Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+visualizations/cluster_comparison.png filter=lfs diff=lfs merge=lfs -text
+visualizations/optimal_k_analysis.png filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,2 @@
+# Jupyter Notebook Checkpoints
+.ipynb_checkpoints/ 

data/customer_data.csv

@@ -0,0 +1,301 @@
+Age,Income
+27.483570765056164,34109.51252187612
+24.308678494144075,30435.235341190855
+28.23844269050346,28504.96324767066
+32.61514928204013,30458.803882677512
+23.829233126383322,20062.155426995538
+23.8293152152541,28901.64056081244
+32.896064077536955,31785.562857558733
+28.837173645764544,37389.47022370758
+22.65262807032524,27408.648908631763
+27.712800217929825,25957.53198553406
+22.682911535937688,27491.214782077317
+22.671351232148716,34577.01058851037
+26.20981135783017,31643.75554829842
+18.0,27351.198981164805
+18.0,32566.33716556678
+22.188562353795138,30485.3877467402
+19.93584439832788,34843.224952664445
+26.571236662976368,26489.734530613237
+20.459879622393945,28361.68926701116
+18.0,28039.45923433921
+32.32824384460777,22682.42525933941
+23.871118497567323,31480.60138532288
+25.33764102343962,31305.276360899446
+18.0,30025.567283212305
+22.278086377374088,28827.064333124265
+25.55461294854933,22923.14628974793
+19.245032112888484,27896.773386173205
+26.87849009172836,28286.427417366154
+21.996806550405974,25988.613653891905
+23.541531251033618,29193.571441669956
+21.991466938853016,32020.254284072693
+34.26139092254469,39430.92950605265
+24.93251387631033,30872.889064159193
+19.7114453552205,31287.75195361382
+29.112724560515947,29627.770421169163
+18.895781750144888,20406.14392350479
+26.044317975023777,29867.430622753916
+18.0,30301.15104970513
+18.359069755507846,42316.21056242643
+25.984306179345616,29038.19517609439
+28.692332899977053,31507.73671166806
+25.85684140594985,29826.441151473784
+24.421758588058797,24156.60981190234
+23.494481522053555,35714.1140725751
+18.0,33759.66516343387
+21.400778958026457,33955.15973521523
+22.696806145201062,25453.062726026306
+30.28561113109458,37013.971554680495
+26.71809144784231,22990.744686038597
+18.0,32934.28546900135
+26.620419846973974,40952.27812904989
+23.074588597918417,25047.31837434656
+21.615389998470206,27168.51135198614
+28.05838144420434,30498.256825438206
+30.154997612479754,27482.621729419003
+29.656400595580994,22246.682844669336
+20.803912383886807,30342.814874030137
+23.453938120743928,24688.481431369477
+26.65631715701782,32367.962153175908
+29.877725635611796,25402.878828830984
+22.60412881077355,37749.6720250877
+24.071705116680914,26083.733538318815
+19.46832512996986,28389.692418971623
+19.018966879596647,34067.58608684835
+29.062629111970992,23845.678417830222
+31.781200142854114,31137.299673020647
+24.63994939209833,36535.71377141214
+30.01766448946012,21962.583827193863
+26.80818012523817,30923.16929266152
+21.77440122697438,31299.413971242117
+26.80697802754207,33909.11435888655
+32.690182832329846,23815.24644560959
+24.820869804450243,23397.716934578617
+32.82321827907003,32609.707828084487
+18.0,31484.92336616593
+47.003942802767014,88711.60477573893
+47.77158567597581,80514.2401527637
+39.559802227372074,71378.04177656554
+46.85802957728803,74277.57032592026
+47.34457978638945,85436.7819914774
+39.28518865578906,74157.0669462629
+59.926196089158054,81731.6687166558
+48.7906633672943,80364.57471923051
+35.46957202237881,74787.19721915346
+50.25242886907064,97151.5527146026
+37.20254663818143,85071.35217854408
+51.296676829939614,63798.85930673914
+54.26876463205923,81491.63451815542
+38.43454145318631,74705.7082818529
+52.70700903395458,86819.46667836979
+48.30224741549198,73659.8340925384
+51.57648127995592,79082.1084682648
+60.17434386123158,84039.89823184366
+43.036895071977035,86926.04155336098
