git-shogg

def sns_heatmap(dataframe, key_column, key_column_format, chart_title, c_pos_neg):
    # Build out heatmap things
    dataframe['Position'] = range(1,len(dataframe) + 1)
    dataframe['y'] = [(x//10 + 1 if x%10 != 0 else (x//10)) for x in dataframe['Position']]
    dataframe['x'] = [(x%10 if x%10 != 0 else 10) for x in dataframe['Position']]
    # most_bought['normalized_dollars_bought_sold'] = (most_bought['dollars_bought_sold'] - most_bought['dollars_bought_sold'].min()) / (most_bought['dollars_bought_sold'].max()-most_bought['dollars_bought_sold'].min())
    # most_bought['natural_log'] = np.log(most_bought['normalized_dollars_bought_sold'])
    pivot_df = dataframe.pivot(index='y', columns='x', values=key_column)
    
    ticker_labels = np.asarray(dataframe['Ticker']).reshape((10,10))

git-shogg

# --- Functions to support pandas lambda function ---
def calc_pct_bought_sold(this_share_count, last_share_count):
    if this_share_count > 0 and last_share_count == 0:
        return 100
    elif this_share_count == 0 and last_share_count == 0:   # In the rare circumstances that both this share count and last share count are zero return 0.
        return 0
    else:
        return ((this_share_count/last_share_count)-1)*100
 
def calc_dollar_bought_sold(count_bought_sold, last_holding_val, last_share_count, this_holding_val, this_share_count):

git-shogg

# --- Map tickers into the quarterly holding dataframes ---
all_this_qtr_holdings['Ticker'] = all_this_qtr_holdings['CUSIP'].map(dict(cusip_mappings))
all_last_qtr_holdings['Ticker'] = all_last_qtr_holdings['CUSIP'].map(dict(cusip_mappings))
all_this_qtr_holdings['Ticker'] = all_this_qtr_holdings['Ticker'].fillna('N/A')
all_last_qtr_holdings['Ticker'] = all_last_qtr_holdings['Ticker'].fillna('N/A')

git-shogg

# --- Functions for mapping CUSIPs to Tickers ---
def write_cusips_to_txt(cusip_mappings, cusip_mapping_file = 'cusips.txt'):
    '''
    Write cusip mappings to txt. Minimizing the need for API calls. 
    '''
    with open(cusip_mapping_file, 'w') as f:
        f.write(str(cusip_mappings))
    return

def read_cusips_from_txt(cusip_mapping_file='cusips.txt'):

git-shogg

# --- Function for running quick statistics on the dataframe ---
def dataframe_statistics(df, manager_name:str, cik:str):
    '''
    Build out the holdings dataframes with some basic statistics. 
    '''
    df['Portfolio percentage'] = (df['Holding value'] / df['Holding value'].sum()) * 100
    df['Manager Name'] = manager_name
    df['CIK'] = cik
    return df

git-shogg

[{"name":"PAULSON & CO. INC.", "cik":"0001035674"}, 
{"name":"BAUPOST GROUP LLC", "cik":"0001061768"}, 
{"name":"BERKSHIRE HATHAWAY INC", "cik":"0001067983"}, 
{"name":"GREENLIGHT CAPITAL INC", "cik":"0001079114"}, 
{"name":"LONE PINE CAPITAL LLC", "cik":"0001061165"}, 
{"name":"SOROS FUND MANAGEMENT LLC", "cik":"0001029160"}, 
{"name":"APPALOOSA LP", "cik":"0001656456"}, 
{"name":"GOLDMAN SACHS GROUP INC", "cik":"0000886982"},
{"name":"SCION ASSET MANAGEMENT, LLC", "cik":"0001649339"}, 
{"name":"BRIDGEWATER ASSOCIATES, LP", "cik":"0001350694"}, 

git-shogg

#--- Import the Required Libraries ---
import requests
import json
import pandas as pd
import open_figi_key
import time
import seaborn as sns
import numpy as np
import matplotlib.pyplot as plt

git-shogg

###############################################################################
#          6. Remove Weekday Exceptions and Aggregate the Results             #
###############################################################################
# Remove Weekday Exceptions
if weekday_exceptions != None:
    df = df[~df.weekday.isin(weekday_exceptions)]

# Aggregate the Results
df = df.groupby(aggregate_list).agg({'timestamp':['count'],'distance':['mean']})

git-shogg

###############################################################################
#                          5. Setup Useful Columns                            #
###############################################################################
# Determine the distance of each GPS coordinate from your point of interest.
distances_list = []
for lat, long in zip(df['latitude'],df['longitude']):
    distances_list.append(distance.geodesic(point_of_interest,(lat,long)).km)
df['distance'] = distances_list
df = df[df['distance'] < distance_from_point_of_interest]

git-shogg

###############################################################################
#                          4. Unpack the Data                                 #
###############################################################################
df_rows = []
for key in locations:
    timestamp = float(key['timestampMs'])
    latitude = float(key['latitudeE7'])/10000000
    longitude = float(key['longitudeE7'])/10000000
    
    if timestamp >= start_datetime and timestamp <= end_datetime: