import pandas as pd
import numpy as np
from sklearn.preprocessing import LabelEncoder
import random
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.cross_validation import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score
from sklearn import tree
import matplotlib.pyplot as plt
%matplotlib inline

df = pd.read_csv('Documents/Poaching_Final.csv')

df

id_report   date_report description longitude   latitude
0   3   1/1/2005    Poaching incident   -7.049359   34.841440
1   0   1/20/2005   Poaching incident   -7.650840   34.480010
2   0   1/20/2005   Poaching incident   -7.843202   34.005704
3   5   1/20/2005   Poaching incident   -7.745846   33.948526
4   2   1/20/2005   Poaching incident   -7.876673   33.690167
5   1   1/20/2005   Poaching incident   -7.466248   34.066729
6   1   1/20/2005   Poaching incident   -7.946153   34.220592
7   2   1/27/2005   Poaching incident   -7.925990   34.857120
dataset = df.values

dataset

array([[3, '1/1/2005', 'Poaching incident', -7.049359,
    34.841440000000006],
   [0, '1/20/2005', 'Poaching incident', -7.65084, 34.48001],
   [0, '1/20/2005', 'Poaching incident', -7.8432018029999995,
    34.00570378],
   ...,
   [3, '9/29/2015', 'White Rhino', 31.89865, -28.253253000000004],
   [3, '10/1/2015', 'African Savannah Elephant', 28.589312,
    -16.884113],
   [2, '3/7/2015', 'White Rhino', 30.934913, -24.301232000000002]],
  dtype=object)
X = fullData.values[:, 3:4]
Y = fullData.values[:, 0]

poaching_incident = df['description']
poaching_incident_encoding = poaching_incident.factorize()
poaching_incident_encoding[:10]

incidnt_date = df['date_report']
incidnt_date_encoding = incidnt_date.factorize()
incidnt_date_encoding[:10]

from sklearn import preprocessing
min_max_scaler = preprocessing.MinMaxScaler()
X_scale = min_max_scaler.fit_transform(X)

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-172-350511f008c8> in <module>()
  1 from sklearn import preprocessing
  2 min_max_scaler = preprocessing.MinMaxScaler()
----> 3 X_scale = min_max_scaler.fit_transform(X)

ValueError: Input contains NaN, infinity or a value too large for
dtype('float64').