updated to do 95% CI instead of 1 std error bars. As if a difference is even noticable

.vscode/settings.json

@@ -1,3 +0,0 @@
-{
-    "python.pythonPath": "C:\\python3.8\\python.exe"
-}

last_attempt.py

@@ -1,223 +0,0 @@
-#!/usr/bin/env python
-# coding: utf-8
-
-# In[1]:
-
-
-import pandas as pd
-from pandas import DataFrame, Series
-from numpy import nan
-import matplotlib.pyplot as plt
-plt.rcParams["figure.figsize"] = (24,5)
-import seaborn as sns
-sns.set()
-sns.set(font_scale=1.75)
-
-
-# In[2]:
-
-
-cols = [
-    "TEST","MAP","SIZE", "TIME"
-]
-onmodded = pd.read_csv("new_repr.csv", quotechar="'", header=None)
-
-onmodded = onmodded.drop([0],1)
-onmodded.columns= cols
-onmodded = onmodded.drop([0],0)
-onmodded.iloc[:,2:] = onmodded.iloc[:,2:].astype("int32")
-
-
-styles = {'absl::flat_hash_map': ["#0000cc"],  # blue
-          "absl::node_hash_map'": ["#3366ff"],
-          'absl::node_hash_map': ["#99ccff"],
-
-          'google::dense_hash_map': ["#ff0000"],  # reds
-          'google::sparse_hash_map': ["#ff6666"],
-          'phmap::parallel_flat_hash_map': ["#ff0066"],
-
-          'ska::bytell_hash_map': ["#009933"],  # greens
-          'ska::flat_hash_map': ["#33cc33"],
-          'ska::unordered_map': ["#99ff66"],
-
-          'tsl::hopscotch_map': ["#9900cc"],  # purples
-          'tsl::robin_map': ["#cc33ff"],
-          'tsl::sparse_map': ["#cc99ff"],
-
-          'robin_hood::unordered_flat_map': ["#ffcc99"],
-          'robin_hood::unordered_node_map': ["#ccff66"],
-
-          'boost::unordered::unordered_map': ["#663300"],  # brown
-
-          'emilib::HashMap': ["#9900cc"],  # purple
-
-          # weird orange
-          'phmap::parallel_node_hash_map': ["#ffcc66", "solid"],
-
-          'std::unordered_map': ["#000000", "solid"],  # black
-         }
-ticks = [50000, 100000, 150000, 200000, 250000, 300000, 350000, 400000, 500000,
-600000, 700000, 800000, 900000, 1000000,
-2000000, 3000000, 4000000, 5000000, 6000000, 7000000, 8000000, 9000000, 10000000,
-15000000, 20000000, 25000000, 30000000, 35000000, 40000000, 45000000, 50000000]
-ticklabels = ['50 K', '100 K',
- '150 K', '200 K', '250 K', '300 K',
- '350 K', '400 K', '0.5 M', '0.6 M',
- '0.7 M', '0.8 M', '0.9 M', '1 M',
- '2 M', '3 M', '4 M', '5 M',
- '6 M', '7 M', '8 M', '9 M',
- '10 M', '15 M', '20 M', '25 M',
- '30 M', '35 M', '40 M', '45 M', '50 M']
-labels = {
-    'int_delete' : ["mean int deletion time", "deletion time (ns)"],
-    'int_insert' : ["mean int insertion time", "insertion time(ns)"],
-    'int_nosucc_lookup' : ["mean int unsucessful lookup time", "unsucessful lookup time (ns)"],
-    'int_succ_lookup' : ["mean int succesful lookup time", "succesful lookup time (ns)"],
-    'string_delete' : ["mean string deletion time", "deletion time (ns)"],
-    'string_insert' : ["mean string insertion time", "insertion time(ns)"], 
-    'string_nosucc_lookup' : ["mean string unsucessful lookup time", "unsucessful lookup time (ns)"],
-    'string_succ_lookup' : ["mean string succesful lookup time", "succesful lookup time (ns)"]
-}
-
-
-# In[3]:
-
-
-# outlier testing functions
-def remove_with_modified_z_score(data, treshold=3.5):
