def areSimilarLst(A,B,level=0.05):
""" finds the similarity of the given list and the next. default level is 0.05
Returns True if they are similar, or returns False otherwise
"""
#only for same length list
if (len(A) != len(B)):
return None;
#set some parameters
degree_of_freedom = len(A);
significance_level = level;
#calculate chisquared between the two lists
Exp_vals = A;
Obv_vals = B;
chiSquared = 0.0;
#use the pearson chi squared test
chiSquared,p_val = stats.lchisquare(Obv_vals,Exp_vals);
print "chiSquared, p_val: ", chiSquared, p_val;
if p_val <= significance_level:
return True,chiSquared,p_val;
else:
return False,chiSquared,p_val;
#
#W1 = numpy.random.rand(50).astype(numpy.float32);
#W2 = numpy.random.rand(50).astype(numpy.float32);
#W3 = numpy.random.poisson(1.0,50);
#print areSimilarLst(W1.tolist(),W2.tolist(),0.05);
#print areSimilarLst(W1.tolist(),W3.tolist(),0.05);
def data_table(self):
global My_Global_NDRL
NDRL_num = My_Global_NDRL
data_table = [None]
try:
number_of_points = len(self.sequence)
except:
number_of_points = 1
data_table.append("""<br><div class="warning">No data! """)
data_table.append(
"""Enter data or select from sample tab.</div>""")
if number_of_points > 2:
number_of_points = number_of_points
output_comment = stats.lchisquare(self.freq_bin(), self.normal())
comment = """Your data is awful! """
if output_comment[1] >= .98:
comment = """ Your data is an excellent fit to a "log normal distribution" so you may be confident in the output of this and any other statistical analysis on this data. """
elif output_comment[1] < .98 and output_comment[1] >= .80:
comment = """Your data is a reasonable fit to a "log normal distribution" but you should investigate for potential reasons for the discrepancy. <br>
<strong>Any local DRL or other statistic claculated from this data should be treated with some caution.</strong> """
elif output_comment[1] < .80 and output_comment[1] >= .50:
comment = """<div class="warning">Your data is a very poor fit to a "log normal distribution" so you should investgate why, as any attempt to calculate a local DRL or other statistic will be invalid.</div> """
elif output_comment[1] < .50 and output_comment[1] >= .20:
comment = """<div class="warning">Your data very random and not behaving like a set of radiation total doses. You should investgate why, as any attempt to calculate a local DRL or other statistic will be invalid. The data comprises of mixed procedures or mixed units.</div> """
else:
comment = """<div class="warning">Your data is very, very random and not behaving like a set of radiation total doses so you should investgate why, as any attempt to calculate a local DRL or other statistic will be invalid. Perhaps the data comprises of mixed procedures or mixed units.</div> """
table_start1 = """ <div = "information"><p>This is a summary of your data that includes so statistical tests for validity. A good quality set of data will fit a "log normal distribution". When plotted correctly, a log normal distribution looks like a smooth bell shaped curve. If your data does not fit such a curve, then you should seek a reason for the discrepancy.</p>
<p>You may cut and paste data from this page into a spreadsheet or other document. (Formatting is usually preserved better when pasting into a spreadsheet).</p>
</div>"""
table_start2 = """<table style="text-align: left; width: 100%;" border="0" cellpadding="1" cellspacing="2"> <tbody> """
table_end = """</tbody>
</table>"""
table_start_row = "<TR>"
table_end_row = "</TR>"
table_start_cell = """<TD align="right">"""
table_end_cell = "</TD>"
# Now create a table of all the data
# This method is "clunky" but easy to read
# Start the table:
# data_table = [None]
data_table.append(table_start1)
data_table.append(comment)
data_table.append(table_start2)
# Histogram
data_table.append(table_start_row)
#data_table.append(table_start_cell)
#data_table.append("Histogram")
#data_table.append(table_end_cell)
data = self.standard_normal_histo_chart()
bins = self.bin_limits()
cols_span = len(bins)
data_table.append("""<TD colspan="%s" align="left" >""" %
cols_span)
data_table.append("""
<img alt="Plot of input data" src="%s"/> <br>
""" % data)
# Units
data_table.append(table_start_row)
data_table.append(table_start_cell)
data_table.append("Units")
data = self.bin_limits()
for item in range(len(data) - 1):
data_table.append(table_start_cell)
data_table.append("%s" % NDRL_num[3])