+38.970110685140085,70397.6287435538
+37.88388456299582,77323.99011327242
+38.47351772027649,76200.43751071235
+44.383186324687166,74773.36613941031
+47.72921579853315,94123.63392224877
+47.213526394640155,83239.85368768765
+51.61746599228819,69912.92836531963
+45.10401513502325,87342.89557643821
+56.62827261725853,96977.24957610107
+42.88274533409635,88259.72208440918
+66.76135333271695,67845.0402723679
+50.00533878212005,76126.12741706999
+38.14273954866974,90135.28919349298
+36.4328600155111,74338.64427504975
+48.85977932194548,83550.55542516983
+43.21229771739319,86197.0724274347
+50.71200395273674,72584.55622737533
+48.78590099658836,79523.7971515056
+44.417368698745015,54069.86127944742
+38.22565025545276,71804.89886932568
+32.88122220251309,77979.45478885472
+41.42788038346383,70017.73454428121
+51.85119035458778,93059.29043145308
+46.71274995304163,68558.86897631495
+35.03408977030409,76479.64410642414
+46.385447406809455,81045.92461828873
+48.08253903783069,91530.18631252892
+37.92914051039094,68513.10279056449
+46.22980084756422,89305.31001723968
+45.465669747568,80081.8644881567
+35.85623761735501,72147.9307916164
+47.86229888278626,83696.82779410617
+49.486276210945874,81592.47756458777
+53.66440994540221,75198.26498272964
+53.43041641627922,80558.41667992015
+33.97864505634327,76917.49122510591
+37.49739968067902,80908.13876200998
+49.12028213766928,85297.04539616837
+49.11028760729767,92688.13452916281
+49.12038149044838,70097.47600938521
+70.0,97064.26699725013
+49.56712408554534,64383.297603819985
+54.08452512144479,78785.71923971534
+52.63201410794562,84706.53765187661
+50.21113001044638,82247.93494188026
+42.47784604287723,75018.40384143525
+51.071753763946134,78335.0219971418
+38.817398283699426,76055.99252272934
+43.10545114607993,75285.08194444631
+41.11709161736717,86796.8167761682
+45.65499311509058,82856.12388772037
+63.51726853338807,74456.72323791476
+30.061878459266012,87196.799003466
+50.49008152299611,82458.39616701288
+32.09827303048279,86502.89695071169
+41.22454507368453,85037.0307353889
+30.026029934467566,50395.914622671706
+31.63891375881818,60233.92382032407
+39.48376163073957,56100.05203443011
+38.66222159260079,68138.81759930603
+34.87459043621511,50150.21028786909
+35.70396429985269,49961.66894691534
+42.66598937473055,51403.644127335865
+31.45057166698502,42256.62565414116
+38.28258428702023,51845.46986991543
+33.78684408539664,50445.204030677814
+33.69391278063668,55902.36271885724
+41.59266111192314,57050.53585466296
+39.95249809392818,66257.02503529532
+39.88105781600383,60702.5430291163
+42.83287284292597,51538.578066025584
+35.12602304979655,49609.51197190985
+39.091717827769784,57951.51502903904
+33.13839946043927,47078.60075787615
+36.944998114930655,65988.75259512612
+34.21914167379389,62076.64072432772
+35.58197578995631,52184.94608737177
+38.570942152621484,44721.19282545473
+30.090675900599166,63123.234244992476
+47.554323654112764,54312.76092848429
+28.96389571100179,62426.89787184077
+27.714868323273606,45433.4340472338
+41.948665241000406,51403.749862277364
+39.74997616377762,55031.4621983091
+38.74471890231293,55281.88356258845
+38.77007305558568,52299.60717112454
+34.92651936291851,58737.09959408499
+29.616473771085012,48594.277423704436
+35.45482734916236,54145.72308987224
+30.93702973092733,55721.77379027139
+40.85071840050651,58086.633004352494
+34.117655710987165,59269.68926853334
+30.04701681924493,48252.147448972784
+33.07168495008204,45795.31497558627
+37.477588725653746,62666.06093139105
+31.61765268317615,56993.88407187755
+30.06667762660141,50509.080780660675
+36.46212326895147,64306.911853135134
+36.46979942665234,55694.04780575715
+31.958340947773223,62075.78310438296
+32.17377016629006,55405.11088846065
+36.39229962414582,67364.48754929192
+26.311493951016054,65532.045054659226
