diff --git a/data analysis/__pycache__/analysis.cpython-37.pyc b/data analysis/__pycache__/analysis.cpython-37.pyc index 1a78a7f0..299a28cf 100644 Binary files a/data analysis/__pycache__/analysis.cpython-37.pyc and b/data analysis/__pycache__/analysis.cpython-37.pyc differ diff --git a/data analysis/__pycache__/titanlearn.cpython-37.pyc b/data analysis/__pycache__/titanlearn.cpython-37.pyc index 7be8234f..5877577c 100644 Binary files a/data analysis/__pycache__/titanlearn.cpython-37.pyc and b/data analysis/__pycache__/titanlearn.cpython-37.pyc differ diff --git a/data analysis/analysis.py b/data analysis/analysis.py index ece02176..c3cc4fd0 100644 --- a/data analysis/analysis.py +++ b/data analysis/analysis.py @@ -758,7 +758,7 @@ def optimize_regression(x, y, _range, resolution):#_range in poly regression is x_test = [] y_test = [] - for i in range (0, math.floor(len(x) * 0.4), 1): + for i in range (0, math.floor(len(x) * 0.5), 1): index = random.randint(0, len(x) - 1) x_test.append(x[index]) diff --git a/data analysis/data/scores.csv b/data analysis/data/scores.csv new file mode 100644 index 00000000..5562ec8a --- /dev/null +++ b/data analysis/data/scores.csv @@ -0,0 +1 @@ +2022, 21, 23, 39, 50, 89, 97, 191, 213, 233, 236, 272, 289, 308, 310, 314, 317, 329, 355, 428, 436 2011, 1, 25, 34, 106, 112, 132, 146, 167, 184, 223, 256, 267, 304, 337, 339, 370, 411, 460, 485, 494 1101, 7, 11, 55, 81, 92, 144, 151, 157, 165, 174, 177, 220, 241, 312, 320, 341, 343, 347, 419, 473 821374, 6, 9, 11, 28, 31, 194, 200, 201, 246, 298, 340, 351, 355, 364, 388, 395, 414, 422, 429, 442 5, 33, 73, 102, 103, 137, 183, 200, 212, 218, 242, 249, 264, 294, 302, 310, 378, 400, 408, 457, 473 \ No newline at end of file diff --git a/data analysis/superscript.py b/data analysis/superscript.py index 90b23298..4371e8b7 100644 --- a/data analysis/superscript.py +++ b/data analysis/superscript.py @@ -41,6 +41,7 @@ import firebase_admin from firebase_admin import credentials from firebase_admin import firestore import analysis +import titanlearn import visualization import os import sys @@ -59,7 +60,7 @@ def titanservice(): file_list = glob.glob(source_dir + '/*.csv') #supposedly sorts by alphabetical order, skips reading teams.csv because of redundancy data = [] files = [fn for fn in glob.glob('data/*.csv') - if not os.path.basename(fn).startswith('teams')] + if not (os.path.basename(fn).startswith('teams'))] #scores will be handled sperately for i in files: data.append(analysis.load_csv(i)) @@ -67,6 +68,7 @@ def titanservice(): stats = [] measure_stats = [] teams = analysis.load_csv("data/teams.csv") + scores = analysis.load_csv("data/scores.csv") end = time.time() @@ -111,19 +113,82 @@ def titanservice(): r2best_curve.pop(0) #print(r2best_curve) + - measure_stats.append(teams[i] + ["|"] + list(analysis.basic_stats(line, 0, 0)) + ["|"] + list(analysis.histo_analysis(line, 1, -3, 3)) + ["|"] + ofbest_curve + ["|"] + r2best_curve) + measure_stats.append(teams[i] + list(analysis.basic_stats(line, 0, 0)) + list(analysis.histo_analysis(line, 1, -3, 3)) + ofbest_curve + r2best_curve) stats.append(list(measure_stats)) - - json_out = {} + nishant = [] + for i in range(len(scores)): + + ofbest_curve = [None] + r2best_curve = [None] + + line = measure[i] + + #print(line) + + x = list(range(len(line))) + eqs, rmss, r2s, overfit = analysis.optimize_regression(x, line, 10, 1) + + beqs, brmss, br2s, boverfit = analysis.select_best_regression(eqs, rmss, r2s, overfit, "min_overfit") + + #print(eqs, rmss, r2s, overfit) - for i in range(len(stats)): - json_out[files[i]]=str(stats[i]) + ofbest_curve.append(beqs) + ofbest_curve.append(brmss) + ofbest_curve.append(br2s) + ofbest_curve.append(boverfit) + ofbest_curve.pop(0) - #print(json_out) + #print(ofbest_curve) - db.collection(u'stats').document(u'stats-noNN').set(json_out) + beqs, brmss, br2s, boverfit = analysis.select_best_regression(eqs, rmss, r2s, overfit, "max_r2s") + + r2best_curve.append(beqs) + r2best_curve.append(brmss) + r2best_curve.append(br2s) + r2best_curve.append(boverfit) + r2best_curve.pop(0) + + #print(r2best_curve) + + z = len(scores[0]) + 1 + nis_num = [] + + nis_num.append(eval(str(ofbest_curve[0]))) + nis_num.append(eval(str(r2best_curve[0]))) + + nis_num.append((eval(ofbest_curve[0]) + eval(r2best_curve[0])) / 2) + + nishant.append(teams[i] + nis_num) + + json_out = {} + score_out = {} + + #print(stats) + + for i in range(len(teams)): + json_out[str(teams[i][0])] = (stats[0][i]) + + for i in range(len(teams)): + score_out[str(teams[i][0])] = (nishant[i]) + + print(json_out) + + #print(json_out.get('5')) + + location = db.collection(u'stats').document(u'stats-noNN') + for i in range(len(teams)): + general_general_stats = location.collection(teams[i][0]) + for j in range(len(files)): + general_general_stats.document(files[j]).set({'stats':json_out.get(teams[i][0])}) + + for i in range(len(teams)): + nnum = location.collection(teams[i][0]).document(u'nishant_number').set({'nishant':score_out.get(teams[i][0])}) + + #general_general_stats.collection().document('stats').set() + #db.collection(u'stats').document(u'stats-noNN').set(score_out) def pulldata(): #TODO @@ -173,3 +238,4 @@ firebase_admin.initialize_app(cred) db = firestore.client() service() #finally we write something that isn't a function definition +#titanservice() diff --git a/data analysis/titanlearn.py b/data analysis/titanlearn.py index 0578a875..a32bceaa 100644 --- a/data analysis/titanlearn.py +++ b/data analysis/titanlearn.py @@ -198,4 +198,4 @@ def retyuoipufdyu(): model = linear_nn(8, 100, 1, 20, act_fn = "relu") print(model) return train_sgd_simple(model,"regression", data, ground, learnrate=1e-4, iters=1000) -retyuoipufdyu() +#retyuoipufdyu()