data_table.append(table_end_cell)
# Observed data
data_table.append(table_start_row)
data_table.append(table_start_cell)
data_table.append("Observed Frequency")
data = self.standard_normal_freq_bin()
Observed_data_frequency = data[0]
for item in range(len(Observed_data_frequency)):
data_table.append(table_start_cell)
data_table.append("%d" % Observed_data_frequency[item])
data_table.append(table_end_cell)
# Expected data
data_table.append(table_start_row)
data_table.append(table_start_cell)
data_table.append("Expected Frequency")
Expected_data_frequency = self.standard_z()
for item in range(len(Expected_data_frequency)):
data_table.append(table_start_cell)
data_table.append("%d" % Expected_data_frequency[item])
data_table.append(table_end_cell)
# Standard Normal Histogram
data_table.append(table_start_row)
#data_table.append(table_start_cell)
bins = self.bin_limits()
cols_span = len(bins)
data_table.append("""<TD colspan="%s" align="left" >""" %
cols_span)
data_table.append("""
<p>The standard normal histogram plots the data as bell shaped curve of with a mean of 0 and a standard deviation of 1. This view allows for easier interpretation of anomalies in the data set. </p><br>
""")
output = stats.lchisquare(self.freq_bin(), self.normal())
# Single data row
data_table.append(table_start_row)
data_table.append(table_start_cell)
data_table.append("Sum of Chi Squared ")
data_table.append("""<TD colspan="%s" align="left" >""" %
cols_span)
data_table.append(
""" (The closer this value is to zero the better fit your data is to a normal distribution ) = %.2f """
% output[0])
# Single data row
data_table.append(table_start_row)
data_table.append(table_start_cell)
data_table.append("P value ")
#data = self.histo_fit_chart()
#bins = self.bin_limits()
#cols_span = len(bins)-1
data_table.append("""<TD colspan="%s" align="left" >""" %
cols_span)
output_percent = output[1] * 100
data_table.append(
""" (The closer this is to 100%% higher the probability that you have a normal distribution) = %.2f %% """
% output_percent)
# Single data row skewness
data_table.append(table_start_row)
data_table.append(table_start_cell)
data_table.append("Skewness ")
skewness = self.skewness()
data_table.append("""<TD colspan="%s" align="left" >""" %
cols_span)
data_table.append(""" left = %s, right = %s """ %
(skewness[0], skewness[1]))
# Single data My_Global_NDRL:
# data_table.append(table_start_row)
# data_table.append(table_start_cell)
# data_table.append("Selected NDRL Data ")
#
# data_table.append("""<TD colspan="%s" align="left" >""" % cols_span)
# data_table.append( """ left = %s, right = """ % (My_Global_NDRL[0]) )
#
#
data_table.append(table_end)
return data_table
def data_table(self):
global My_Global_NDRL
NDRL_num = My_Global_NDRL
data_table = [None]
try:
number_of_points = len(self.sequence)
except:
number_of_points = 1
data_table.append("""<br><div class="warning">No data! """)
data_table.append("""Enter data or select from sample tab.</div>""")
if number_of_points > 2:
number_of_points = number_of_points
output_comment = stats.lchisquare(self.freq_bin(),self.normal())
comment = """Your data is awful! """
if output_comment[1] >= .98:
comment = """ Your data is an excellent fit to a "log normal distribution" so you may be confident in the output of this and any other statistical analysis on this data. """
elif output_comment[1] < .98 and output_comment[1] >= .80 :
comment = """Your data is a reasonable fit to a "log normal distribution" but you should investigate for potential reasons for the discrepancy. <br>
<strong>Any local DRL or other statistic claculated from this data should be treated with some caution.</strong> """
elif output_comment[1] < .80 and output_comment[1] >= .50 :
comment = """<div class="warning">Your data is a very poor fit to a "log normal distribution" so you should investgate why, as any attempt to calculate a local DRL or other statistic will be invalid.</div> """
elif output_comment[1] < .50 and output_comment[1] >= .20 :
comment = """<div class="warning">Your data very random and not behaving like a set of radiation total doses. You should investgate why, as any attempt to calculate a local DRL or other statistic will be invalid. The data comprises of mixed procedures or mixed units.</div> """
else:
comment = """<div class="warning">Your data is very, very random and not behaving like a set of radiation total doses so you should investgate why, as any attempt to calculate a local DRL or other statistic will be invalid. Perhaps the data comprises of mixed procedures or mixed units.</div> """
