solution to exponea challenge

Exponea_.ipynb_checkpoints_case-checkpoint.ipynb

Exponea_case.ipynb

Exponea_utils.py

BOOL_COLS = {
    'Dependent-Company Status': str, # to bool
    'Has the team size grown': str, # to bool
    'Presence of a top angel or venture fund in previous round of investment': str, # to bool
    'Worked in top companies': str, # to bool
    'Have been part of startups in the past?': str, # to bool
    'Have been part of successful startups in the past?': str, # to bool
    'Was he or she partner in Big 5 consulting?': str, # to bool
    'Consulting experience?': str, # to bool
    'Focus on consumer data?': str, # to bool
    'Subscription based business': str, # to bool
    'Capital intensive business e.g. e-commerce, Engineering products and operations can also \
cause a business to be capital intensive': str, # to bool
    'Crowdsourcing based business': str, # to bool
    'Crowdfunding based business': str, # to bool
    'Machine Learning based business': str, # to bool
    'Predictive Analytics business': str, # to bool
    'Speech analytics business': str, # to bool
    'Prescriptive analytics business': str, # to bool
    'Big Data Business': str, # to bool
    'Cross-Channel Analytics/ marketing channels': str, # to bool
    'Owns data or not? (monetization of data) e.g. Factual': str, # to bool
    'Is the company an aggregator/market place? e.g. Bluekai': str, # to bool
    'Exposure across the globe': str, # to bool
    'Relevance of education to venture': str, # to bool
    'Relevance of experience to venture': str, # to bool
    'Pricing Strategy': str, # to bool
    'Hyper localisation': str, # to bool
    'Long term relationship with other founders': str, # to bool
    'Proprietary or patent position (competitive position)': str, # to bool
    'Barriers of entry for the competitors': str, # to bool
    'Company awards': str, # to bool
    'Controversial history of founder or co founder': str, # to bool
    'Legal risk and intellectual property': str, # to bool
    'Technical proficiencies to analyse and interpret unstructured data': str, # to bool
    'Solutions offered': str, # to bool
    'Invested through global incubation competitions?': str, # to bool
}

DATETIME_COLS = {
    'Est. Founding Date': str, # to datetime
    'Last Funding Date': str, # to datetime and number of days
}

CATEGORY_COLS = {
    'year of founding': int,
    'Industry of company': str, # to category
    'Country of company': str, # to category
    'Continent of company': str, # to category
    'Number of  Sales Support material': str, # to category
    'Average size of companies worked for in the past': str, # to category
    'Product or service company?': str, # to category
    'Focus on structured or unstructured data': str, # to category
    'Catering to product/service across verticals': str, # to category
    'Focus on private or public data?': str, # to category
    'Cloud or platform based serive/product?': str, # to category
    'Local or global player': str, # to category
    'Linear or Non-linear business model': str, # to category
    'Number of  of Partners of company': str, # to category
    'Online or offline venture - physical location based business or online venture?': str, # to category
    'B2C or B2B venture?': str, # to category
    "Top forums like 'Tech crunch' or 'Venture beat' \
talking about the company/model - How much is it being talked about?": str, # to category
    'Average Years of experience for founder and co founder': str, # to category
    'Breadth of experience across verticals': str, # to category
    'Highest education': str, # to category
    'Specialization of highest education': str, # to category
    'Degree from a Tier 1 or Tier 2 university?': str, # to category
    'Renowned in professional circle': str, # to category
    'Experience in selling and building products': str, # to category
    'Top management similarity': str, # to category
    'Number of  of Research publications': str, # to category
    'Team Composition score': str, # to category
    'Dificulty of Obtaining Work force': str, # to category
    'Time to market service or product': str, # to category
    'Employee benefits and salary structures': str, # to category    
    'Client Reputation': str, # to category
    'Disruptiveness of technology': str, # to category
    'Survival through recession, based on existence of the \
company through recession times': str, # to category
    'Gartner hype cycle stage': str, # to category
    'Time to maturity of technology (in years)': str, # to category
}

CATEGORY_COLS = dict.fromkeys(CATEGORY_COLS.keys(), 'category')

INDEX_COL = {
    'Company_Name': str, # to index
}

NUMERIC_COLS = {
    'Age of company in years': int,
    'Internet Activity Score': float,
#     'Short Description of company profile': str,
#     'Focus functions of company': str,
#     'Investors': str,
    'Employee Count': int,
    'Employees count MoM change': float,
    'Last Funding Amount': float,
    'Number of Investors in Seed': int, 
    'Number of Investors in Angel and or VC': int,
    'Number of Co-founders': int,
    'Number of of advisors': int,
    'Team size Senior leadership': int,
    'Team size all employees': int,
    'Number of of repeat investors': int,
    'Experience in Fortune 100 organizations': int,
    'Experience in Fortune 500 organizations': int,
    'Experience in Fortune 1000 organizations': int,
    'Years of education': int,
    'Number of Recognitions for Founders and Co-founders': int,
    'Skills score': float,
    'google page rank of company website': int,
    'Industry trend in investing': float,
    'Number of Direct competitors': int,
    'Employees per year of company existence': float,
    'Last round of funding received (in milionUSD)': float,
    'Time to 1st investment (in months)': int,
    'Avg time to investment - average across all rounds, measured from previous investment': float,
    'Percent_skill_Entrepreneurship': float,
    'Percent_skill_Operations': float,
    'Percent_skill_Engineering': float,
    'Percent_skill_Marketing': float,
    'Percent_skill_Leadership': float,
    'Percent_skill_Data Science': float,
    'Percent_skill_Business Strategy': float,
    'Percent_skill_Product Management': float,
    'Percent_skill_Sales': float,
    'Percent_skill_Domain': float,
    'Percent_skill_Law': float,
    'Percent_skill_Consulting': float,
    'Percent_skill_Finance': float,
    'Percent_skill_Investment': float,
    'Renown score': int
}

ALL_COLS = dict(INDEX_COL.items() + 
                NUMERIC_COLS.items() + 
                DATETIME_COLS.items() + 
                BOOL_COLS.items() + 
                CATEGORY_COLS.items())