diff --git a/12.prezentacja/Prezentacja.ipynb b/12.prezentacja/Prezentacja.ipynb new file mode 100644 index 0000000..01e379c --- /dev/null +++ b/12.prezentacja/Prezentacja.ipynb @@ -0,0 +1,513 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "9dfc3fde", + "metadata": {}, + "source": [ + "## Machine Learning Engineer / Data Scientist\n", + "### Apple\n", + "##### San Diego, CA\n", + "\n", + "As a Machine Learning Engineer / Data Scientist within the Ground Truth Systems Team, you will be part of a team building infrastructure and tools for exciting new technologies that will shape our future. We build web services that work at scale to support new products and also enable Machine Learning development workflows. We are looking for a Machine learning (ML) engineer with a broad experience and knowledge in machine/deep learning and computer vision. You will be part of every stage of development from concept to deployment. The Engineer will be working on cutting edge problems in efficient data annotation building ML models that assist humans in reducing labeling efforts without sacrificing quality.\n", + "\n", + "[link](https://www.linkedin.com/jobs/view/2584308794/?eBP=CwEAAAF6CRxknubs856bz_PHS2RwzxBP22k1Www5KO5SwXHAQzHjLnnBf0OqUYJcFuFPxT9_Ni3NOqrfW2ccoRpXlXfZ2m16H04HabnJK6Qtlt03gBHOCntkR5hbRtX6xEZWUZacGCK1YSIP4g5qqPAEhXnucz2qIFyG__8-QDkprPpMWGa8Zaz2V_rE6DSGPSisLpBAZjzytc7gRut77Ct6qPeZr7oCZ3MT-0zaDLt8VJqb9lsuvOMdYGyy5GEAxSSClKRkVIjEgpKYWxG2txssbkp8OIr1bG94isk9-SswwCoEmZm6IdaTZtcHV2gspusSDgUqkqM6j0IgexWVt_hJMfzQXRMOQr40maY0OTJ6vFQt1zLR1YglO-TiE67wcpA&recommendedFlavor=SCHOOL_RECRUIT&refId=5UIq6O5Ixb7BM93P6KM9Ow%3D%3D&trackingId=LIZwq23GVUlSLmsiNqIf9g%3D%3D&trk=flagship3_search_srp_jobs)" + ] + }, + { + "cell_type": "markdown", + "id": "bcc3cfa4", + "metadata": {}, + "source": [ + "## Data Scientist\n", + "### TikTok\n", + "##### Mountain View, CA\n", + "\n", + "- Develop comprehensive product metrics and quantitative measurement structure based on product stages and business purposes.\n", + "\n", + "- Implement standardized product reports, ad hoc queries, and data related projects\n", + "\n", + "- Design and implement reporting dashboards and the associated data pipeline to deliver insights and improve the workflows of internal teams\n", + "\n", + "- Partner closely with key stakeholders to optimize overall product adoption and performance driven growth. Provide suggestions for improvements to align with the business goal\n", + "\n", + "- Measure and visualize the effectiveness of product updates, conduct research and analysis on various business processes to identify business problems, and further provide optimization suggestions to improve operating efficiency\n", + "\n", + "[link](https://www.linkedin.com/jobs/view/2571802899/?eBP=CwEAAAF6CRxknhlqp224nAtkRSzwDm7a0IyxC0dMZRQDu9mnozaAa0te00pANtBORJU7ga8tNXtQeOiAEpFh6G2zaIrSsmLyLLLKhnLvA4xJ7Y1OgxcwuR2T11he_AJxnVe4-SABBmzu2I1sb6g061gdKWFb8bivgMwY2COaXdL5XDKDLQ4rIOShRAxvQOBHPfEs8nTOBF0oxEex3LS9iTzavr4g-ObUKc7CQNYbSUCwLnTH6fkKBrtfwgq51EzHiiIw2wYiWKm9guveUUR3dWh1VeCwYNZ7ajIeLhbG_TZpD1jV2Nhhr7SxFmc-OxJkTS2z0143md3Yy1pvMOGLtVGaOIyGpecfqwPTrgDw6-NEl6kf5zwpCQgUG5R7sXV9&recommendedFlavor=SCHOOL_RECRUIT&refId=5UIq6O5Ixb7BM93P6KM9Ow%3D%3D&trackingId=YHXKHwxjJYcwMSB1DvrMiQ%3D%3D&trk=flagship3_search_srp_jobs)" + ] + }, + { + "cell_type": "markdown", + "id": "3653d133", + "metadata": {}, + "source": [ + "## Data Scientist, Analytics\n", + "### Facebook\n", + "##### Los Angeles, CA\n", + "\n", + "- Work with large and complex data sets to solve a wide array of challenging problems using different analytical and statistical approaches.\n", + "- Apply technical expertise with quantitative analysis, experimentation, data mining, and the presentation of data to develop strategies for our products that serve billions of people and hundreds of millions of businesses.