From 4b730b6e428859cb7e699079a4f472116cbeb457 Mon Sep 17 00:00:00 2001
From: SHUBHAM LADDHA <laddha.shubham97@gmail.com>
Date: Wed, 22 May 2019 11:07:08 -0700
Subject: [PATCH] Add files via upload

---
 plot.py  | 60 ++++++++++++++++++++++++++++++++++++++++++++++
 tests.py | 72 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 132 insertions(+)
 create mode 100644 plot.py
 create mode 100644 tests.py

diff --git a/plot.py b/plot.py
new file mode 100644
index 000000000..e6957bbb3
--- /dev/null
+++ b/plot.py
@@ -0,0 +1,60 @@
+import dask
+from dask import delayed
+import dask.dataframe as dd
+import dask.array as da
+import pandas as pd
+
+def f1(dataframe, col):
+    x = dataframe.groupby(col)[col].count()
+    return dict(x)
+
+def f2(dataframe, col):
+    minv = dataframe[col].min()
+    maxv = dataframe[col].max()
+    #print ('min = ',  minv, 'maxv = ', maxv)
+    #print (dataframe[col])
+    dframe = dd.from_array(dataframe[col]).dropna()
+    h, b = da.histogram(dframe.values, range=[minv, maxv], bins=10)
+    return h
+
+
+def plot(df, unique_threshold):
+    
+    #df = pd.read_csv('C:/Users/sladdha/Desktop/DataPrep/Datasets/Normal.csv')
+    
+    ls = list()
+    for col in df.columns:
+        ls.append(delayed(df[col].nunique)())
+        
+    x, = dask.compute(ls)
+    y, = dask.compute(x)
+    result = list()
+    
+    test = []
+    
+    for i, col in enumerate(df.columns):
+        if (df[col].count()==0):
+            continue
+        
+        
+        if (y[i]/df[col].count()<unique_threshold):                                                       #categorial
+            cnt_series = delayed(f1)(df, col)
+            #grp_cnt = delayed(dict)(cnt_series)
+            #print('cat')
+            result.append(cnt_series)
+            test.append(col)
+        elif (df[col].dtype=='float64' or df[col].dtype=='int64') :          #numeric
+            #print('num')      
+            hist = f2(df, col)
+            result.append(hist)
+            test.append(col)
+        
+    
+    computed_res, = dask.compute(result)  
+    column_dict = dict()
+    
+    for i, res in enumerate(computed_res):
+        column_dict[test[i]] = res
+    
+    
+    return (column_dict)
\ No newline at end of file
diff --git a/tests.py b/tests.py
new file mode 100644
index 000000000..fcd9d89e9
--- /dev/null
+++ b/tests.py
@@ -0,0 +1,72 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Tue May 21 15:41:21 2019
+
+@author: sladdha
+"""
+import datetime
+import numpy as np
+import pandas as pd
+from temp import plot
+from temp import f1
+from temp import f2
+
+class TestClass(object):
+    
+    def test_normal(self):
+        self.data_1 = {
+
+            'id': [chr(97 + c) for c in range(1, 10)],
+
+            'x': [50, 50, -10, 0, 0, 5, 15, -3, None],
+
+            'y': [0.000001, 654.152, None, 15.984512, 3122, -3.1415926535, 111, 15.9, 13.5],
+
+            's1': np.ones(9),
+
+            'somedate': [datetime.date(2011, 7, 4), datetime.datetime(2022, 1, 1, 13, 57), datetime.datetime(1990, 12, 9), np.nan, datetime.datetime(1990, 12, 9), datetime.datetime(1950, 12, 9), datetime.datetime(1898, 1, 2), datetime.datetime(1950, 12, 9), datetime.datetime(1950, 12, 9)],
+
+            'bool_tf': [True, True, False, True, False, True, True, False, True],
+
+            'bool_tf_with_nan': [True, False, False, False, False, True, True, False, np.nan],
+
+            'bool_01': [1, 1, 0, 1, 1, 0, 0, 0, 1],
+
+            'bool_01_with_nan': [1, 0, 1, 0, 0, 1, 1, 0, np.nan],
+
+            'mixed': [1, 2, "a", 4, 5, 6, 7, 8, 9]
+
+        }
+
+        self.df_1 = pd.DataFrame(self.data_1)
+        #threshold = 0.4
+        self.df_1_expected = {'bool_01': {0: 4, 1: 5}, 'bool_01_with_nan': {0.0: 4, 1.0: 4}, 'bool_tf': {False: 3, True: 6}, 'bool_tf_with_nan': {False: 5, True: 3}, 's1': {1.0: 9}, 'x': np.array([1, 3, 1, 0, 1, 0, 0, 0, 0, 2], dtype=np.int64), 'y': np.array([6, 0, 1, 0, 0, 0, 0, 0, 0, 1], dtype=np.int64)}
+        res = plot(self.df_1, 0.4)
+        assert res['bool_01'] == self.df_1_expected['bool_01']
+        assert res['bool_01_with_nan'] == self.df_1_expected['bool_01_with_nan']
+        assert res['bool_tf'] == self.df_1_expected['bool_tf']
+        assert res['bool_tf_with_nan'] == self.df_1_expected['bool_tf_with_nan']
+        assert res['s1'] == self.df_1_expected['s1']
+        assert np.all(res['x'] == self.df_1_expected['x'])
+        assert np.all(res['y'] == self.df_1_expected['y'])
+        
+        
+    def test_corner(self):
+        
+        self.df_2 = pd.DataFrame({'all_nan':[np.nan for _ in range(10)], 'all_one':np.ones(10), 'all_zeros':np.zeros(10), 'random':np.array([ 0.38538395,  0.13609054,  0.15973238,  0.96192966,  0.03708882,
+        0.03633855,  0.25260128,  0.72139843,  0.74553949,  0.41102021])})
+        
+        #threshold = 0.5
+        self.df_1_expected = {'all_one': {1.0: 10},
+                              'all_zeros': {0.0: 10},
+                              'random': np.array([2, 2, 1, 1, 1, 0, 0, 2, 0, 1], dtype=np.int64)}
+        
+        res = plot(self.df_2, 0.5)
+       
+        #assert np.all(res['all_nan'] == self.df_1_expected['all_nan'])
+        assert res['all_one'] == self.df_1_expected['all_one']
+        assert res['all_zeros'] == self.df_1_expected['all_zeros']
+            
+            
+            
+        
\ No newline at end of file