-    # https://www.itl.nist.gov/div898/handbook/eda/section3/eda35h.htm
-    data = data.astype(int)
-    stats = data.describe()
-    median_absolute_deviation = abs(data - data.median()).median()
-    if not median_absolute_deviation:
-        return data
-    modified_z_scores = abs(0.6745 * (data - data.median()) / median_absolute_deviation)
-    cutoff = modified_z_scores <= treshold
-    data = data * cutoff
-    data = data.replace(0, nan)
-    return data
-
-#function that takes one of the outlier testers and data, and removes outliers
-def remove_outlier(data, function):
-    new_data = data.copy(True)
-    new_data["TIME"] = new_data["TIME"].astype(int)
-    new_data["SIZE"] = new_data["SIZE"].astype(int)
-    new_data
-    for i in range(4216):
-        start = i * 30
-        end = start+30
-        new_data.loc[start:end, "TIME"] = function(data.loc[start:end, "TIME"])
-        if not i % 420:
-            print(i / 42 , "% done")
-    return new_data
-
-
-# helpers for plot functions
-def sort_maps(test):
-    maps = data[data["TEST"]== test]["MAP"].unique()
-    new = [(gr_max.loc[test, i]["TIME"], i) for i in maps]
-    new.sort()
-    new = [i[1] for i in new]
-    return new
-
-def divider(df, maplist):
-    filters = df['MAP'].isin(maplist)
-    return df[filters]
-
-
-def plotter2(test, data):
-    mydata = data[data["TEST"] == test]
-    maps = sort_maps(test)
-    set1 = divider(mydata, maps[:5])
-    set2 = divider(mydata, maps[5:11])
-    set3 = divider(mydata, maps[11:])
-    
-    plot = sns.lineplot(x="SIZE", y="TIME", hue="MAP", data=set1)
-    plt.xscale("log")
-    plt.xticks(ticks, ticklabels)
-    plot.set_xticklabels(
-        plot.get_xticklabels(), 
-        rotation=55, 
-        horizontalalignment='center',
-        fontweight='light',
-    )
-    plt.ylabel(labels[test][1])
-    plt.legend()
-    plt.title(labels[test][0])
-    plt.savefig("./plots/{}/{}.png".format(test,1))
-    plt.clf()
-    
-    plot = sns.lineplot(x="SIZE", y="TIME", hue="MAP", data=set2)
-    plt.xscale("log")
-    plt.xticks(ticks, ticklabels)
-    plot.set_xticklabels(
-        plot.get_xticklabels(), 
-        rotation=55, 
-        horizontalalignment='center',
-        fontweight='light',
-        )
-    plt.ylabel(labels[test][1])
-    plt.legend()
-    plt.title(labels[test][0])
-    plt.savefig("./plots/{}/{}.png".format(test,2))
-    plt.clf()
-    
-    plot = sns.lineplot(x="SIZE", y="TIME", hue="MAP", data=set2)
-    plt.xscale("log")
-    plt.xticks(ticks, ticklabels)
-    plot.set_xticklabels(
-        plot.get_xticklabels(), 
-        rotation=55, 
-        horizontalalignment='center',
-        fontweight='light',
-    )
-    plt.ylabel(labels[test][1])
-    plt.legend()
-    plt.title(labels[test][0])
-    plt.savefig("./plots/{}/{}.png".format(test,3))
-    plt.clf()
-
-
-    
-
-
-
-# In[4]:
-
-
-data = remove_outlier(onmodded, remove_with_modified_z_score)
-groups = data.groupby(["TEST", "MAP"])
-gr_max = groups.max()
-gr_mean = groups.mean()
-
-
-# In[5]:
-
-
-tests = data["TEST"].unique()
-for i in tests:
-    plotter2(i, data)
-
-
-# In[6]:
-
-
-
-
-# In[ ]:
-
-
-
-
-
-# In[ ]:
-
-
-
-
-
-# In[ ]:
-
-
-
-