\n", + "- Identify and measure success of product efforts through goal setting, forecasting, and monitoring of key product metrics to understand trends.\n", + "- Define, understand, and test opportunities and levers to improve the product, and drive roadmaps through your insights and recommendations.\n", + "- Partner with Product, Engineering, and cross-functional teams to inform, influence, support, and execute product strategy and investment decisions.\n", + " \n", + "[link](https://www.linkedin.com/jobs/view/2588110784/?eBP=JOB_SEARCH_ORGANIC&recommendedFlavor=SCHOOL_RECRUIT&refId=5UIq6O5Ixb7BM93P6KM9Ow%3D%3D&trackingId=Kdo6mVCV4CNabYcLscppyg%3D%3D&trk=flagship3_search_srp_jobs)" + ] + }, + { + "cell_type": "markdown", + "id": "93eb962f", + "metadata": {}, + "source": [ + "## Data Scientist\n", + "### Amazon\n", + "##### Nowy Jork, NY \n", + "\n", + "- Design, build and automate datasets to scale and support business needs, allowing you to focus on answering hard and ambiguous question\n", + "- Identify, develop, manage, and execute research to uncover areas of opportunity and present recommendations that will shape the future of the retail website\n", + "- Collaborate with Qualitative Researchers on an iterative approach to a deep understanding of our customers and their behaviors\n", + "- Retrieve and analyze data using a broad set of Amazon’s data technologies and resources, knowing how, when, and which to use.\n", + "- Collaborate with product, technical, business, marketing, finance, and UX leaders to gather data and metrics requirements.\n", + "- Design, drive and analyze experiments to form actionable recommendations. Present recommendations to business leaders and drive decisions.\n", + "- Manage and execute entire projects from start to finish including project management, data gathering and manipulation, synthesis and modeling, problem solving, and communication of insights and recommendations.\n", + "- Develop and document scientific research to be shared with the greater data science community at Amazon\n", + "\n", + "[link](https://www.linkedin.com/jobs/view/2582618509/?eBP=CwEAAAF6CRxknjKsOy5QgUK2dXC1qDGNrXk4dR8gePRmhusuL2O5QLOPhSie5QJ3AKlh3KWHfgga0m8s_V6GrFPkhkVgsR7qGrt2E5iyslmNeU2UjwiwNSBBu-VN2i0lOXG1Dk67lUxNaCZ02NOxtCkSHipsc70BX4Sd7zG1FJcaixzJT9Sx0CTnNs5pPeqSrHBML1_Sb0On9tV9f-6mho0t1jWMPuqZbvFcbsNJvjK1FKTvtb5jukcv0uqn3bndjScGz2WYe4_mAwQFEzgMHw995w0VveQf3X619Iwd60B5fktJrq8fZnC4n3kiYelUs-GlH3U5W6Jopvi_m1nCxkLiJCA9ZFI6opm-4-6AT4-mObZsKTOFyp55U81vkBWyfuE&recommendedFlavor=SCHOOL_RECRUIT&refId=5UIq6O5Ixb7BM93P6KM9Ow%3D%3D&trackingId=qpwlAurNjwYqPhyFViuwtQ%3D%3D&trk=flagship3_search_srp_jobs)" + ] + }, + { + "cell_type": "markdown", + "id": "a7297a20", + "metadata": {}, + "source": [ + "## Data Scientist, Engineering\n", + "### Google\n", + "##### Nowy Jork, NY\n", + "\n", + "As a Data Scientist, you will evaluate and improve Google's products. You will collaborate with a multi-disciplinary team of engineers and analysts on a wide range of problems. This position will bring scientific rigor and statistical methods to the challenges of product creation, development and improvement with an appreciation for the behaviors of the end user.\n", + "\n", + "[link](https://www.linkedin.com/jobs/view/2583397397/?eBP=JOB_SEARCH_ORGANIC&recommendedFlavor=SCHOOL_RECRUIT&refId=5UIq6O5Ixb7BM93P6KM9Ow%3D%3D&trackingId=AJZ8%2BXWmJPjcWRIKX1Fkrw%3D%3D&trk=flagship3_search_srp_jobs)" + ] + }, + { + "cell_type": "markdown", + "id": "f6950af2", + "metadata": {}, + "source": [ + "## Data scientist -Remote\n", + "### Starbucks\n", + "##### Seattle, WA\n", + "\n", + "- Extract and transform data from multiple sources in preparation for exploratory data analysis, modeling, and reporting.