0},
'YearAlter1': {0: 0.0,
1: 0.0,
2: 1980.0,
3: 0.0,
4: 1998.0,
5: 0.0,
6: 2009.0,
7: 2012.0,
8: 0.0,
9: 0.0},
'YearAlter2': {0: 0.0,
1: 0.0,
2: 0.0,
3: 0.0,
4: 2000.0,
5: 0.0,
6: 0.0,
7: 0.0,
8: 0.0,
9: 0.0},
'ZipCode': {0: 11220.0,
1: 11201.0,
2: 11201.0,
3: 11234.0,
4: 11201.0,
5: 11249.0,
6: 11241.0,
7: 11211.0,
8: 11249.0,
9: 11205.0},
'ZoneDist1': {0: 24,
1: 76,
2: 5,
3: 64,
4: 24,
5: 24,
6: 30,
7: 74,
8: 45,
9: 27},
'ZoneMap': {0: 3,
1: 19,
2: 19,
3: 22,
4: 19,
5: 19,
6: 19,
7: 2,
8: 19,
9: 19},
'building_class': {0: 141,
1: 97,
2: 87,
3: 176,
4: 168,
5: 8,
6: 102,
7: 46,
8: 97,
9: 66},
'building_class_at_sale': {0: 143,
1: 98,
2: 89,
3: 179,
4: 171,
5: 7,
6: 103,
7: 49,
8: 98,
9: 69},
'building_class_category': {0: 39,
1: 71,
2: 31,
3: 38,
4: 86,
5: 40,
6: 80,
7: 75,
8: 71,
9: 41},
'commercial_units': {0: 1,
1: 0,
2: 0,
3: 123,
4: 1,
5: 0,
6: 102,
7: 3,
8: 0,
9: 1},
'gross_sqft': {0: 0.0,
1: 0.0,
2: 304650.0,
3: 2548000.0,
4: 356000.0,
5: 0.0,
6: 290440.0,
7: 241764.0,
8: 0.0,
9: 547000.0},
'land_sqft': {0: 0.0,
1: 134988.0,
2: 32000.0,
3: 905000.0,
4: 20267.0,
5: 57600.0,
6: 12500.0,
7: 50173.0,
8: 44704.0,
9: 113800.0},
'neighborhood': {0: 43,
1: 48,
2: 6,
3: 44,
4: 6,
5: 40,
6: 6,
7: 28,
8: 40,
9: 56},
'residential_units': {0: 0,
1: 0,
2: 0,
3: 0,
4: 0,
5: 0,
6: 0,
7: 234,
8: 0,
9: 0},
'sale_date': {0: 2257,
1: 4839,
2: 337,
3: 638,
4: 27,
5: 1458,
6: 2450,
7: 3276,
8: 5082,
9: 1835},
'sale_price': {0: 499401179.0,
1: 345000000.0,
2: 340000000.0,
3: 276947000.0,
4: 202500000.0,
5: 185445000.0,
6: 171000000.0,
7: 169000000.0,
8: 165000000.0,
9: 161000000.0},
'tax_class': {0: 3, 1: 3, 2: 3, 3: 3, 4: 3, 5: 3, 6: 3, 7: 7, 8: 3, 9: 3},
'total_units': {0: 1,
1: 0,
2: 0,
3: 123,
4: 1,
5: 0,
6: 102,
7: 237,
8: 0,
9: 1},
'zip_code': {0: 11201,
1: 11201,
2: 11201,
3: 11234,
4: 11201,
5: 11249,
6: 11241,
7: 11211,
8: 11249,
9: 11205}}