{ "cells": [ { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "#Import Necessary Libraries\n", "\n", "# NumPy: For mathematical funcations, array, matrices operations\n", "import numpy as np \n", "\n", "# Graph: Plotting graphs and other visula tools\n", "import pandas as pd\n", "import seaborn as sns\n", "\n", "sns.set_palette(\"muted\")\n", "\n", "# color_palette = sns.color_palette()\n", "# To enable inline plotting graphs\n", "import matplotlib.pyplot as plt\n", "%matplotlib inline\n" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Columns ['ID', 'Age', 'Experience', 'Income', 'ZIP Code', 'Family', 'CCAvg', 'Education', 'Mortgage', 'Personal Loan', 'Securities Account', 'CD Account', 'Online', 'CreditCard']\n", "***********************************************************************************************************************\n", "Columns Map {0: 'ID', 1: 'Age', 2: 'Experience', 3: 'Income', 4: 'ZIP Code', 5: 'Family', 6: 'CCAvg', 7: 'Education', 8: 'Mortgage', 9: 'Personal Loan', 10: 'Securities Account', 11: 'CD Account', 12: 'Online', 13: 'CreditCard'}\n" ] }, { "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", "
IDAgeExperienceIncomeZIP CodeFamilyCCAvgEducationMortgagePersonal LoanSecurities AccountCD AccountOnlineCreditCard
01251499110741.61001000
124519349008931.51001000
233915119472011.01000000
343591009411212.72000000
45358459133041.02000001
\n", "
" ], "text/plain": [ " ID Age Experience Income ZIP Code Family CCAvg Education Mortgage \\\n", "0 1 25 1 49 91107 4 1.6 1 0 \n", "1 2 45 19 34 90089 3 1.5 1 0 \n", "2 3 39 15 11 94720 1 1.0 1 0 \n", "3 4 35 9 100 94112 1 2.7 2 0 \n", "4 5 35 8 45 91330 4 1.0 2 0 \n", "\n", " Personal Loan Securities Account CD Account Online CreditCard \n", "0 0 1 0 0 0 \n", "1 0 1 0 0 0 \n", "2 0 0 0 0 0 \n", "3 0 0 0 0 0 \n", "4 0 0 0 0 1 " ] }, "execution_count": 2, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Import CSV data using pandas data frame\n", "df_original = pd.read_csv('bank.csv')\n", "\n", "# Prepare columns names\n", "df_columns = []\n", "for column in df_original.columns:\n", " df_columns.append(column)\n", "\n", "# Prepare mapping of column names for quick access\n", "df_columns_map = {}\n", "map_index: int = 0\n", "for column in df_columns:\n", " df_columns_map[map_index] = column\n", " map_index = map_index + 1\n", " \n", "print(\"Columns {}\".format(df_columns))\n", "print(\"***********************************************************************************************************************\")\n", "print(\"Columns Map {}\".format(df_columns_map))\n", "\n", "# We have separated out columns and its mapping from data, at any point of time during data analysis or cleaning we \n", "# can directly refer or get data from either index or column identifier\n", "\n", "# See data overview\n", "\n", "df_original.head()" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "RangeIndex: 5000 entries, 0 to 4999\n", "Data columns (total 14 columns):\n", " # Column Non-Null Count Dtype \n", "--- ------ -------------- ----- \n", " 0 ID 5000 non-null int64 \n", " 1 Age 5000 non-null int64 \n", " 2 Experience 5000 non-null int64 \n", " 3 Income 5000 non-null int64 \n", " 4 ZIP Code 5000 non-null int64 \n", " 5 Family 5000 non-null int64 \n", " 6 CCAvg 5000 non-null float64\n", " 7 Education 5000 non-null int64 \n", " 8 Mortgage 5000 non-null int64 \n", " 9 Personal Loan 5000 non-null int64 \n", " 10 Securities Account 5000 non-null int64 \n", " 11 CD Account 5000 non-null int64 \n", " 12 Online 5000 non-null int64 \n", " 13 CreditCard 5000 non-null int64 \n", "dtypes: float64(1), int64(13)\n", "memory usage: 547.0 KB\n" ] } ], "source": [ "# Lets analyse data based on following conditions\n", "# 1. Check whether all rows x colums are loaded as given in question, all data must match before we start to even operate on it.\n", "# 2. Print shape of the data\n", "# 8. Check data types of each field\n", "# 3. Find presence of null or missing values.\n", "# 4. Visually inspect data and check presense of Outliers if there are any and see are \n", "# they enough to drop or need to consider during model building\n", "# 5. Print shape of the data\n", "# 6. Do we need to consider all data columns given in data set for model building\n", "# 7. Find Corr, median, mean, std deviation, min, max for columns.\n", "\n", "# Below is info for our data\n", "\n", "df_original.info();" ] }, { "cell_type": "code", "execution_count": 4, "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", "
countmeanstdmin25%50%75%max
ID5000.02500.5000001443.5200031.01250.752500.53750.255000.0
Age5000.045.33840011.46316623.035.0045.055.0067.0
Experience5000.020.10460011.467954-3.010.0020.030.0043.0
Income5000.073.77420046.0337298.039.0064.098.00224.0
ZIP Code5000.093152.5030002121.8521979307.091911.0093437.094608.0096651.0
Family5000.02.3964001.1476631.01.002.03.004.0
CCAvg5000.01.9379381.7476590.00.701.52.5010.0
Education5000.01.8810000.8398691.01.002.03.003.0
Mortgage5000.056.498800101.7138020.00.000.0101.00635.0
Personal Loan5000.00.0960000.2946210.00.000.00.001.0
Securities Account5000.00.1044000.3058090.00.000.00.001.0
CD Account5000.00.0604000.2382500.00.000.00.001.0
Online5000.00.5968000.4905890.00.001.01.001.0
CreditCard5000.00.2940000.4556370.00.000.01.001.0
\n", "