+26.55521735374067,53506.21510912556
+30.689334672485383,60829.425705726135
+33.71931708972892,58872.25569751088
+36.865445393588026,63211.78934519409
+43.85213730169731,49210.459236519375
+40.145957739212115,59116.308759990636
+34.040368820219435,61350.54692109753
+34.88590275258387,44447.56308146132
+28.984823812173147,47900.44892400535
+34.888921184045664,42764.6069334394
+33.268048166479176,53383.558993332656
+36.93631136202854,59305.25353477577
+30.03661433868606,64014.14231257617
+38.11607908544703,55444.56868251865
+44.196433478015464,64771.69327342775
+34.34743910925886,46719.39125071065
+37.41027033259365,44779.70536386907
+39.14086395026668,54666.71380662029
+32.59267716868498,57304.39269363584
+36.3445548908625,54803.83151143544
+35.07555440469077,42595.34739976074
+35.58605659129299,54465.27976292327
+30.3619412968672,47173.18299697088
+35.147061045553656,59018.03529298023
+37.987989747472696,57199.58947658109
+43.70686164677025,49360.72128203587
+40.75562495651124,51916.79849597984
+47.91909474506934,48644.71886866629
+54.37320902726828,81951.17899335481
+64.55142320501238,83724.57562116838
+45.14273953664456,100480.84946661381
+60.040465155178445,102597.22501721482
+49.697423816275595,90956.83374895592
+47.07127167737656,106385.92458777374
+53.929696400454425,83384.7993773104
+44.64757677580626,99339.20201352684
+49.46350694652818,87889.83800237543
+43.021221074111516,93481.6389219784
+70.0,100473.98671316414
+55.35263551971729,91395.86634716048
+48.00274492007414,96154.44455770175
+57.13979910734222,110062.9280921444
+53.87671950309171,94231.08130476851
+52.790304004667775,108356.92112065142
+61.14166700043425,88702.93145342382
+62.57507710047305,105298.04177915283
+49.69498852389472,114415.686206579
+49.2418175935532,75283.55499872711
+52.24948302848356,92031.04744529523
+31.98078835264415,105770.7212718054
+39.84808937801448,97969.54613957007
+68.66874267444524,103711.4587337131
+70.0,93960.1481328418
+52.50963960443622,100865.897874729
+60.765569630557664,98443.2276460792
+58.112501545435364,111677.82061659807
+70.0,102544.20843301213
+66.19574911434577,103376.02662075202
+53.72082408519233,95881.23033877532
+45.44459559399574,95123.93775927507
+38.93553679742428,95674.41812180378
+57.03463635867223,103944.52142378296
+47.436492547156966,95790.15519179737
+40.77746290402326,102897.74856896413
+48.534271157574736,120754.00798645438
+44.18451996385605,108711.24703431693
+70.0,96739.76467832159
+63.816397569494505,112012.13922163945
+54.92027358683383,95919.24626978449
+69.79944138890026,79618.75464822147
+55.77368307647618,89919.13689082596
+46.38715798671736,81292.08078974145
+70.0,96484.86515958692
+60.38910043684659,100184.18379189551
+44.62753845673544,116764.37312275283
+53.09661321916392,103269.27373764163
+46.24381746615243,97808.99471191136
+41.172002690356635,108294.05581183489
+64.26177547531641,77888.64690992115
+70.0,102356.14558108566
+41.01432426180859,107708.65193886966
+60.62969236690571,85214.13754220158
+48.49357430878173,111437.54043206929
+50.12874616235304,103384.96407494415
+49.07606075761131,95847.12086099198
+46.36009230320184,106327.81866106285
+55.48521627944827,122706.92857804395
+46.69049883588962,101818.66255058495
+57.704568257798385,102482.20586300336
+54.49761890550863,95406.39100459756
+52.6105195313359,91501.55630535209
+45.92436337958402,108303.35816544245
+49.23228669431667,91439.16174091132
+62.55391225825756,100715.66237219392
+60.009171876243805,95223.42553234883
+45.22444755201449,104789.79825746392
+55.99332305429226,103336.62105286948
+62.51387123371789,110375.399442579
+38.305947188786284,94899.83601145253
+60.43360192379935,97301.25064706629
+48.37376241054153,90212.36284217692
+60.70598668593159,95557.06739923889
+47.367408434574834,103773.00493044851

