Python_VS/bankrupt.py at master · varun5001/Python_VS · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
# -*- coding: utf-8 -*-
"""
Spyder Editor

This is a temporary script file.
"""

import numpy as np
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
from pandas.tools.plotting import scatter_matrix
import qtpy

%matplotlib qt
%pylab qt
data = pd.read_csv('E:/MS_US/Spring_2017/MIS6v99_Python/Project/data.csv')

data.info()

data.hist()
plt.figure()

data.plot(kind='density', subplots=True, layout=(4,4), sharex=False)
plt.show()

df = pd.DataFrame(data)

df.info()
colnames = list(df.columns.values)
colnames = colnames[2:]
colnames

for colname in colnames:
    print(colname)
    sns.boxplot(x="bstatus", y='trans_mve_td', data=df)
    sns.stripplot(x="bstatus", y="trans_mve_td", data=df, jitter=True, edgecolor="gray")
    sns.plt.show()

sns.jointplot(x="bstatus", y="trans_mve_td", data=df, size=5)
sns.distplot(data['trans_mve_td'], hist=False, rug=True)

sns.kdeplot(data['trans_mve_td'], shade=True)
sns.plt.show()

x = data['trans_ca_cl']
sns.kdeplot(x)
sns.kdeplot(x, bw=.2, label="bw: 0.2")
sns.kdeplot(x, bw=2, label="bw: 2")
plt.legend()
sns.plt.show()
df_mod = df.drop(df.columns[[0,1]], axis = 1)

df_mod.info()

sns.boxplot(data=df_mod, orient="h", palette="Set2")
sns.plt.show()


scatter_matrix(df)
plt.show()


#df = sns.load_dataset("iris")
sns.pairplot(df_mod)
sns.plt.show()

g = sns.PairGrid(df)
g.map_diag(sns.kdeplot)
g.map_offdiag(sns.kdeplot, cmap="Blues_d", n_levels=6)


sns.boxplot(data=df)
sns.swarmplot(data=df, color=".25")

def plot_histograms( df , variables , n_rows , n_cols ):
    fig = plt.figure( figsize = ( 16 , 12 ) )
    for i, var_name in enumerate( variables ):
        ax=fig.add_subplot( n_rows , n_cols , i+1 )
        df[ var_name ].hist( bins=10 , ax=ax )
        ax.set_title( 'Skew: ' + str( round( float( df[ var_name ].skew() ) , ) ) ) # + ' ' + var_name ) #var_name+" Distribution")
        ax.set_xticklabels( [] , visible=False )
        ax.set_yticklabels( [] , visible=False )
    fig.tight_layout()  # Improves appearance a bit.
    plt.show()

def plot_distribution( df , var , target , **kwargs ):
    row = kwargs.get( 'row' , None )
    col = kwargs.get( 'col' , None )
    facet = sns.FacetGrid( df , hue=target , aspect=4 , row = row , col = col )
    facet.map( sns.kdeplot , var , shade= True )
    facet.set( xlim=( 0 , df[ var ].max() ) )
    facet.add_legend()

def plot_categories( df , cat , target , **kwargs ):
    row = kwargs.get( 'row' , None )
    col = kwargs.get( 'col' , None )
    facet = sns.FacetGrid( df , row = row , col = col )
    facet.map( sns.barplot , cat , target )
    facet.add_legend()

def plot_correlation_map( df ):
    corr = data.corr()
    _ , ax = plt.subplots( figsize =( 12 , 10 ) )
    cmap = sns.diverging_palette( 220 , 10 , as_cmap = True )
    _ = sns.heatmap(
        corr,
        cmap = cmap,
        square=True,
        cbar_kws={ 'shrink' : .9 },
        ax=ax,
        annot = True,
        annot_kws = { 'fontsize' : 12 }
    )

def describe_more( df ):
    var = [] ; l = [] ; t = []
    for x in df:
        var.append( x )
        l.append( len( pd.value_counts( df[ x ] ) ) )
        t.append( df[ x ].dtypes )
    levels = pd.DataFrame( { 'Variable' : var , 'Levels' : l , 'Datatype' : t } )
    levels.sort_values( by = 'Levels' , inplace = True )
    return levels

def plot_variable_importance( X , y ):
    tree = DecisionTreeClassifier( random_state = 99 )
    tree.fit( X , y )
    plot_model_var_imp( tree , X , y )

def plot_model_var_imp( model , X , y ):
    imp = pd.DataFrame(
        model.feature_importances_  ,
        columns = [ 'Importance' ] ,
        index = X.columns
    )
    imp = imp.sort_values( [ 'Importance' ] , ascending = True )
    imp[ : 10 ].plot( kind = 'barh' )
    print (model.score( X , y ))

plot_correlation_map(data)