" ], "text/plain": [ " count mean std min 25% \\\n", "ID 5000.0 2500.500000 1443.520003 1.0 1250.75 \n", "Age 5000.0 45.338400 11.463166 23.0 35.00 \n", "Experience 5000.0 20.104600 11.467954 -3.0 10.00 \n", "Income 5000.0 73.774200 46.033729 8.0 39.00 \n", "ZIP Code 5000.0 93152.503000 2121.852197 9307.0 91911.00 \n", "Family 5000.0 2.396400 1.147663 1.0 1.00 \n", "CCAvg 5000.0 1.937938 1.747659 0.0 0.70 \n", "Education 5000.0 1.881000 0.839869 1.0 1.00 \n", "Mortgage 5000.0 56.498800 101.713802 0.0 0.00 \n", "Personal Loan 5000.0 0.096000 0.294621 0.0 0.00 \n", "Securities Account 5000.0 0.104400 0.305809 0.0 0.00 \n", "CD Account 5000.0 0.060400 0.238250 0.0 0.00 \n", "Online 5000.0 0.596800 0.490589 0.0 0.00 \n", "CreditCard 5000.0 0.294000 0.455637 0.0 0.00 \n", "\n", " 50% 75% max \n", "ID 2500.5 3750.25 5000.0 \n", "Age 45.0 55.00 67.0 \n", "Experience 20.0 30.00 43.0 \n", "Income 64.0 98.00 224.0 \n", "ZIP Code 93437.0 94608.00 96651.0 \n", "Family 2.0 3.00 4.0 \n", "CCAvg 1.5 2.50 10.0 \n", "Education 2.0 3.00 3.0 \n", "Mortgage 0.0 101.00 635.0 \n", "Personal Loan 0.0 0.00 1.0 \n", "Securities Account 0.0 0.00 1.0 \n", "CD Account 0.0 0.00 1.0 \n", "Online 1.0 1.00 1.0 \n", "CreditCard 0.0 1.00 1.0 " ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# 1. Check whether all rows x colums are loaded as given in question, all data must match before we start to even operate on it.\n", "\n", "#df_original.describe() difficult to view hence lets apply transpose() to visually see it better\n", "\n", "df_original.describe().transpose()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### Data Analysis Column Wise\n", "\n", "* ID: seems just a identity representation of row or an item in a data frame, this can be dropped when processing model.\n", "* Age: based on std, q1, q2, q3 seems valid values.\n", "* **Experience**: Look at min, it say *-3 experience* cannot be in negative and this particular needs correction. Ideal values should be 0-80 considering a person started to work at 20 years and lives for max 100 years.\n", "* ZipCode: All values seems fine. If we wish to discard region from the model still our model is not impacted if we drop this column. But at later stage we are predicting, people from which area are accepting more personal loans, then we may need to consider this field mandatorily.\n", "* Family: Data looks ok and can play role like if children are less, then less responsibility and hence no need of loan, but more kids and then sometime people tend to go for extra loan apart from education as well. So this is very important field in model buulding.\n", "* CreditCard: General human assumption i would do that, person who has creditcard is vrey unlikely to go for personal load. But if the need arises for a longer term some data points might be there who has credit card as well as personal loan.\n", "\n", "\n", "Skipping some other fields which are self explanatory.\n" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(5000, 14)" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# From our given data set we have succesfully loaded all columns looking at the column labels\n", "# Lets check shape of the data\n", "df_original.shape\n", "\n", "# Here we see total 5000 rows and 14 colums. " ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "# sns.boxplot(y=\"Age\", orient=\"v\", x=\"Personal Loan\", hue=\"Education\", data=df_original)" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "ID int64\n", "Age int64\n", "Experience int64\n", "Income int64\n", "ZIP Code int64\n", "Family int64\n", "CCAvg float64\n", "Education int64\n", "Mortgage int64\n", "Personal Loan int64\n", "Securities Account int64\n", "CD Account int64\n", "Online int64\n", "CreditCard int64\n", "dtype: object" ] }, "execution_count": 7, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Data types of fields\n", "\n", "df_original.dtypes\n", "\n", "# We see that everything is numeric data and need not need any conversion" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "False" ] }, "execution_count": 8, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Presence of null values or missing values\n", "df_original.isnull().values.any()\n", "\n", "# This tell us that we have for each row x column.\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Check validity for data, as we have seen, there is no missing data in out data frame, but are the values \n", "valid enough like we have seen that experience field has -3 having experience as -3 doesnt add any value to our model\n", "but it may impact our final consideration, this also depends on how many such values are present.\n", "Lets print column colmposition or categories spread of data for suspicious column.\n", "\n", "\n", " " ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Experience has unique data in this range [1, 19, 15, 9, 8, 13, 27, 24, 10, 39, 5, 23, 32, 41, 30, 14, 18, 21, 28, 31, 11, 16, 20, 35, 6, 25, 7, 12, 26, 37, 17, 2, 36, 29, 3, 22, -1, 34, 0, 38, 40, 33, 4, -2, 42, -3, 43]\n" ] }, { "data": { "text/plain": [ "-1 33\n", "-2 15\n", "-3 4\n", "Name: Experience, dtype: int64" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Lets see what are experience range in our data set we have.\n", "\n", "print(\"Experience has unique data in this range {}\".format(df_original[\"Experience\"].unique().tolist()))\n", "\n", "# len(df_original[df_original[\"Experience\"] < 0]['Experience'].unique().tolist())\n", "df_experience = df_original[df_original['Experience'] < 0]\n", "df_experience['Experience'].value_counts()\n", "\n", "# So there are 52 values whose experience is a missing value which constitute ~1 % of data for experience column\n", "# We have few options to deal with this\n", "# - purge this invalid data\n", "# - Replace it with meaning full" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Age experience has unique data in this range [25, 45, 39, 35, 37, 53, 50, 34, 65, 29, 48, 59, 67, 60, 38, 42, 46, 55, 56, 57, 44, 36, 43, 40, 30, 31, 51, 32, 61, 41, 28, 49, 47, 62, 58, 54, 33, 27, 66, 24, 52, 26, 64, 63, 23]\n" ] }, { "data": { "text/plain": [ "35 151\n", "43 149\n", "52 145\n", "58 143\n", "54 143\n", "50 138\n", "41 136\n", "30 136\n", "56 135\n", "34 134\n", "39 133\n", "59 132\n", "57 132\n", "51 129\n", "60 127\n", "45 127\n", "46 127\n", "42 126\n", "40 125\n", "31 125\n", "55 125\n", "62 123\n", "29 123\n", "61 122\n", "44 121\n", "32 120\n", "33 120\n", "48 118\n", "38 115\n", "49 115\n", "47 113\n", "53 112\n", "63 108\n", "36 107\n", "37 106\n", "28 103\n", "27 91\n", "65 80\n", "64 78\n", "26 78\n", "25 53\n", "24 28\n", "66 24\n", "23 12\n", "67 12\n", "Name: Age, dtype: int64" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Lets quickly check Age\n", "\n", "print(\"Age experience has unique data in this range {}\".format(df_original['Age'].unique().tolist()))\n", "# This looks ok.