table_start1 = """ <div = "information"><p>This is a summary of your data that includes so statistical tests for validity. A good quality set of data will fit a "log normal distribution". When plotted correctly, a log normal distribution looks like a smooth bell shaped curve. If your data does not fit such a curve, then you should seek a reason for the discrepancy.</p>
<p>You may cut and paste data from this page into a spreadsheet or other document. (Formatting is usually preserved better when pasting into a spreadsheet).</p>
</div>"""
table_start2 ="""<table style="text-align: left; width: 100%;" border="0" cellpadding="1" cellspacing="2"> <tbody> """
table_end= """</tbody>
</table>"""
table_start_row = "<TR>"
table_end_row = "</TR>"
table_start_cell = """<TD align="right">"""
table_end_cell = "</TD>"
# Now create a table of all the data
# This method is "clunky" but easy to read
# Start the table:
# data_table = [None]
data_table.append(table_start1)
data_table.append(comment)
data_table.append(table_start2)
# Histogram
data_table.append(table_start_row)
#data_table.append(table_start_cell)
#data_table.append("Histogram")
#data_table.append(table_end_cell)
data = self.standard_normal_histo_chart()
bins = self.bin_limits()
cols_span = len(bins)
data_table.append("""<TD colspan="%s" align="left" >""" % cols_span)
data_table.append("""
<img alt="Plot of input data" src="%s"/> <br>
""" % data)
# Units
data_table.append(table_start_row)
data_table.append(table_start_cell)
data_table.append("Units")
data = self.bin_limits()
for item in range(len(data)-1):
data_table.append(table_start_cell)
data_table.append("%s" %NDRL_num[3])
data_table.append(table_end_cell)
# Observed data
data_table.append(table_start_row)
data_table.append(table_start_cell)
data_table.append("Observed Frequency")
data = self.standard_normal_freq_bin()
Observed_data_frequency = data[0]
for item in range(len(Observed_data_frequency)):
data_table.append(table_start_cell)
data_table.append("%d" % Observed_data_frequency[item])
data_table.append(table_end_cell)
# Expected data
data_table.append(table_start_row)
data_table.append(table_start_cell)
data_table.append("Expected Frequency")
Expected_data_frequency = self.standard_z()
for item in range(len(Expected_data_frequency)):
data_table.append(table_start_cell)
data_table.append("%d" % Expected_data_frequency[item])
data_table.append(table_end_cell)
# Standard Normal Histogram
data_table.append(table_start_row)
#data_table.append(table_start_cell)
bins = self.bin_limits()
cols_span = len(bins)
data_table.append("""<TD colspan="%s" align="left" >""" % cols_span)
data_table.append("""
<p>The standard normal histogram plots the data as bell shaped curve of with a mean of 0 and a standard deviation of 1. This view allows for easier interpretation of anomalies in the data set. </p><br>
""" )
output = stats.lchisquare(self.freq_bin(), self.normal() )
# Single data row
data_table.append(table_start_row)
data_table.append(table_start_cell)
data_table.append("Sum of Chi Squared ")
data_table.append("""<TD colspan="%s" align="left" >""" % cols_span)
data_table.append( """ (The closer this value is to zero the better fit your data is to a normal distribution ) = %.2f """ % output[0] )
# Single data row
data_table.append(table_start_row)
data_table.append(table_start_cell)
data_table.append("P value ")
#data = self.histo_fit_chart()
#bins = self.bin_limits()
#cols_span = len(bins)-1
data_table.append("""<TD colspan="%s" align="left" >""" % cols_span)
output_percent = output[1]*100
data_table.append( """ (The closer this is to 100%% higher the probability that you have a normal distribution) = %.2f %% """ % output_percent )
# Single data row skewness
data_table.append(table_start_row)
data_table.append(table_start_cell)
data_table.append("Skewness ")
skewness = self.skewness()
data_table.append("""<TD colspan="%s" align="left" >""" % cols_span)
data_table.append( """ left = %s, right = %s """ % (skewness[0], skewness[1]) )
# Single data My_Global_NDRL:
# data_table.append(table_start_row)
# data_table.append(table_start_cell)
# data_table.append("Selected NDRL Data ")
#
# data_table.append("""<TD colspan="%s" align="left" >""" % cols_span)
# data_table.append( """ left = %s, right = """ % (My_Global_NDRL[0]) )
#
#
data_table.append(table_end)
return data_table