\n", + "- Leverage predictive and inferential advanced statistical and machine learning techniques to solve business problems, including methods to surface uncertainty intervals to provide increased context.\n", + "\n", + "- Transform model outputs into formats that are digestible to the end users through visualization, clear tables, and/or thoughtful presentations. Assist technical and non-technical end users in how to leverage and interpret the analysis.\n", + "- Drive innovation by proposing and testing novel techniques and technologies to solve known problems and identify new business problems that can be addressed using data science products developed by the team.\n", + " \n", + "[link](https://www.linkedin.com/jobs/view/2586220311/?eBP=JOB_SEARCH_ORGANIC&recommendedFlavor=SCHOOL_RECRUIT&refId=5UIq6O5Ixb7BM93P6KM9Ow%3D%3D&trackingId=DFMIYo5z2q%2F5DGd13qDGcQ%3D%3D&trk=flagship3_search_srp_jobs)" + ] + }, + { + "cell_type": "markdown", + "id": "abee661a", + "metadata": {}, + "source": [ + "## Data Scientist - Instagram, Core Growth\n", + "### Instagram\n", + "##### Menlo Park, CA\n", + "\n", + "Help Instagram acquire our next wave of new users and tap into new markets and demographics.\n", + "Enable Instagram to grow in a way that is incremental to the Family of Apps and expand our footprint, while maintaining a differentiated experience for our users.\n", + "Have a solid understanding of emerging market growth and ensure that Instagram breaks into new territories, and better understand how users in emerging markets use Instagram differently.\n", + "\n", + "[link](https://www.linkedin.com/jobs/view/2588110859/?eBP=JOB_SEARCH_ORGANIC&recommendedFlavor=SCHOOL_RECRUIT&refId=5UIq6O5Ixb7BM93P6KM9Ow%3D%3D&trackingId=8co2HnRzdFpCMuY3MoLq3Q%3D%3D&trk=flagship3_search_srp_jobs)" + ] + }, + { + "cell_type": "code", + "execution_count": 1, + "id": "291c1ab5", + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
skillsum
0Python6
1SQL5
2Communication and collaboration skills5
3Statistical/mathematical software (e.g. R, Sta...5
4Master’s degree +4
5Bachelor's degree +3
6Ph.D.3
7Experience with large datasets2
8Experience in business analysis2
9Experience in data analysis2
10Experience in product analysis2
11Experience in analytics2
12Counterfactual causal models1
13Advanced competency in working with time serie...1
14sampling methods1
15Synthetic control models1
16Matching approaches1
17Deep knowledge of traditional ML concepts1
18Experience initiating and driving projects1
19Stochastic models1
20Multivariate analysis1
21Experience working in data science in e-commerce1
22Recommendation systems1
23Information retrieval1
24NLP1
25Demand modeling1
26Financial analysis1
27Keras1
28Understanding of algorithms1
29Research science1
30Understanding of data structures1
31Ability to succeed in an innovative and fast-p...2
32Leadership skills1
33Numpy1
34Scipy1
35Statistical analysis1
36PyTorch1
37Tensorflow1
38Previous publication in conferences1
39Regression modeling1
40Data modeling1
41Machine learning1
42Understanding of software design principles1
\n", + "
" + ], + "text/plain": [ + " skill sum\n", + "0 Python 6\n", + "1 SQL 5\n", + "2 Communication and collaboration skills 5\n", + "3 Statistical/mathematical software (e.g. R, Sta... 5\n", + "4 Master’s degree + 4\n", + "5 Bachelor's degree + 3\n", + "6 Ph.D. 3\n", + "7 Experience with large datasets 2\n", + "8 Experience in business analysis 2\n", + "9 Experience in data analysis 2\n", + "10 Experience in product analysis 2\n", + "11 Experience in analytics 2\n", + "12 Counterfactual causal models 1\n", + "13 Advanced competency in working with time serie... 