\n", "\n", "#Values count\n", "df_original['Age'].value_counts()\n", "\n", "# There are no suspicious values" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We are able to view visually since values are in thousands range what if it is lakhs. It is not feasible of even a good approach to manually check terminal and see if we have invalid values. In that case we can try to parse the values in fields.\n", "Create a helper method for string, bool, int and other data types. Signature might look like this:\n", "\n", "\n", "```python\n", "def all_int(self, column_int_values_list):\n", " # Iterate over list parsing values\n", "```\n", "\n", "Lets try to check validity of values using parse approach." ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [], "source": [ "# Validate function\n", "\n", "def validate_column(column_as_list, column_name):\n", " print(\"Analysing {} column for unique value {}\".format(column_name, column_as_list))\n", " for value in df_original['Age'].tolist():\n", " try:\n", " value += 1\n", " except TypeError:\n", " print(\"Error identyfying {} in {} column \".format(value, column_name) )\n", " return False\n", " return True \n", " " ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Analysing Age column for unique value [25, 45, 39, 35, 37, 53, 50, 34, 65, 29, 48, 59, 67, 60, 38, 42, 46, 55, 56, 57, 44, 36, 43, 40, 30, 31, 51, 32, 61, 41, 28, 49, 47, 62, 58, 54, 33, 27, 66, 24, 52, 26, 64, 63, 23]\n", "Is Age column valid True\n" ] } ], "source": [ "print(\"Is Age column valid {}\".format(validate_column(df_original['Age'].unique().tolist(), 'Age')))" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Analysing Experience column for unique value [1, 19, 15, 9, 8, 13, 27, 24, 10, 39, 5, 23, 32, 41, 30, 14, 18, 21, 28, 31, 11, 16, 20, 35, 6, 25, 7, 12, 26, 37, 17, 2, 36, 29, 3, 22, -1, 34, 0, 38, 40, 33, 4, -2, 42, -3, 43]\n", "Is Experience column valid True\n" ] } ], "source": [ "print(\"Is Experience column valid {}\".format(validate_column(df_original['Experience'].unique().tolist(), 'Experience')))" ] }, { "cell_type": "code", "execution_count": 14, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Analysing Income column for unique value [49, 34, 11, 100, 45, 29, 72, 22, 81, 180, 105, 114, 40, 112, 130, 193, 21, 25, 63, 62, 43, 152, 83, 158, 48, 119, 35, 41, 18, 50, 121, 71, 141, 80, 84, 60, 132, 104, 52, 194, 8, 131, 190, 44, 139, 93, 188, 39, 125, 32, 20, 115, 69, 85, 135, 12, 133, 19, 82, 109, 42, 78, 51, 113, 118, 64, 161, 94, 15, 74, 30, 38, 9, 92, 61, 73, 70, 149, 98, 128, 31, 58, 54, 124, 163, 24, 79, 134, 23, 13, 138, 171, 168, 65, 10, 148, 159, 169, 144, 165, 59, 68, 91, 172, 55, 155, 53, 89, 28, 75, 170, 120, 99, 111, 33, 129, 122, 150, 195, 110, 101, 191, 140, 153, 173, 174, 90, 179, 145, 200, 183, 182, 88, 160, 205, 164, 14, 175, 103, 108, 185, 204, 154, 102, 192, 202, 162, 142, 95, 184, 181, 143, 123, 178, 198, 201, 203, 189, 151, 199, 224, 218]\n", "Is Income column valid True\n" ] } ], "source": [ "print(\"Is Income column valid {}\".format(validate_column(df_original['Income'].unique().tolist(), 'Income')))" ] }, { "cell_type": "code", "execution_count": 15, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Analysing ZIP Code column for unique value [91107, 90089, 94720, 94112, 91330, 92121, 91711, 93943, 93023, 94710, 90277, 93106, 94920, 91741, 95054, 95010, 94305, 91604, 94015, 90095, 91320, 95521, 95064, 90064, 94539, 94104, 94117, 94801, 94035, 92647, 95814, 94114, 94115, 92672, 94122, 90019, 95616, 94065, 95014, 91380, 95747, 92373, 92093, 94005, 90245, 95819, 94022, 90404, 93407, 94523, 90024, 91360, 95670, 95123, 90045, 91335, 93907, 92007, 94606, 94611, 94901, 92220, 93305, 95134, 94612, 92507, 91730, 94501, 94303, 94105, 94550, 92612, 95617, 92374, 94080, 94608, 93555, 93311, 94704, 92717, 92037, 95136, 94542, 94143, 91775, 92703, 92354, 92024, 92831, 92833, 94304, 90057, 92130, 91301, 92096, 92646, 92182, 92131, 93720, 90840, 95035, 93010, 94928, 95831, 91770, 90007, 94102, 91423, 93955, 94107, 92834, 93117, 94551, 94596, 94025, 94545, 95053, 90036, 91125, 95120, 94706, 95827, 90503, 90250, 95817, 95503, 93111, 94132, 95818, 91942, 90401, 93524, 95133, 92173, 94043, 92521, 92122, 93118, 92697, 94577, 91345, 94123, 92152, 91355, 94609, 94306, 96150, 94110, 94707, 91326, 90291, 92807, 95051, 94085, 92677, 92614, 92626, 94583, 92103, 92691, 92407, 90504, 94002, 95039, 94063, 94923, 95023, 90058, 92126, 94118, 90029, 92806, 94806, 92110, 94536, 90623, 92069, 92843, 92120, 95605, 90740, 91207, 95929, 93437, 90630, 90034, 90266, 95630, 93657, 92038, 91304, 92606, 92192, 90745, 95060, 94301, 92692, 92101, 94610, 90254, 94590, 92028, 92054, 92029, 93105, 91941, 92346, 94402, 94618, 94904, 9307, 95482, 91709, 91311, 94509, 92866, 91745, 94111, 94309, 90073, 92333, 90505, 94998, 94086, 94709, 95825, 90509, 93108, 94588, 91706, 92109, 92068, 95841, 92123, 91342, 90232, 92634, 91006, 91768, 90028, 92008, 95112, 92154, 92115, 92177, 90640, 94607, 92780, 90009, 92518, 91007, 93014, 94024, 90027, 95207, 90717, 94534, 94010, 91614, 94234, 90210, 95020, 92870, 92124, 90049, 94521, 95678, 95045, 92653, 92821, 90025, 92835, 91910, 94701, 91129, 90071, 96651, 94960, 91902, 90033, 95621, 90037, 90005, 93940, 91109, 93009, 93561, 95126, 94109, 93107, 94591, 92251, 92648, 92709, 91754, 92009, 96064, 91103, 91030, 90066, 95403, 91016, 95348, 91950, 95822, 94538, 92056, 93063, 91040, 92661, 94061, 95758, 96091, 94066, 94939, 95138, 95762, 92064, 94708, 92106, 92116, 91302, 90048, 90405, 92325, 91116, 92868, 90638, 90747, 93611, 95833, 91605, 92675, 90650, 95820, 90018, 93711, 95973, 92886, 95812, 91203, 91105, 95008, 90016, 90035, 92129, 90720, 94949, 90041, 95003, 95192, 91101, 94126, 90230, 93101, 91365, 91367, 91763, 92660, 92104, 91361, 90011, 90032, 95354, 94546, 92673, 95741, 95351, 92399, 90274, 94087, 90044, 94131, 94124, 95032, 90212, 93109, 94019, 95828, 90086, 94555, 93033, 93022, 91343, 91911, 94803, 94553, 95211, 90304, 92084, 90601, 92704, 92350, 94705, 93401, 90502, 94571, 95070, 92735, 95037, 95135, 94028, 96003, 91024, 90065, 95405, 95370, 93727, 92867, 95821, 94566, 95125, 94526, 94604, 96008, 93065, 96001, 95006, 90639, 92630, 95307, 91801, 94302, 91710, 93950, 90059, 94108, 94558, 93933, 92161, 94507, 94575, 95449, 93403, 93460, 