Participated in the mentoring of both postgraduate and junior petrophysicist from E & P Companies Provide quick look log evaluation and recommend perforation pointĭata collection, data review and validation of Izombe field (45 wells) for FDP: Addax petroleum Limited. Provided quality assurance and formation analysis support at well site Wellsite supervision onshore logging operations, formation evaluation analyses,, VSP data acquisition.
![rokdoc crossplot rokdoc crossplot](https://library.seg.org/cms/10.1190/INT-2019-0157.1/asset/images/medium/figure10.gif)
Participate as an instructor in periodical geosciences training of Nigeria University Application of petrophysical and rock property analysis to predict and understand seismic attribute responses (predicting which attribute, or combination of attributes, best illuminates lithology, reservoir quality, or pore fluid).ĪVO analysis using intercept gradient crossplot to validate seismic amplitude on seismic section.ĭANVIC CONCEPTS INTL. Seismic evaluation and QC with wavelet estimation, seismic tie and intercept & gradient analysis. Perform petrophysical evaluation qc, forward modeling and gradient and intercept analysis using rokdoc to understand the relationship between fluid and lithology in a reservoir interval( Oando PLC) UGE- Field (4 wells) OML 145.ģD seismic modeling using the logged well data / averaged values on a real model. 2015 ? Date)ĭHI, Fault Seal Analysis and Resource Assessment:Team player: probs = model.REIGHSHORE ENERGY SERVICES LTD. Now plot the ROC curve, the output can be viewed on the link provided below. Oob_score=False, random_state=None, verbose=0, Min_weight_fraction_leaf=0.0, n_estimators=10, n_jobs=None, Min_impurity_decrease=0.0, min_impurity_split=None, Max_depth=None, max_features='auto', max_leaf_nodes=None,
![rokdoc crossplot rokdoc crossplot](https://img.yumpu.com/42601678/1/500x640/rock-physics-and-reservoir-characterization-of-a-calcitic-ikon-rokdoc.jpg)
Output: RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini', However, I have used RandomForestClassifier. Now use any algorithm to fit, that is learning the data. Train_X, test_X, train_y, test_y = train_test_split(data_X, cls_lab, test_size=0.3, random_state=1) data_X, cls_lab = make_classification(n_samples=1100, n_classes=2, weights=, random_state=1) Now use the classification and model selection to scrutinize and random division of data. NOTE: Proper indentation and syntax should be used. Plt.title('Receiver Operating Characteristic (ROC) Curve') Plt.plot(,, color='darkblue', linestyle='-') Plt.plot(fper, tper, color='orange', label='ROC') import numpy as npįrom sklearn.datasets import make_classificationįrom sklearn.neighbors import KNeighborsClassifierįrom sklearn.ensemble import RandomForestClassifierįrom sklearn.model_selection import train_test_splitĭefine the function and place the components. Import all the important libraries and functions that are required to understand the ROC curve, for instance, numpy and pandas. True Positive Rate as the name suggests itself stands for ‘real’ sensitivity and It’s opposite False Positive Rate stands for ‘pseudo’ sensitivity.įor further reading and understanding, kindly look into the following link below.Both the parameters are the defining factors for the ROC curve and are known as operating characteristics.TPR stands for True Positive Rate and FPR stands for False Positive Rate.It has one more name that is the relative operating characteristic curve.
![rokdoc crossplot rokdoc crossplot](https://i.ytimg.com/vi/RAzfvVk4vBM/maxresdefault.jpg)
![rokdoc crossplot rokdoc crossplot](http://www.crackcad.com/wp-content/uploads/2019/04/rokdoc-6.6.2.jpg)
#ROKDOC CROSSPLOT HOW TO#
In this tutorial, we will learn an interesting thing that is how to plot the roc curve using the most useful library Scikit-learn in Python.