1\n", + "14 sampling methods 1\n", + "15 Synthetic control models 1\n", + "16 Matching approaches 1\n", + "17 Deep knowledge of traditional ML concepts 1\n", + "18 Experience initiating and driving projects 1\n", + "19 Stochastic models 1\n", + "20 Multivariate analysis 1\n", + "21 Experience working in data science in e-commerce 1\n", + "22 Recommendation systems 1\n", + "23 Information retrieval 1\n", + "24 NLP 1\n", + "25 Demand modeling 1\n", + "26 Financial analysis 1\n", + "27 Keras 1\n", + "28 Understanding of algorithms 1\n", + "29 Research science 1\n", + "30 Understanding of data structures 1\n", + "31 Ability to succeed in an innovative and fast-p... 2\n", + "32 Leadership skills 1\n", + "33 Numpy 1\n", + "34 Scipy 1\n", + "35 Statistical analysis 1\n", + "36 PyTorch 1\n", + "37 Tensorflow 1\n", + "38 Previous publication in conferences 1\n", + "39 Regression modeling 1\n", + "40 Data modeling 1\n", + "41 Machine learning 1\n", + "42 Understanding of software design principles 1" + ] + }, + "execution_count": 1, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import pandas as pd\n", + "df = pd.read_csv('skill.csv') \n", + "df" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "id": "20d17d3f", + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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\n", + "text/plain": [ + "
" + ] + }, + "metadata": { + "needs_background": "light" + }, + "output_type": "display_data" + } + ], + "source": [ + "import matplotlib.pyplot as plt\n", + "import numpy as np\n", + "df = df.sort_values(by=['sum'])\n", + "ypos = np.arange(len(df.skill))\n", + "fig = plt.figure(figsize=(10,10))\n", + "ax = fig.add_axes([0,0,1,1])\n", + "ax.barh(df['skill'],df['sum'])\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "id": "9811f409", + "metadata": {}, + "source": [ + "![image](picture1.png)" + ] + }, + { + "cell_type": "markdown", + "id": "bef5f4a5", + "metadata": {}, + "source": [ + "![image](picture2.png)" + ] + }, + { + "cell_type": "markdown", + "id": "41a66038", + "metadata": {}, + "source": [ + "https://plato.stanford.edu/entries/causation-counterfactual/\n", + "\n", + "https://www.youtube.com/watch?v=zkxHWDAefEw" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.8.8" + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} diff --git a/12.prezentacja/picture1.png b/12.prezentacja/picture1.png new file mode 100644 index 0000000..1ca6e03 Binary files /dev/null and b/12.prezentacja/picture1.png differ diff --git a/12.prezentacja/picture2.png b/12.prezentacja/picture2.png new file mode 100644 index 0000000..3b349f7 Binary files /dev/null and b/12.prezentacja/picture2.png differ diff --git a/12.prezentacja/skill.csv b/12.prezentacja/skill.csv new file mode 100644 index 0000000..abecb73 --- /dev/null +++ b/12.prezentacja/skill.csv @@ -0,0 +1,44 @@ +skill,sum +Python,6 +SQL,5 +Communication and collaboration skills,5 +"Statistical/mathematical software (e.g. R, Stata, Matlab).",5 +Master’s degree +,4 +Bachelor's degree +,3 +Ph.D.,3 +Experience with large datasets,2 +Experience in business analysis,2 +Experience in data analysis,2 +Experience in product analysis,2 +Experience in analytics,2 +Counterfactual causal models,1 +Advanced competency in working with time series data,1 +sampling methods,1 +Synthetic control models,1 +Matching approaches,1 +Deep knowledge of traditional ML concepts,1 +Experience initiating and driving projects,1 +Stochastic models,1 +Multivariate analysis,1 +Experience working in data science in e-commerce,1 +Recommendation systems,1 +Information retrieval,1 +NLP,1 +Demand modeling,1 +Financial analysis,1 +Keras,1 +Understanding of algorithms,1 +Research science,1 +Understanding of data structures,1 +Ability to succeed in an innovative and fast-paced environment,2 +Leadership skills,1 +Numpy,1 +Scipy,1 +Statistical analysis,1 +PyTorch,1 +Tensorflow,1 +Previous publication in conferences,1 +Regression modeling,1 +Data modeling,1 +Machine learning,1 +Understanding of software design principles,1