95005, 93302, 94040, 91401, 95816, 92624, 95131, 94965, 91784, 91765, 90280, 95422, 95518, 95193, 92694, 90275, 90272, 91791, 92705, 91773, 93003, 90755, 96145, 94703, 96094, 95842, 94116, 90068, 94970, 90813, 94404, 94598]\n", "Is ZIP Code colum valid True\n" ] } ], "source": [ "print(\"Is ZIP Code colum valid {}\".format(validate_column(df_original['ZIP Code'].unique().tolist(), 'ZIP Code')))" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Analysing Family column for unique value [4, 3, 1, 2]\n", "Is Family colum valid True\n" ] } ], "source": [ "print(\"Is Family colum valid {}\".format(validate_column(df_original['Family'].unique().tolist(), 'Family')))" ] }, { "cell_type": "code", "execution_count": 17, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Analysing CCAvg column for unique value [1.6, 1.5, 1.0, 2.7, 0.4, 0.3, 0.6, 8.9, 2.4, 0.1, 3.8, 2.5, 2.0, 4.7, 8.1, 0.5, 0.9, 1.2, 0.7, 3.9, 0.2, 2.2, 3.3, 1.8, 2.9, 1.4, 5.0, 2.3, 1.1, 5.7, 4.5, 2.1, 8.0, 1.7, 0.0, 2.8, 3.5, 4.0, 2.6, 1.3, 5.6, 5.2, 3.0, 4.6, 3.6, 7.2, 1.75, 7.4, 2.67, 7.5, 6.5, 7.8, 7.9, 4.1, 1.9, 4.3, 6.8, 5.1, 3.1, 0.8, 3.7, 6.2, 0.75, 2.33, 4.9, 0.67, 3.2, 5.5, 6.9, 4.33, 7.3, 4.2, 4.4, 6.1, 6.33, 6.6, 5.3, 3.4, 7.0, 6.3, 8.3, 6.0, 1.67, 8.6, 7.6, 6.4, 10.0, 5.9, 5.4, 8.8, 1.33, 9.0, 6.7, 4.25, 6.67, 5.8, 4.8, 3.25, 5.67, 8.5, 4.75, 4.67, 3.67, 8.2, 3.33, 5.33, 9.3, 2.75]\n", "Is CCAvg colum valid True\n" ] } ], "source": [ "print(\"Is CCAvg colum valid {}\".format(validate_column(df_original['CCAvg'].unique().tolist(), 'CCAvg')))" ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Analysing Education column for unique value [1, 2, 3]\n", "Is Education colum valid True\n" ] } ], "source": [ "print(\"Is Education colum valid {}\".format(validate_column(df_original['Education'].unique().tolist(), 'Education')))" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Analysing Mortgage column for unique value [0, 155, 104, 134, 111, 260, 163, 159, 97, 122, 193, 198, 285, 412, 153, 211, 207, 240, 455, 112, 336, 132, 118, 174, 126, 236, 166, 136, 309, 103, 366, 101, 251, 276, 161, 149, 188, 116, 135, 244, 164, 81, 315, 140, 95, 89, 90, 105, 100, 282, 209, 249, 91, 98, 145, 150, 169, 280, 99, 78, 264, 113, 117, 325, 121, 138, 77, 158, 109, 131, 391, 88, 129, 196, 617, 123, 167, 190, 248, 82, 402, 360, 392, 185, 419, 270, 148, 466, 175, 147, 220, 133, 182, 290, 125, 124, 224, 141, 119, 139, 115, 458, 172, 156, 547, 470, 304, 221, 108, 179, 271, 378, 176, 76, 314, 87, 203, 180, 230, 137, 152, 485, 300, 272, 144, 94, 208, 275, 83, 218, 327, 322, 205, 227, 239, 85, 160, 364, 449, 75, 107, 92, 187, 355, 106, 587, 214, 307, 263, 310, 127, 252, 170, 265, 177, 305, 372, 79, 301, 232, 289, 212, 250, 84, 130, 303, 256, 259, 204, 524, 157, 231, 287, 247, 333, 229, 357, 361, 294, 86, 329, 142, 184, 442, 233, 215, 394, 475, 197, 228, 297, 128, 241, 437, 178, 428, 162, 234, 257, 219, 337, 382, 397, 181, 120, 380, 200, 433, 222, 483, 154, 171, 146, 110, 201, 277, 268, 237, 102, 93, 354, 195, 194, 238, 226, 318, 342, 266, 114, 245, 341, 421, 359, 565, 319, 151, 267, 601, 567, 352, 284, 199, 80, 334, 389, 186, 246, 589, 242, 143, 323, 535, 293, 398, 343, 255, 311, 446, 223, 262, 422, 192, 217, 168, 299, 505, 400, 165, 183, 326, 298, 569, 374, 216, 191, 408, 406, 452, 432, 312, 477, 396, 582, 358, 213, 467, 331, 295, 235, 635, 385, 328, 522, 496, 415, 461, 344, 206, 368, 321, 296, 373, 292, 383, 427, 189, 202, 96, 429, 431, 286, 508, 210, 416, 553, 403, 225, 500, 313, 410, 273, 381, 330, 345, 253, 258, 351, 353, 308, 278, 464, 509, 243, 173, 481, 281, 306, 577, 302, 405, 571, 581, 550, 283, 612, 590, 541]\n", "Is Mortgage colum valid True\n" ] } ], "source": [ "print(\"Is Mortgage colum valid {}\".format(validate_column(df_original['Mortgage'].unique().tolist(), 'Mortgage')))" ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Analysing Securities Account column for unique value [1, 0]\n", "Is Securities Account colum valid True\n" ] } ], "source": [ "print(\"Is Securities Account colum valid {}\".format(validate_column(df_original['Securities Account'].unique().tolist(), 'Securities Account')))" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Analysing CD Account column for unique value [0, 1]\n", "Is CD Account colum valid True\n" ] } ], "source": [ "print(\"Is CD Account colum valid {}\".format(validate_column(df_original['CD Account'].unique().tolist(), 'CD Account')))" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Analysing Online column for unique value [0, 1]\n", "Is Online colum valid True\n" ] } ], "source": [ "print(\"Is Online colum valid {}\".format(validate_column(df_original['Online'].unique().tolist(), 'Online')))" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Analysing CreditCard column for unique value [0, 1]\n", "Is CreditCard colum valid True\n" ] } ], "source": [ "print(\"Is CreditCard colum valid {}\".format(validate_column(df_original['CreditCard'].unique().tolist(), 'CreditCard')))" ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Analysing Personal Loan column for unique value [0, 1]\n", "Is Personal Loan colum valid True\n" ] } ], "source": [ "\n", "print(\"Is Personal Loan colum valid {}\".format(validate_column(df_original['Personal Loan'].unique().tolist(), 'Personal Loan')))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Lets Visually inspect distribution of values across each column and check presence of outlier" ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 25, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# Age\n", "sns.distplot(df_original['Age'],kde=True)\n", "# Here we conclude that data set is captured for a wide range of age group" ] }, { "cell_type": "code", "execution_count": 26, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 26, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# Experience\n", "sns.distplot(df_original['Experience'],kde=True)\n", "\n", "#Again here wide range of experience levels" ] }, { "cell_type": "code", "execution_count": 27, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "#Lets Analyse which relation between age and personal load\n", "\n", "sns.catplot(y='Age', x='Personal