models/dbscan_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0599bfff6985fb13b3e0996781ecdd0c98003bcc06f815ddd1f2a14bfced6848
+size 9967

models/gmm_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1093b308ed67e5df368edc02558d6473efb64ae599e155300f746fb95398fa
+size 1092

models/hierarchical_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf8f3be7ad95f262f2725e62e0116a8c36711843cfa922d5fd013e45f6da1fd8
+size 7717

models/kmeans_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f16a22650c46ee3dad1c8975cc484aac7646304fb1de4cb69315ba6e16fbd46d
+size 1834

models/scaler.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76bebb396818875e801e8ae3755d837ab0ac79bd58705bc8271846da45b4ccaa
+size 498

results/algorithm_comparison.csv

@@ -0,0 +1,5 @@
+Algorithm,Silhouette Score,ARI vs True
+K-Means,0.5537000452752183,0.41898597684663885
+Hierarchical,0.520642563349694,0.3232534610119113
+DBSCAN,0.11803191067383975,0.0
+GMM,0.5487883507919733,0.45337001162039525

results/detailed_analysis.json

@@ -0,0 +1,79 @@
+{
+  "K-Means": {
+    "silhouette_score": 0.5537000452752183,
+    "adjusted_rand_index": 0.41898597684663885,
+    "n_clusters": 2,
+    "cluster_statistics": {
+      "Cluster_0": {
+        "size": 159,
+        "age_mean": 30.422187845693067,
+        "age_std": 6.981503859820691,
+        "income_mean": 44239.89409133459,
+        "income_std": 15533.897625620913
+      },
+      "Cluster_1": {
+        "size": 141,
+        "age_mean": 50.94627258956317,
+        "age_std": 8.60146418458902,
+        "income_mean": 90270.60032281383,
+        "income_std": 12948.39618157893
+      }
+    }
+  },
+  "Hierarchical": {
+    "silhouette_score": 0.520642563349694,
+    "adjusted_rand_index": 0.3232534610119113,
+    "n_clusters": 2,
+    "cluster_statistics": {
+      "Cluster_0": {
+        "size": 180,
+        "age_mean": 31.46694055464164,
+        "age_std": 7.25667648787366,
+        "income_mean": 48769.132085291734,
+        "income_std": 19566.604864644247
+      },
+      "Cluster_1": {
+        "size": 120,
+        "age_mean": 52.970858356317585,
+        "age_std": 7.576333090600229,
+        "income_mean": 91532.11692238698,
+        "income_std": 12835.257179910019
+      }
+    }
+  },
+  "DBSCAN": {
+    "silhouette_score": 0.11803191067383975,
+    "adjusted_rand_index": 0.0,
+    "n_clusters": 1,
+    "cluster_statistics": {
+      "Cluster_0": {
+        "size": 299,
+        "age_mean": 40.095556903815925,
+        "age_std": 12.879072636075085,
+        "income_mean": 65740.89326009079,
+        "income_std": 27048.205749675155
+      }
+    }
+  },
+  "GMM": {
+    "silhouette_score": 0.5487883507919733,
+    "adjusted_rand_index": 0.45337001162039525,
+    "n_clusters": 2,
+    "cluster_statistics": {
+      "Cluster_0": {
+        "size": 157,
+        "age_mean": 30.61151617631749,
+        "age_std": 7.2842280129277,
+        "income_mean": 43483.59337851532,
+        "income_std": 14557.431206884427
+      },
+      "Cluster_1": {
+        "size": 143,
+        "age_mean": 50.451358481900414,
+        "age_std": 9.112097928511313,
+        "income_mean": 90457.1583609234,
+        "income_std": 12388.673659001814
+      }
+    }
+  }
+}

results/experiment_summary.json

@@ -0,0 +1,44 @@
+{
+  "experiment_date": "2025-07-15T20:53:15.486278",
+  "dataset_info": {
+    "type": "synthetic_customer_data",
+    "n_samples": 300,
+    "n_features": 2,
+    "feature_names": [
+      "Age",
+      "Income"
+    ],
+    "true_clusters": 4
+  },
+  "algorithms_tested": [
+    "K-Means",
+    "Hierarchical",
+    "DBSCAN",
+    "GMM"
+  ],
+  "files_created": {
+    "models": [
+      "kmeans_model.pkl",
+      "hierarchical_model.pkl",
+      "dbscan_model.pkl",
+      "gmm_model.pkl",
+      "scaler.pkl"
+    ],
+    "visualizations": [
+      "optimal_k_analysis.png",
+      "cluster_comparison.png"
+    ],
+    "results": [
+      "algorithm_comparison.csv",
+      "detailed_analysis.json"
+    ],
+    "data": [
+      "customer_data.csv"
+    ]
+  },
+  "key_findings": {
+    "best_algorithm": "To be determined from results",
+    "optimal_k": "Found using elbow method and silhouette analysis",
+    "insights": "Customer segmentation reveals distinct spending patterns"
+  }
+}