plot_stuff.py

@@ -1,90 +0,0 @@
-import seaborn as sns
-import pandas as pd
-from pandas import DataFrame, Series
-import matplotlib.pyplot as plt
-
-import pathlib
-import os
-plt.rcParams["figure.figsize"] = (40, 5)
-sns.set()
-
-## new cell
-cols = [
-    "TEST", "MAP", '50000', '100000', '150000', '200000', '250000', '300000', '350000', '400000',
-    '500000', '600000', '700000', '800000', '900000', '1000000', '2000000', '3000000',
-    '4000000', '5000000', '6000000', '7000000', '8000000', '9000000', '10000000', '15000000',
-    '20000000', '25000000', '30000000', '35000000', '40000000', '45000000', '50000000'
-]
-data = pd.read_csv("results.csv", quotechar="'", header=None)
-data.columns = cols
-# data.head()
-
-## new cell
-groups = data.groupby(["TEST", "MAP"])
-groups_mean = groups.mean()
-groups_std = groups.std()
-
-## new cell
-def max_val(hmap, test):
-    return groups_mean.loc[test, hmap].max()
-
-def sort_maps(test):
-    maps = list(groups_mean.loc[test].index)
-    new = [(max_val(i, test), i) for i in maps]
-    new.sort()
-    new = [i[1] for i in new]
-    return new
-
-
-
-def plot_test(test, include_error=True, log=False):
-    sizes = [50000, 100000, 150000, 200000, 250000, 300000, 350000, 400000, 500000,
-        600000, 700000, 800000, 900000, 1000000,
-        2000000, 3000000, 4000000, 5000000, 6000000, 7000000, 8000000, 9000000, 10000000,
-        15000000, 20000000, 25000000, 30000000, 35000000, 40000000, 45000000, 50000000]
-    maps = sort_maps(test)
-    # print(maps)
-    count = 16
-    repeats = [0, 5, 11]
-    while count > -1:
-        if not count and count not in repeats:
-            break
-        mp = maps[count]
-        if include_error:
-            plt.errorbar(groups_mean.columns,groups_mean.loc[test, mp], yerr=groups_std.loc[test, mp], label=mp)
-        else:
-            plt.plot(groups_mean.columns, groups_mean.loc[test, mp], label=mp)
-
-        if count in repeats:
-            if log:
-                plt.xscale("log")
-            plt.ylabel("{} time (ns)".format(test))
-            
-            plt.legend()
-            plt.title(test)
-            plt.savefig("./plots/{}/{}.png".format(test,count))
-            plt.clf()
-            # plt.show()
-            
-            repeats.pop(repeats.index(count))
-        else:
-            count -=1
-## new cell
-
-tests = data["TEST"].unique()
-p = pathlib.Path("./plots")
-if not p.is_dir():
-    p.mkdir()
-for i in tests:
-    path = pathlib.Path("./plots/{}/".format(i))
-    if not path.is_dir():
-        path.mkdir()
-    print(i)
-    plot_test(i, False)
-    # break
-
-
-    
-        
-
-

readme.md

@@ -1,5 +1,8 @@
 # Files and what they contain
 
+# HTML export for those who don't have a data science stack + python installed
+[last_attempt.html](./last_attempt.html)
+
 ## results.csv
 
 [Results.csv](./results.csv) has the raw data as outputed by the benchmark code
@@ -17,12 +20,13 @@ to
 
 ## new_repr_no_outlier.csv
 
-[New_repr.csv](./new_repr_no_outlier.csv) has the data from no_repr but with outliers removed with the modified z score test
+[new_repr_no_outlier.csv](./new_repr_no_outlier.csv) has the data from no_repr but with outliers removed with the modified z score test
 
 # Notebooks
 
-## Better_plotting
-better plotting is an incomplete and now broken notebook where we attempted to plot on the raw results
-
 ## Last_attempt
 Last attempt has our last attempt at plotting, plus some random stuff at the end
+
+
+
+

to.py

@@ -1,28 +0,0 @@
-styles = {'absl::flat_hash_map': ["#0000cc", "--"],  # blue
-          "absl::node_hash_map'": ["#3366ff", "--"],
-          'absl::node_hash_map': ["#99ccff", "--"],
-
-          'google::dense_hash_map': ["#ff0000", "-."],  # reds
-          'google::sparse_hash_map': ["#ff6666", "-,"],
-          'phmap::parallel_flat_hash_map': ["#ff0066", "-."],
-
-          'ska::bytell_hash_map': ["#009933", "- "],  # greens
-          'ska::flat_hash_map': ["#33cc33", "- "],
-          'ska::unordered_map': ["#99ff66", "- "],
-
-          'tsl::hopscotch_map': ["#9900cc", ":"],  # purples
-          'tsl::robin_map': ["#cc33ff", ":"],
-          'tsl::sparse_map': ["#cc99ff", ":"],
-
-          'robin_hood::unordered_flat_map': ["#ffcc99", ".."],
-          'robin_hood::unordered_node_map': ["#ccff66", ".."],
-
-          'boost::unordered::unordered_map': ["#663300", "solid"],  # brown
-
-          'emilib::HashMap': ["#9900cc", "solid"],  # purple
-
-          # weird orange
-          'phmap::parallel_node_hash_map': ["#ffcc66", "solid"],
-
-          'std::unordered_map': ["#000000", "solid"],  # black
-          }