Loan', data=df_original)\n", "# Except that 0 is more denser than 1 there is no enough visual reference that who would take more loan from this relationship" ] }, { "cell_type": "code", "execution_count": 28, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "['ID', 'Age', 'Experience', 'Income', 'ZIP Code', 'Family', 'CCAvg', 'Education', 'Mortgage', 'Personal Loan', 'Securities Account', 'CD Account', 'Online', 'CreditCard']\n" ] }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAWAAAAFgCAYAAACFYaNMAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjMsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+AADFEAAAgAElEQVR4nOydd3wc1bm/nzMz21fVqpZ77zbYxhSbZsC0hF5CCz3l5uaSckPavSm/m4RULtwktIRgQmgJhNDBVGOaMe4F927ZsmXV1daZ8/tj5ZVWu5JWtqQtOs/nY6Q9c2bmXaT96sx73iKklCgUCoWi/9HSbYBCoVAMVJQAKxQKRZpQAqxQKBRpQgmwQqFQpAklwAqFQpEmjHQbcCyce+658tVXX023GQqFQtEdItlgVq+ADx06lG4TFAqF4qjJagFWKBSKbEYJsEKhUKQJJcAKhUKRJpQAKxQKRZpQAqxQKBRpQgmwQqFQpAklwAqFQpEmlAArFApFmlACrFAoFGlCCfAAJBi2aPBF0m2GQjHgyepaEIqe86/3D7Lw9f34QxYnjM/ju18Yjsuhp9sshWJAolbAA4j9h4M8+NI+/CELgKUbm3jufVVPQ6FIF0qABxA7DwSxOrQA3LHfnx5jFAqFEuCBxOQRHlyO+B/5zHH5abJGoVAoAR5AeF06P71xJFNGehha6uCmcys5Z1Zxus1SKAYsIpvb0s+aNUsuW7Ys3WYoFApFd+ReQXaFQqHIZpQA5wiHG8MsXl3P3kPBdJuiUChSRMUB5wCfbGzkp3/dQcSUCAFfvrCKz59ckm6zFApFN6gVcA6w8PX9RMyoL19KeHRRdey1QqHIXJQA5wDNfjPutT9kETGtNFmjUChSRQlwDrBgdnwo2enTinDaVXqxQpHpKB9wDvCFM8opL7SzYksTowe7uGDOoHSbpFAoUkAJcI5w5nFFnHlcUbrNUCgUPUC5IBQKhSJNKAFWKBSKNKEEWKFQKNKEEmCFQqFIE0qAFQqFIk0oAVYoFIo0oQRYoVAo0oQSYIVCoUgTSoAVCoUiTSgBVigUijShUpEHCB+ub2Dj7hamjvQyc1xep/NCYYu3V9ZRUx9m7pQCRla6+tFKhWJgoXrCZRk19SEafBHGDHYhRFubqeraIKu2NnPSpHwKvLa4cx55rZqn3qmJvb71/Eoum1eW9Prf+9NWVm5tBkDX4Gc3j2b6aG8fvBOFYkCRtCecWgFnEX96eR/PLjmIlDCiwskvbhlFodfG75/bw0sf1wJwzz/h9gsGc8ncUgAsS/Lc+4firvPPJYeSCvD2an9MfAFMC57/8JASYIWij1A+4Cxh1bYmnnkvKr4AO/YHeOa9g9Q2hmPie4S/vFpNONJWkF3v8FPu+PoImpb4R9pQvyGKo8RsqKHpyf+m/ndX0vz3n2I1H063SRmH+nhlCX9+uTphrKY+zKGGcMJ42JQEQlEB1jTBVWeUxx2/usPrIwwvd3Ly5ILYa4dNxFbSCkVXyHCAwId/x/f8bwiteweAlud/Q2Tbp8iAj/Dmj2l5+d70GpmBKBdEFmCakm3V/oTx4jyDvYcCOO1aTHCP8Pqnh6ka5OD4sXlceVoZk4d72LSnhSkjPYytcnd6r+9fM5ylnzVSUx/ixIkFlBfZe/39KHIP33O/JLx5KQChtW9jNtcR2b0ubk54+ypCn72PbdTxCLva3IU+3IQTQgwFHgUqAAt4UEp5jxCiGHgKGAHsAK6UUtaJ6I7SPcD5QAtwo5RyeVf3GAibcIGQybfu38K26sBRnV9ZbOfnt4yirNCOpgkipsSyJHabevhR9A6Wr56Ge66NG9NLR4CmYx7YmjBfeIrIu+HX6EWV/WRhRtDvm3AR4FtSyuVCiDzgUyHEIuBG4E0p5V1CiO8C3wXuBM4Dxrb+mwPc1/p1QPP2yvoE8RUCUv27WX04xE2//ozSAhvHjfXy3poGwhHJOTOL+epFVehJ/L4KRU8QNgcYDogE28ZcebjP+TK+53+DWbM9br701RFc+hzuBV/pb1Mzjj4TYCllNVDd+n2TEGIDUAVcBJzeOm0h8A5RAb4IeFRGl+QfCSEKhRCVrdcZsPgCZsJYTwT4CAcbwry+rC72+uWltdQ1hYlYEkMXXDavjMkjPLy9so5Fnx6mwGNw9RnlDC93HutbUOQ4wu7CNe8a/G//JTpgc+I89Tr0shHk3/p7QluX4XvqR3HnyEBzkisNPPrFByyEGAEcB3wMlB8RVSlltRDiSDxUFbC73Wl7WsfiBFgIcTtwO8CwYcP61O5M4NRphTz+1gH8waiP1+PUOGFCPm+vrI+bZzMEZx1fxCtLU99p/nBDY+z7pZ81csPZlfzltbb/3cu3NPHIf07E5VAdlhVd4zzpcmxj52Ae2oUxbCqaOz92zDbyOLTiIViH90QHhIZ9+jlpsjSz6HMBFkJ4gWeAO6SUje2TBzpOTTKWsM6TUj4IPAhRH3Bv2ZmplBXaueerY3l5aS0COH9OCZXFdiYN97B6WzOBkEV5oY1h5S4eeHHvUd/HtOCR1+MfNhp9Jqu2NXPixIJOzlIo2tBLhqKXDE0YF5pO3vW/IvjpC1i+ehxTzsAYOjkNFmYefSrAQggbUfH9m5Ty2dbhA0dcC0KISuBIitYeoP1Pbwiwry/tyxaGljn50oVVcWMXnljChSeWxF5//89bMeMDIThnVhGaEHz8WSMep86eg0G6Iplbo0JFQSh6Ac1TgOvU69JtRsbRZ1vhrVENfwY2SCl/1+7Q88AXW7//IvCvduM3iCgnAg0D3f/bE5KJ57XzK/iPS4fy+Pcnc9XpiZlvhp740FHgibobNAGXzStlRIUKF1Io+oq+XAGfAlwPrBFCrGwd+z5wF/C0EOIWYBdwReuxl4mGoG0hGoZ2Ux/alnVYluT+F/eyelszJfk2KopsDC51EQxZNLZEmDjMHZdG7DAEv356FxefXMLSz5rYvK8Ft0Oj5Ygv2aXxh38fx48e2c7OmujK2GnX+MWto0GC161TWqBWv7mMFWgmtOIVrOY67JNPwxg8vsv5Zu0egqteRxh2HMedi5ZX0uX80Pr3iOxagz54HMao4wkseRJz30b0qgm45l2D5lauLVWMJ0v49v1bWLfTd8zXKc4zuHReKWdML+Jwc5jDjWEO1odp8keoKHZQUWRnwjBPL1isyGSktGj689fbQsSEhvean2EbPi3pfPPwXhof/g8IRROChLeYvJvvxarZHo1ocHqRkSD4GjCGTib02RICix9ru0DHMLWCMgq+/CBCt3W8Va6iivFkK1LKXhFfgMNNEaaP8vLAS/tYvDoaSTF4kB2HTWP7/mi88axxefz4hpHoSVwUitzA3LMhPj5XWgRXvNqpAIfWvBUTXwDZfJjG+2+HUEvyG9g6hC9G4vcfZEMNkR2rsI2edVT25woqHSoLqD4c6tXr7T4YjIkvwL7aUEx8AZZtauKTjY3JTlXkCFYoMbOyq/TgpMc6E1+AcAqZmx1FegCiBDgLaGiOHPW5Hdewc6cUYDO6X9kePoZ7KjKf0PKXEsZEu9jdjtgmnAKOdq4pe+f1RFLBGDZVhaKhXBBZwbihboaUOhLCyFLJiPvGZUPQDY0NO33MmZDPrPH5tARNvC6dZn9ilh1Ekz0mDnXzytJaygptHD82jy7itxVZSGTvZwljwQ+exmquw3PBfyCEwPI3Ed78EcLhJfDpixBsc4PZRh1P+LMlR3dzmwvvtT9Xv1MoAc4KdE3wy1tH88ySg6zY3BRzF6Syf/rJpia+f80IZo7Nw9AF/qDJU28fSCq++W6dWePyOHFSPt+6fwv+1gprp00r5LtfGN6r70mRXoyhkwlv/CBhPLx6Ec0NB3BfcAeNf7kD/MldUebBHXgu+yG+F34X74pwtK6Mg527J2wjZyCEevgGFQWRddzymw3sq03dJ/y5EwfR5Dd5d3U9guiquWPCBkBpgY3GlgjBsKTAo9PgixfoB+4Yx7ByFROcK1jNh2n8yx3Iptqkx0V+GbKxJukxABwePJfcie/J/+5woohGPCT1AQv0EdPwfv7baN7iozc+O1FRELlAKNz5H8yKIjv760LtXtvYfSjIyi3R+GAZ+08itY1hrNZjHcUXYPmWZiXAOYTmLSb/i7+l4fc3Jj3epfgCBH2Elr+a5ESZVHzzv/wQevHgo7A0t1ECnGVcdmopD7yYmKFt02HmuDyGljooKbRR4DZYsaWZx9860O0181w6TZ34g48QjmTvk5IiOVp+KbZJpxFe/+5RnW+2NCDySpBN7XsOCpL9lfcveQJj8HgcU89EOI5tAy+XUI6YLOPiU0r53heGMXm4m/KitiD2sAkvfVzL/S/uY//hEFNGersNJasosjH/uCLuv2M8+e7OK55pIhobrMg93Au+AlqK67AOflt5aCdG1cQOk5L/oQ6vfQv/6/fR9NidSKvrP/YDCSXAWcip04r41e1jkroKINr1GKCqxBE3LgQMK3MwosLJly4czF++M4lvXzmM4nwb/++mUYwenBiXWegx+N41wxlZqdwPuYjmyiPv2l+gD54Adhd0kplmjJ2DMWFu3JgMNKcQCRHv+jQPbCOyc82xmJxTKAHOUoTovLuxrTWD7cYFlYyoiIqq26Hx7SuG8cA3JnDff4zn4lPim22OG+LmtvOrEq512vRC5k4p7F3jFRmFMXQS+Tf+lqJv/wP7hFOSTHDgvewHGGUjEo91E0qmJTtHV57PIygBzlKEEJ12N776jDJMS/LxhgbshmBEuYOrzyjj1GldC+nUkR6mjGgLtrcbgoMNIVZsaepV2xWZQ2jdO/j+9WsCHzyNDAVwnHBxgkvCPvVMhKbjmH42wjsoNq6XjsAx84LOL253RwvuGG1FnVQCRjwqDC3L2bDTx2e7W/A4NXwBi6mjPIwZ7Ob+F/byrw8Oxc09e2YR37w82kUkFLb4dHMTDpvGjNFetNbecOGIxQfrGrj/hb3Ut7o4hID/d+MoZio/cE4RWPpP/G/8KfZaqxyHUTma0PJX4icKDddZt+GYeQFWoJnAkqcwD+5EK65EL6oi8PbDIJPENra/hKcIx5yLcc6+GDEwV8AqDC1XCIYthAC7oTFxuIeJw+Orl/kCJq9/mtiaaNGndZw/ZxAl+Ta+8+AWqg+HAZgy0sNdt4xG1wU2Q6PQa4uJL0QjixZ9elgJcI4RXLUo7rVVvYlQ9abEidLCv+gBguveQQgNc+8GAMydKwmneC/pqyPw1l8gFFCF2duhBDiLkFLywIv7eOnjWnRNcNm8Uq4/uyJ2fMveFn751K4uO198874tCIjF/AKs3e7jk42NnDgpWp8135MYEZFsTJHdaK58ul63xmPt23jM9wx8+HccJ1yM5vQe87VyAeUDziKWrG3gXx8cImJKgmGLx986wOptbUXYf/v33Sm1HbKSeJ2a23VfPlifuK4ZW6ViN3MN56nX9X9FMjNC46N3Etm9rn/vm6EoAc4iPlzXkDD2zOIaPtnYyDOLa9hxIIUSgEkwdMFJk9q6EyzblBg/vH2/P2FMkd1ornyccy5FHzunX+8rD+2g6bHvYdZ3nySU6ygXRJaw8PVq3l5VnzC+dGMTSzd2HaVgMwRDShxxNX/bM/+4aHREs9+ktjFMc0tifLGpYudzivDWZTT//aeQrqQIaRL6bAmuEy9Lz/0zBCXAWcBjb+znybe7yc3vgnBEUlFs55xZxTz7Xg21jZGYG8JuE7y2rI43V0TFPWImj4qZNlr57HIJ/+LH+lZ8dQPMrmtKy8ZDXR4fCCgBznD2HAzytzeP/VHtw/WNFOfZaPZbcT7gI8V9OhNegBEVTuZMUBEQuYR5eG8f30GA0wuB5k5nqJRk5QPOePbVdr2p1hFbF8EKL31cG6vx2xN27A/w1opE94cii+ks/l/0UrSLGe5SfCHalcOs398798tSlABnOFNHerCn0ELoCOE+WlS8n2QDUJG92CedlvyANNGTpQ8nw3Hs3bMjO1Yd8zWyGSXAGY7LoXPdWYkpx2WFNiYNdydPrzkKvC6NUyYXUFqYvBhLJFkVd0XW4j77dmxTzkh+7KI7McackPxEpxetciyu+bdC8NgjY7TCiu4n5TBKgLOAy+aVccGcQehatD7DVaeXsfDOSfz2y2P50ucG43J0/mPUNbh0XmmnxwGGlDr45W1j+OF1I/jLtyfG1YM4wqxxnTdsVGQfwubAdcpViQdsTozSYeRd+SP0IYk1G1xzr6bgpv/FMfvzCEeHCnlCb6v7IDT0IZO6Ltaj6RhV44/hXWQ/ahMuC9A0wdcuHsIt51UihMBhE7zw4SE+XN+AL2AyssJJKCLZdSBAqLVwelmhjfIiGxOHetF1GJRvUNsYvyttN+CnN45m6kg3r35Sx8LXqhlS5uQ7Vw3jRwu3x8LWhpY5OGfWgGshk/Pog4aiV47FrN4cG7NPOyv2fd41P6Nx4bewDmwFQCsejH1q9LjQdJzzrsH/xkO0DqCPmI5ZvQmEhjZ4PFreIBACc//Wti4Z7TrJOuddgxjgrelVMZ4sYvW2ZnbVBNhXG4zV/E3GqEoH26qTb96176Rs6ILf//s4lm1q5E8vV8fmTBru5pe3jWHZxkZMCbPH52E31MNSLhLasQrfk//VFpImNPK++Bu0wkrCmz+Ktp/XdIS0sI2ZjWhX2QzArNlBZP8WwttWEF7/Tqf30QePxzZmNhKi1xp7IkbF6L57Y5mHKsaTzTz08j6efe9gSnM7E1+I3/yOmJIla+v5cH185tv6nS3U1IVitSEUuUng05fxv/aH+EFpEVj6HJHtK5GtHZH1IZPwXPoDhGFHWiZWUy1afglCaOhlI5C6Tsuih7q8l7lvI2a7WhLCmTfQBDgpSoCzgCZ/hOc/6Jug9ZICG4PybWzdF7+h8q37N/OD60YwZYRKwMhFIrvX43/9vqTHwusXx70296yn8d5rMUZMJ3JwF/jq0IoG477oO7Q8dxfWUYSS+Rf/Defszx+V7bmEeq7MAkwTzGQVdJLgdXX9I3XY2p6EDB3cdo3r5pcn7JXU+0zueXZPj21VZAe+l+7ptoZvRyI7VoGvDgCrbh/NT/zgqMQXgFAL2ez+7C2UAGcBhV6D07rpZgFQXmTjaxclthVqT/uMt4gJv3hiFxHLShqXv+dgkGcW19DcTcdkRXYhLROrNzLhgr7EMU8R+uhZeK74bwq+thBj1Mzk59pdiG7aGQ0ElABnCdedVdFd+y2a/SZDS504bZ1P7LiQlsD/PrOH0YOTN9380yvVfPP+zYQjKg44VxCajj5sSt9c3FeHuXUZvmd+RmjrMpzzrk1a8tLeSQzyQEMJcJbw7qr6TrNHj+ALWHz8WRP/7+ZRTBvlochrUOjRGZQfDUk7d1YxupYozrtqgty4oIKTJuXjcWqxpp5H2F0TZPnmrtNKFdlFYjv5dthdcX3cusRTlHzcMvG/8n80L/xmWwhaO0Lr3iGy97PU7pHDqE24LMGWYjqyzRBMGeHll7eNSTj24keHeHVZYqsigIoiO2fMKGLXgQCHGsPQwetg6OpxMZfQ3J0UV7K70EuGxUUsRE/Qk1dPa/UJ95hAM/63Hibv+l8d3fk5gloBZwnzj+/eB+ywCbyuzouprNuRxGcHnDq1ALtN45dP7mRvbYhgOH6pPWm4mxljVDRELmGfMj+h+zEI8q7+KbIlSd0PaaGPO6lXbbBUOUolwNlCcZ6deVOTx+VWFEUfF4NhyT3P7uGVpbUJc1ZsaeKdDgXdDV3wrcuHcufVw1m/00fHcg+Thrn5/jXDuevW0UldF4rsxaqvBqtDvV7dwBgyCduEuYknSIm5ZWmv2mCMnNGr18tGlABnEd+8fBjXnFlOeaENl12jstjOv188hP11obh5i5J0RH5zeeKj4m3nV3LWzGI0TTCuyp2wyTf/+GLmTS3EprLgco7QmjcTxrSiaGEcY+ik5Cf1tH6v3rUfWbhVoo/yAWcRTrvG9WdXxHVCbvBFuO+FvXHhZQWexB9rsrFJ7drZDy5x8PVLhvDIa/tpCZqcM7OYBar+Q86STPycJ18NgNbZxlpXGPaonzjkB6HhmPU5nKfdQPMTP4y1se+I5u7erZbrKAHOQg43hXnsjf3sPBBg1vh8rjytjMffinbN0DTId+v87G87aGoxOWdWMSUFNrZW+7EbIlas58wZRYzp0On43NmDOGdmEf/6oJYP1jVw9zO7ue6sciqKHf3+HhV9i2PmhYTWvYtVtw8A27iTcEw5HQDhKYrW+u0Y52tzRtsMWZFoURGhxVbFxojpCM3ADDTjPP48HK31hvO/+BssMwLSwvf0j2P1f/WykTimn90/bzaDUcV4spA7/riZjbtbYq/HDHaw91AIfyj5z1LTwGr17woB375yKGfOSL66fe79gzzw4r7Y68piO3/61gQ05QPOOczGg7S8+gdksAXnSVdiHzMLgLr/vRZaOu+AYp99EY5pZ9H02J0QbEk6Rx9/MkZhBVp+KfbJp6G5C5BSYu5Zj4yEMYZPRWi91H0jO1DFeLKZcMRi98EgDpsWJ74AW/Z13bbIare5JiUsWdPAmTOKqWsK0+w3GVLqYFdNEE2Dha/tizu3+nCILXv9jBvqRpE7WI0HaXzgSxCO/u74dv+IyGk3YBs2pUvxBQgtfxm9uKpT8QUwN34Qi2QMfPh38m++F81bhDE0scbwQEYJcBawYZePn/51B/XNkZTjgbti814/C1+v5ul3a7CsaPhax9Cz9uytDSoBzjGCqxbFxDc29u6jyKlndXJGO8wwkU78usmQzYcJrX0L5wBvQZ8Mtb2dBdz/wl7qm6MhQ+FI9y4jXWtrRDB+SGKKsU2HJ9+uia2MuxJfAI9zQD0qDmjC25K49ESiTER2ru7RdYOrXsc8vK/7iQMMJcBZQHVtqPtJ7dA1wQN3jOOKU0vwhyw6um8bfJHkJyahvMjG8WNVS/pcwzH9bNAT+/9JX0N87QZXAcb0BQhnu98Bw45sSow17wqrdg9Nj34b38v/R2jDe0drds6hBDgLOGVKz+IlQxHJtx/cyt8XH2JXTTChAE9LMLWN16oSO/ffMV6lIecgZv2BaERDAhLCAYSnCMfcL0DIT2TlK8hAE9hd2KfOP+pGmrKlgdDKV/H98y4CHz1zbG8gR1ACnAV8+XNVTB3Zsxbgjb5jLyFZVmjDaVfuh1wktPI1orXwkiN9ddGSlWa7p6+Qn9CaN7EO7YqffBRlJYMrXunxObmIEuAswGHTOHly/2cNrdjiY8Ou5PUjFNmNcHS/qWo1ptACSwhsSWpECFfXbithV5u6oAQ4axhenp7usT3xFyuyB/vx5yet0xtHKh2LpSS86SOEp11Wm9CQIX/n5wDoOjLSs72NXEQJcJYwbaSXwYNSrNHaS3hdOseNURtwuUhw6XMd6vQmuhHM7StSu5i0kL76uNfJ/cvtrr1vE02PfTe16+cwSoCzBF0X/Pr2MVx+ailnzCikyNt7IdwFnng/rxAwc5yXP3x9HA6b+hXJRULr3o0fEFp8pEM/YO7b1K/3y0RUIkYWUZxv45bzBgOwdZ+f3z+3hy37/HGFeI6Ga+dXsH2/n8Wr6ykrtPOlC6uYPlrV/81ltPxBWO3icrXCMmwjjye4/KXOTxICY+wcIps+6h0jbKrGiBLgLGDngQB3P7ObHfv9eF0GnztpEBt2tbDnUJCudrI7w2aIWEKH067x0Mv7cDs0Sgts2A2N2sZwL78DRabhPut2mv95V9QNYXPgPvt29LKRhLcvx6qrBgQivwR5ZCNOMxDlI3FMPQs9v4zgsuej4zZXtCDPkWgJ3WhzPwgNY8QMItuXx16378Tsnn9z/7zZDEYV48lwIqbkhl+up66p9zfD2ldH68g3Lx/C2TMH9fo9FZmDFWjGPLAdvXwkmjP6xCMtE3PvRkReMc1P/Qirdk/Ced6b7kZzeGl+5mdYB3fEH9R0HGfejLn3M/DVIwFz15p2EwS2ifNwnn07hvcoyl5mL0lj9ZSDL8PZVu3vE/EFOhVfgLuf2aNC0HIczenFNnxqTHwh2jHZGDqJ4PJXkoovQMuzdyFceYniC2CZBN94iMiG94jsWtNBfAEk4Q2LCX38bO+9kSxGCXCGU1ncv5EPR5ASXvqoZ+mmitwhuPLVTo9ZDQew/E1JU5lTvv6nLyF72mEjB1E+4Awnz21QNcjO3h7Wg+gNeqPymiJ7CG1eiv+tP0dDysyu9wE0mwO9YnTU1XA0mGEiez/DNsDLU6oVcBbw1Yuq0nLfdTt8PPHWAfxBtVLJdSxfA75//gKrdg8y0JxQqrI9tglz0fIG4T7zlqNKQwaiHTKe/TmyG6HPdfpMgIUQDwshaoQQa9uN/VgIsVcIsbL13/ntjn1PCLFFCLFRCLGgr+zKRo6Uouxvdh8M8uii/fz88Z1pub+ib7GaDhFc8xaR/VswqzdCCplp+ogZeC6JJlAYQyfhPPPW7s8ZPj3puPTVY9Xu7ZnROUZfroAfAc5NMn63lHJG67+XAYQQk4Crgcmt5/xRCKGqwLTS19lohh4tvNMZyzY1Udc0sFcquUZ4+0oa/ngrLS/8lqaH/4PwjtWgde+RdEw5HdG66pXhAPZJ87o+wVuM53PfwHnK1Yj80rhDwpWPVjz4qN9DLtBnAiylXAwk9kdPzkXAk1LKoJRyO7AFOKGvbMs2/EGLory+c9fPHp8fS/DoDF/A6vK4IrsILHk8zs8bXPocrtNvQHg7CT0UGo7ZF2GfOh8pJS2LHqT+d1fR+Iebo7G/7XFEK/eJvEEQDtD4+5swa7aRd8Ovo4V7hIZWNBjPxXcijPRsMmcK6diE+5oQ4gZgGfAtKWUdUAW0T6/Z0zqWgBDiduB2gGHDhvWxqZnBH5/f22ehaAAfrm/E7ej6b/Gjr1fz/WtH9JkNiv7FSujnJgnvXEvh1x+l/g83IxsOxB11nPZF3CdfDkBo44cEP/lX/OlCRENnbE68l/8Qqen4HrszOgaENy8Fhzd6TFqIJF02BiL9/X/hPmA0MAOoBn7bOp7Mk580SFVK+aCUcpaUclZpaWmyKTnHpr2dNz/sLd5c0XUjxs37+t4GRf9hn3xawph1eDcA+pCJCcciWz6Ofa6Wit4AACAASURBVJ8sRM1+wqV4rvhvCr72CMbQybQ8+/OY+B4hvO5trIYaJb7t6Nf/E1LKA1JKU0ppAQ/R5mbYAwxtN3UIoBpItVKSf/Txlr3FCRPy022CohdxnXQFIi9+AWMbeRwAjolJ/LrtykvK5rqEw0bZCOxj56C58jAPbIuvjhY7URLe8smxGZ5j9KsACyEq2728BDgSIfE8cLUQwiGEGAmMBZb2p22ZzIUnlnR5fMYYL2OrXFQNsjO83BFtytnJ3HlT8inJN/B043IAMHSBTRfMm1LATQsG9mZJLpJ37c8wRs9C5JVgn7EA15nR2gzG4HEJjTiNIZNi3+uVY+IvJDRso2bGXmr5pZ1u6A30TbeO9JkPWAjxBHA6UCKE2AP8CDhdCDGDqHthB/AlACnlOiHE08B6IAL8m5RSBZ+20l29jkZfhK98vopnFh9k2aYmNE0w/7hCPndSCXc+tJWWYNsG2ntrGxECJg1z0xK02L4/EBVrEf/EePEpJXzpwvTEHyv6B81ThOYpIuJfQ2jl64RWv4Ft4jy8F/0nrjNvwv/OQjAj6KUjcJ5yFQAyHMSs2dF2EaHhOus2NE9Bu+sW4jrzZvxvPQxW296FbewJGCNm9NfbywpUMZ4MpyVgctlP1nY7T9OItZk/Qp5Lo8nfefTC6dML2by3hb2H4uM/h5c5uP8bE47KXkX24Hv53tbecPG4zr4d5+yLsFoaMfdvIbxzFZgRHNMX4F/yOOEOXY3zbroHo92qOLxjFaENSzAP78Fs175euPIp+PeFAzXyIelDqUpFznA+3NCQ0ryO4gt0Kb4Ayzc30diS+KCxsyZIU0uEPLf69chlIjtWJh0PbViCY8a5RLavoOW1P0Yz44DgilchiXiGPluCXjaCyM5VRPZvI/DOI0mvK/2NhLetACyMynFoearanvqEZTjTR/ZdYfRRlU721YaoqU9MslCdMHIfvXw0Vv2BhHFt0BAa7r8N2dShGFM4gObKx/I3xs8vHUHjg1/Bqutm31zo+J79WbR+sGbgueg/sU+ce6xvI6tRn7IMp76lb+J/7Ybgm5cP49tXDkNL8nB00X+v4d/u3ciO/d00V1RkLe6zbgMjsStFeNWiRPE9gtMD3uK4If/zv+5efDUDpBkVXwArgv/th4/G7JxCCXCG09Dcs71IPcXaKBFT8pV7NvLnl/ehd/JbsK06wPcf3taj+yuyB62gDOFM9oTV+b6QVbMd1wkXo6e4mWY/7nxs40+J24yLXcuXmnstl1ECnOF0Jo6dkWp7OEtG04s37vET7kLj65oiPLfkYM+MUGQNR+OHjexam1JDTb1yLI7jzyO88f2kx4Vh6zbCJ9dRApzhfLAu9VVCWYGe1J1wrLy2TBVmz1XMuuoenxPethxC3WdGmtWbCa5a1Olx6W/COjiwK+0pAc5wCvNSz4KraTCx+mBB4bCrX5NcRXQspNMdhj2pOyEpDjcyoeZEh/t7BlRfuATUJyvDOXd2cfeT+phDSaIkFNlNcP1i6n93NdKXmFbcKYYdI9UOFkLDffbt2JLUlYhhd8UlcAxElABnOMV5Ni6Yk954ydqmCGaqzmVFxmM1H6bluV8hA009Os82YS6uedfQeaI7YNhxnn07BV9/DMe0s7FPOjWampyMSBirNcZ4oKIEOAv46uerGDPYlVYbDjWqVXCuEN70EV1FOgBgcyWEqNnHnYgxZBKus5J3wdBKhpF/2x9xzb4otrIVDnc0U6610E8cVoTI7nVH8xZyBpWIkQVommDmuDy27Os6JtemC/LcOjZDcKCum6aKgqT+YrdD0BKMP2DT6dOC8Ir+Rasc1/lBw45WOhzPuf8GkTD+JY8jA804pi/APuEUAJwnXIwwHARXvIzV0gC6gW3kTNxn3IhwehLv5ynAe9VPaHr8Bx3a1Av0QUMT5g8k1KcqC4iYknpfJE40dQ3M1kxjIeDGBRV4nDpPvFVDS9DC69Jp9iePL5t/XCHXnFnBN+/bSENLm9gKAaFI9AHzyKgm4OuXDsVuqIelXMFWOQbb5DMIr3s7/oDQcMxYgOusaBac76V7iOxej/AU4n/7L/g/eBqjfCSRXWuRkVC0o4bQ0AePR7i8NDzwJRAC50lX4Jh2Fi2v/oHQpo/Qi6twL/gKeVf8N83//AWRbcvBcOA69Vr0AV4dTRXjyQL+sbiGP7/SFi6kazCmysXG3UeXpWY3BE/8YDIfbWjk10/v6nRegUujIM/GNWeWc9r0gb1bnWuEt3xC89M/TnpMrxiNlBLrwNEn4ehVEzH3boi9Fp4iCr72CEI3sJoPI+wuhD29brV+RhXjyVbW7fDFvTYtjlp8AUIRyZf/dyNlRV2HuDX4LRr8Qe56che6Lpg7pfCo76nILMI7V3V6zNy/9Ziv3158AaSvDqtuH3rJMDRv+iN7MgX1XJkFTBzm7vVrHmwIs25H6m2GXlmqkjFyCWPolH6/p9mofoc6ogQ4C7h4bikzx/Vta/ruKO5BQogi87GPOzF5ZEIfEvzoH/16v2xACXAWoGuCLf3QmLMr5k4Z2AHzuYYM+YmkUM+hd++pGrt2RAlwFtDUEqHB1z8dmvLdyX8ldh8M9sv9Ff1D0zM/g6Cv+4m9iG3SaYTWvYN/yZPxbY0GMGoTLgso9NqoGmRjb23fJ0NMHeHh/fWJGVL+YNfdNRTZhbk9eTeMviTw5sPRmsBAYMnjeK/6SawT80BFrYCzgA/WNVBT3zeF2TuSTHwBxg3p/Y1ARXqIFsg5xvBTwwE9LeTTvs+uZRJY+tyx2ZADKAHOcExL8r/P7CacxloMZYU2Zo9P7yagohcRx16zVMvrJJRMKEnpCer/VoZzqCFMUycZbf2BJuB/bhqF1heFhhVpQdhd2I+/4JiuYdVVg5nkqazLxK52v0OagXPOpcdkQy6gfMAZzvY092QbP9TN0DJnWm1Q9D7uBV/BGD6V8Lp3CG/9NJpW3AvYxp2Ic941hDYsIfjxM3Ei7b70+wgkVl01trFz0EsGdh0ISFGAhRDjgPuAcinlFCHENODzUsr/6VPrFIyscMXVZuhvFmRAPWJF7yOEwDFxHo6J82j4079j1XRIO7ZFa/Va9fvjhvXKsWiFFYQ3vBd/PVc+9kmn4Tr9BoTDjVE+Cvv4kwh88HdkqAXHcedhGzcnOlfT+/S9ZROpuiAeAr4HhAGklKuBq/vKKEUb5UV2rjqjLKVWQ0JAgafrX26PU6MkP/UPwOqt/RuqpOg/IrvXUX/PdQnia595IUX/+Q/yb/sjxqiZsXGRX4Z98hmEd8WXkBR5g8i76W7cC76McLRt1hqVY/Fe9n3yvvA/RKo3Uf+bK6i/+2oCHzzdt28si0hVgN1SyqUdxvpnW17BkrUNKbUamjLCzZM/nMLT/zW5U5H1BSwONabuU35rZR2/eXqnKsieY0jLpPmfdyXtiCEMe/SrzYFsFyssG2vwv/Eg+A7HX6uplpZX/xB7HVz+Mk1P/Bctr92H1XyY0MYPCX74D4gEIdiC/52FRHav76N3ll2k6gM+JIQYTeuTsBDicqDn3fwUPcYXMNmTYhLEup0t1DdHqG0M9Uhku+PNFfUU5dm45byBXTowl5DNh5HNh5MeC2/7FHnmTQihYVZvTul6kR2r8X/8T4Rl4n/7L9Gx7csJbfwQ28jEFvaBj/6BZ/D3EPrATnFPqRylEGIU8CBwMlAHbAeuk1Lu6FPrumGglKP82v9tYms3xdiP4LRrgCQQ6t0Va1mhjYV3TurVayrSh5SShnuvQ/rqkx63TZyHe/6t+F78HZEdnVdOS0AzUm7aqQ0aSv7tf0QMjNC1pE7ElN65lHKblPIsoBSYIKWcm27xHUjcel4leophYIGQ1a34Hk1AWWmh/SjOUmQqZvUmZLIwslbCG96j4fdfBAnC1UkdED3J70SqHZMBq3Y3kR2rU56fi6QaBVEI3ACMAAzRGsgtpfx6n1mmiHHfC3sxe7HffE+vpGtwy3mVvXZ/RfppefUPkEJDzEgXdYP1YZMxt69IPGDYIRJKzZAeCHYukqoP+GXgI2ANoIoC9CPLNjayqya9hXBMCw43DewPSq5h1u459mvs3YRePhrzQLsC7nYPhJO4y4RITNLIG9TvJTEzjVQF2Cml/GafWqJIyicbe9Y6vK/45LNGTpmsSlLmClpBOdahdu2oerJqPULIh+uMm4gc2EJk+wqEtwSsCOH17yZMdZ/3NYJr34lryumYMHfAxwSn6v3+qxDiNiFEpRCi+Mi/PrVMAcDwiszIQhtenhl2KHoHq+FA/EAX/uCuCG1fjuukK9DyywivfTOp+Nqnzscx41ysgzvjxoMrXyObe1L2BqmugEPAr4Ef0OZClMCovjBK0cbZxxfxtzf2p9UFUF5k4zyVEZdbmB3CFOXReRZDHz9LaNlLYHbuJrNNOZPIga0JBdmFYUf0QmGgbCbVFfA3gTFSyhFSypGt/5T49gM2Q8PQ0/tLeqAuzHtrG9Jqg6J3EfbEJ5r2WW89ogvxhWhDTt+zdyWssp3zrj26++UQqQrwOkD1E0kThd6+rZmUSoRbx87MiuzGcdx5ca9t407Ce+WP8F75YxwnXNJr9xGuPPSKMVh1++LHvcU4Z13Ya/fJVlL9ZJvASiHE20Dsz50KQ+sfzp09iE17jn3XGqC8yGD0YDfLNzURNiWVgxxMH+nhpaXJs6KO0BedmRXpw3na9QhPEZEdK9FKR2CfeCoyFEAfPA598DiCy19KvilncyIc7k6z6ACwu9BLR6CXDMU55xK0QVWIgnJkO7+zMaz/uzJnIqkK8HOt/xRp4JxZxazf6eON5Yl5+51h0yGcJBv5QF2Eg/WNeJwagbCkJWDy9qrk2VBHyHdrzFIF2XMKoek4T7iIgM2O/7X7CH7YViBHHzIJ94KvEFjyJFbTIbT8UqzGQ2gFZbjP+RJafim+53+DeaBdER+HB0J+jJEz8Fz4DTRv255BeMvShJoT4a2fEvrsfewTTunz95rJpCTAUsqFQgg7MK51aKOUsu8blCmAaFfkBbOLeyTAycT3CJaEJn900yWVzb3GFot7nt3DT29Ubv9cwvLV43/1jwkbcOae9bTs/Qxt0BD04dMw92xAeApxnX0bttGzMA/uwgp28EhKi8JvPhWrhhZc8xahFa+Cw0Vk97rE1XTQh+/Fu7GNOh5hd/Xl28xoUs2EOx1YCOwgmsk6VAjxRSnl4r4zTdGe+57vHRfE0fLJxiZM00LXB0Te/oDArN3TefSDtKJxwq2xwjIcwPf3nxI5+ysE3/pToqCG/Jj1+zHKRxHe8gktL/y2ewNCfqz6A+hlI47tjWQxqX6afgucI6U8TUp5KrAAuLvvzFK0573V9WyrTn9b+KUZkhSi6B2MyjFg60F8t5QEX/9jUt+wyCtBLx0OQOiz91O6nJZfijbAu2KkKsA2KeXGIy+klJuAgV1Hrh954KW96TYBgIpiVZAnlxA2J3nX/hxRUH5s18kvxXvVj2NZbV0V+TmCPmwq3it/POAz4VLdhFsmhPgz8NfW19cCn/aNSYr2mKakLkPqMJQWKAHONbTiKrS8YsyOmXE9IeTHv+ghrJAf2XgQrXUlnBSbE88Fd2CfNO/o75dDpCrAXwH+Dfg6UR/wYuCPfWWUog1/yEqpG0Zf43EKvK6BvVrJRfyLHsTcs+GYriEDzXFV00xfHcJdgGxJTN7RiquU+LYjVReEAdwjpbxUSnkJcC+gPo39gNelU5yX/ubVgwc50m2CoheRUhLeuYbw1tQaGhhjZvfo+qKwAveFd0AHF4N1YCsylN5O35lEqgL8JtA+VsQFvNH75ig6EgpbNPjS74LYvDeg+sLlCNIyaX7ihzT/7btJV6ntMUYeh/uyH+Cafys4vSnfw1Y5Fse0sxNLUCKQUiKt3muZlc30pBxlrHqzlLJZCKFSo/oBXRPYDQ1/KP1lmDUVgZYTRLZ9SmTHypTmClce/hf/N7pqTbFgjzF6Fs5Tr4u+cBdAXBKGpOG3V4DQcJx0Be7Tb+ih9blFqh8pnxDi+CMvhBAzAfUc0Q8IAXoGOHs0Daz0/w1Q9AKWP/VwwvD6xdHOyEnE133xnWglw2Kv9aqJFHzjSfKu+gmaK5o56Z5/CyTr+SYtgh88RaR9Nt0AJNUV8B3A34UQRypqVAJX9Y1JivY0+CI0+49O+QQ9bz/UGZYFh5vDKhIiB7CNOaHTTTKE1ia2ug3M5AmvWvFg7BNOwT7+ZCLbl4Nuwxg+LSGszDHlDIwhk4jsXk/LC79JuI5ZvRmjfOBmWKbalPMTYALRaIivAhOllCoMrR8oyrMxtOzoNsAumVfS5fHSAoOf3zySISXdi+rgQXZK8lXody6gufLIu/F32KcvoGOLVufcL2CbcgaOmRfiueyHCceN4dNwnnwledf9EqHpCN3ANuYEbCOPi4mv1dKI1VATO0cvLMcx9Qy04iEJtgz0ojwptaUHEEKcTGtTziNjUspH+8as1BgIbelDYYsfPrKNNdui5SBLCwyaAxb+YHSVYjcEFcV2fAGTYEgikThsGk1+k3BEUujVsSxobEnc9EjWpisZBR6dX9w6mpEVAzdnP1cJffY+/nf/igz6MCrHEt6+EiJBtJLhCKcHc8/66ES7C+fJV+I6+cour+d/ZyGBj54FK4Ix8ni8l/0gVnvYrD9A8xM/xKqrBpsD1/ybcR5/QV+/xUwhadHXVGtB/BUYDawkWpoSok+3aRXggcBryw7HxBfgYEN8REQoIpkzIZ8XP6olELIwDIEv0DanvtnEaU/+oJNqN5gGn8memqAS4BzEPuEU7BNOwfI30fB/N8TSjK1D8e2DCPmxj50TeymlJPDBU4TWvo2WNwjX6V8E3SDwQVtVtcj25QQ++geuU69DBlsIfPAUALaJ83CfdSta3qC+f4MZTqo+4FnAJDnQGzilge3V3e91/n3xwdj34UjijyjQCxEU97+4l7lTCwZ8C5lcxWo82G1TTvPw3li9h+Dylwi8G02MtWr30PzUj6Khah0Irnwd26jj8T3/O6z66uj8un34fHXkXXdXL7+L7CPVKIi1QEVfGqJIjmFkhuAdbopQU68qkOYSlq+e8PYVWIHm7uNyHW6MYVNjLyNb47eApL8JYU+MTJXNtTQ9+p8x8Y2dv2sNMhw4euNzhFRXwCXAeiHEUuI7Yny+T6xSxDjcmBmip2tQlAEZeYreIbR+Mb4Xfhvt02Zzog/qvCqZMWI6rtNuiIWWAeilwwlvWdo2SdMxqsajlQyLb3ffSSyOcBeAobIrU/1E/bgvjVB0TnGGRB6MqXJhN1QmRi4gpaTljYfammSGA5gHtiSfrOl4LvkemBEan/wvzG0roppqOIiJq2HHfdbtaHmDcJ58BS3Pt68FnNxraT/uPOXOIvUwtHeT/evqHCHEw0KIGiHE2nZjxUKIRUKIza1fi1rHhRDiXiHEFiHE6vZJHwOd8+ekf6NC1+BLF1al2wxFb2GZSF+HNlSdbO84Zn8ezZVHy6IHMLctB2R0bjhATFwtE9u4E6PfJy1FGS8zWumIbqMpBgpdroCFEE0k/xMmACmlzO/i9EeA3xMfKfFd4E0p5V1CiO+2vr4TOA8Y2/pvDnBf69cBT0Nz+nPmJ43wMHGYJ91mKHoJoRvYJ51KaN07bWP5ZcjGmrh5+uBxuOffitXSSGT7is4vaJlEqjdhGzMb/0fPJBz2XPpdrOY6rKZa9IpR2MeeiDAy48ku3XQpwFLKo+7EKKVcLIQY0WH4IuD01u8XAu8QFeCLgEdboyw+EkIUCiEqpZTVDHD6uiV9KqzZ5uPxN6u5Zn5luk1R9BLu87+ONmgoZvUmjOFTwV2M//lfxc2xjZ6NeWgXTY/+JzLQ3MmVogSXvYDmLUbWxrfOEoOGYp9wCjLkR1omWg8K+gwE+vvTXX5EVKWU1UKIstbxKmB3u3l7WscSBFgIcTtwO8CwYcM6Hs45ygozY6XwtzdrlADnEMLmwDX36tjrpr9+p8MEgf248wgs/mu34gsQ2b6CyPjEDsciEsK/+DECHz0DZgT75NNxX/AfCD39C4tMIFN2VZJ545M6paSUD0opZ0kpZ5WWlvaxWeknYsnkKTT9jCXBF0i/O0TRNySEhEkQQiBDqYeKJWsvJJxeAkueiMYYS4vQ2rcIrXnzWM3NGfpbgA8IISoBWr8ecTrtAdrHwQwB9qFg36FQrxXUOVaqD6e/Maiib3DMvDDutW3CKWieQhzHnZe8mlkH9NIR2KfNxxg6ud2oQB8yMWGueXBnwthApb+fA54Hvgjc1fr1X+3GvyaEeJLo5luD8v9GGVXppCjPSHtfuEH5NkaUq1TkXMMKNGPV7sE++XS0vEGEt3yCXjIc+/SzALANn0rejb8jtO5dhDufyL5NRDZ92HYBzcB5ylU4Zn0Ooel4r/oJwZWvYzUcwD5hLsJbRGjFK9Au0UOvHNvfbzNj6TMBFkI8QXTDrUQIsQf4EVHhfVoIcQuwC7iidfrLwPnAFqAFuKmv7Mo2bIbGiRPzeWXp4YRjgmhBnaPtGTd5mIv1u/zdrrAFcP1Z5Rh6JjhDFL1FaP17+F66G8JBhLsA75U/wn3OlxPmGa2C2fzUj5Et9aDpCFcB+qAqXKfdgDF0UmyusLtwnnBR3Pney3+I/92/Yh7cBVaElhfvRjbV4jzp8r59g1lAytXQMpGBUA1NSsmFP1id9sacVSV2/vStxMdJRXYiLZOGe6+Prwms29DyS3GedDmOGQvi5jc99l0iu9a0DWg63mt/gS3O5dA5vpfuIbTq9bjzC772CJq3+FjeRjaRdPWSKZtwik4ImzLt4guw91AIMxMMUfQOoUBiQXYzjFW3j5aX7yWyb2P8obj0YsAyaf7H/yDbFfAJbfwA34t3E/jw7wmNN62Obe8tk/D+rcf8NrIdJcAZTial/+4/3HW1LEX2IJwejFGdJ5xGdq6OfR9avzh59wx/Y2xDLbjyNXzP/IzQ6jfwv/0Izc/8LG6qfWJiK/qWf/0KmWKfuVwlcz7dik4pK8yMmMnSDIlJVvQOnou+g2Pm59BaS0y2R69o2ygLrnyt02tE9n7WOufV+PHtK+K6YtinnAEdY3+DLUR2rDoa03MGJcBZwJ1XJ35A+htDy6zVuOLYsJrr8D37c4KfvgDhALZJp0YL7Nic0bZEI2fE5gpX5wmxgfceR0qJcHaYoxlgd2E11ND46Lep//VlSbu6CndBr72nbCQzllaKLgmnNwINQEVA5Bj+tx6OuRms+gPIcIiCO/6G0G0JWWrOk68kvO1TCLYkXEcGW0BauOZdQ9Oe9dDq+3WefAWaK4/mF+/G3LOhdXK8AOuDxw/ohpygBDgrWLS8Nt0mYM+QwvCK3iFSvTnutfTVIVsa0QrLE+Ya5aPQ8suwDu5IOGafNh+h6RhVEyj46sMEV7yC9DehFVUQ+PhZwrvXJ54z80Jsw6Yk9QsPNJQAZzj+oMlbK+q7n9jHzBp/1HWZFBmIbfg0grVt5Ve0okq0guSp/ebhvQniK1x5OOddi+P482NjoXXvEHi36zaRevkoPAu+cvSG5xhKgDOcZ947mHLzzL5keEViuxlF9uI640ZkJEh481L0kmG4FnwZ0UnKseYpivqHI22p6MbwaThnfS5u3pGmmwkIAQ4vRsVo3Od+tdfeQy6gBDjDCZsZoL7Axl2+7icpsgbhcOO58Bspz3XPv4WWNx4EM4KWX4rr1OsTJybZZIteQKfw3x5GONQf8Y4oAc5wrji1lGcW12CmOVzS5VAREAMZx8wLsE2Yi9VwAL1idNLKZ445lxB4Z2Hi+IwFSnw7QQlwhuN1GfzpWxO47XefEUljNchTpxWl7+aKfkGaYSK716N5i9FLEpt0ap4CNE/nYWOuk6/EqBhNZPd6hMONDLagl4/CNv7k6PXDQSJ71qMVVqAXqdrSoAQ44zEtyS+e2JlW8fW6NGaNU5twuYzZUEPzY3fGkiccsz6P+5wv9fg6tlEzsY2amXj9gztpevz7rb3oBM5Tr8U19wvHanbWowQ4w/nks0Y27fF3P7EPafZbvLemntOmq1VwrhDespSWRQ9hNR7EPvk00G1xmWvBZc/jmHkB+qAhvXI//5In2jUClQSWPIHjuPPQPIW9cv1sRQlwhrPzQOodCfqSVz85rAQ4R7ACzTT/85etnY0htPoNtEGJLoeW1+9DhkMI3cAYPB77zAsJrV5EZMcqZDiIVlyFc/bn0ctHEfzkX0R2r8OomoDjhEtAQPCT54nsWY9RNQGrqUMsu2Vi1u5VApxuAxRd43Unbnakg5o61Q0jVzBrdsTEN0aSLsWR7Svbvt+5muDK15D+xrbrVG8ivPF9bONOJrz+HQDCmz8mtHUZwuYgsm15dGzTR+hJylb633gA2833HvsbymLU1naGk58hAnygPpxuExS9hF42AmzOuDH7uJPwXP5f2CbMRR88Lul57cU3RiREeOP7cUPm7nUx8Y2NVW9GK66KH9u/NVqkfQCjBDjDGT04M8J3TAvqm5QI5wKa04v30u9FBdFwYJ9+Ns6TLsc+7kTc534V6e++C3J7RAqt5jVvEXrHug+agXDn9+heuYZyQWQ4oXBmJGIANAdMCvNUScpcwDZ6FgWjZyWMB5Y8iVWXrB+uwDbpVMIbloBsC8kxhk7BccJF+P71m7hMuTh0G675t6EXVxHZtaYtEmLuF5QPON0GKLpm7bamdJsQw6bKUeY8ZpKCO65zvox97By0gjKss27FrNmB1DQ0mxOjagIAxr8vJLR+Mf43HgIz+qSkFVbgOvtLGFXj0VrLThb821+iscZFFeiFFf32vjIVJcAZTlmxI90mxGhqiVBeZE+3GYo+xDZ6Vlw3DOEpwnHcuQg9+uSjeYuT9nHTXHk4Z16AbdgUgmvfQnN4sM9YEBPe2PUMe1yt4YGOEuAMp8CTGZtwAFUlmfPHQNE3YUs2pgAAD7xJREFUOE64GBlsIbThPbSCclxn3hgT31TQS4fjPkM1NU8VJcAZTk19ZvRh0zVwOTLnj4GibxCajuu063GdlqTYjqLXUU69DKe+OY05yAqFok9RApzhnHlcEZnQi2LCME+6TVBkCNIyCW9dRnjrMqSlFgjHgnJBZDgep85PbhzJTx7dnraSlFNGerjr1tHpubkio5ChAE1//Q7mga0A6BVjyLv+l4gOiR2K1FAr4Cxg/+FQWusB+4Mmh1UShgIIrX83Jr4A5v4thDa8l0aLshslwFnA8x8eTOv9t+4LcN/ze9NqgyL9WE2HCK58NWG8p5lzijaUCyLDOdwUYs/B9EdCLNuYpA6AYsAgpaT5yR8lJGoIh0d1Nz4GlABnOE+/XdP9pH4grPZaBjRW7Z5E8fUU4bn0e2oj7hhQApzhHG6OpNuEGM1+E69LxQIPRIS3CAw7RNqexoTdRfNj3wVpYYyehffS7yNsKlmnJygfcIaTl0GC19SSOX8MFP2L5vTiOvMW0KNrNuEpihbtkdHd4cjWZQRXLUqniVmJWgFnOCUFmfMjavarR82BRqR6M6F176B5CrHPOBf7pHlYDTVE9m/F/8r/xc1NXkVN0RWZ8+lWJKWpJc396NsxerAr3SYo+pHI7nU0/e170OrjDa19h7xb7sVwF6B5i/AbjrgSlLZxJ6bL1KxFuSAynExadQbDmfPHQNH3BFe8GhNfiJaqjOxeD4CWV4L36p9ijJ6FMXQKnovvxDZ8WrpMzVrUCjjDGZxBFcgsmTnF4RX9QJLsNmFvG7MNm4Jt2JT+tCjnUCvgDOfc2cXkZUhfODKiKoWiv3CecDHC1dYyyDbuRIzKsWm0KPdQK+AMp9Br4+6vjOHW325Mqx0VxXY8zkz5Q6DoD/RBVeR/+UHCWz9B8xRhjIgvpC6DLYQ2f4QwHNjGnIBI0llZ0TVKgLOAb9+/Jd0mMChP/aoMJGQogAz50bxFOKacmXDc8tXT9Jc7sBqjafJ6xRjybviNEuEeoj5VGc7mvS3U+9K/EbduZwuHGsKUFKgPWK4T+OR5/O8shHAAY9TxeC/5HsIR3507tOr1mPhCtChPePNHKi25hygfcIbT7M+c5IdQREVB5Dpm/YFoY81wAIDItuUElj6XME9GEuuTJBtTdI0S4AynvDAzoiAG5RsMHpQZtij6Dqt2dyy77QjJOiXbp86HdqtikVeCfdxJfW1ezqFcEBlOcX5m/IiKvJlhh6JvMYZMigprsCU2Zhs9O2GeXlRJ/s33Elr9Bhh2HNPPTnBTKLpHfaoynA/XZ0YZyK37AoQjFjZDPTTlMsLhJu+qn+J/969YvnocU8/EMf3spHP1okrVvPMYUQKc4TQH0r8BByCJZuUV5SkBznWMIRPJu/bnvX7d4IpXCXzwNEgLx5xLcc7+fK/fI9tQn6YMx+PMnB9RXQaVxlRkF5F9G2l55f+wGg5gNR7Ev+gBwjtWpdustJM5n25FUvzBzIk8GFWpivEojo7IrrVJxtakwZLMQglwhjOiTHWbVWQ/epIUZr1yXBosySyUAGc4/3gvvQ05j6CpMhCKY8A2fBrOU68HuwtsDpwnX4l97AnpNivtqE24DKfRlxl+10IVhqY4Rlxzr8Z58hUACE3VFQG1As54bj2/Mt0mAHD92RXpNkGRAwhNV+LbDiXAGc7E4V5GV6Y3A83t0Jg9Pr/7iQqFokcoAc5w9tUG2Vod7H5iH9IStFj06eG02qBQ5CJKgDOc99c2pNsEAMKqEI9C0esoAc5w9tWmd/V7BF9ACbBC0dsoAc5wGjIk++yNT2vTbYJCkXOkRYCFEDuEEGuEECuFEMtax4qFEIuEEJtbvxalw7ZMY8GszPjf4AtK9h3KjNW4QpErpHMFfIaUcoaUclbr6+8Cb0opxwJvtr4e8AQzYwEMgN2msjEUit4kk1wQFwELW79fCFycRlsyhrrmcLpNiFHgUckYCkVvki4BlsDrQohPhRC3t46VSymrAVq/liU7UQhxuxBimRBi2cGDmZGm25e4M6gaWigi022CQpFTpGtJc4qUcp8Qooz/3969x/ZZ1XEcf39637putN3Wld2EbFwmCmwVJF4iMGASicFg1AAhSEJIJERjNJoYJUYNMUIM6h8ssICKwIhBpkO5LBBBcFJ0wJxch5Ot69qtDHbpjfb4R582ZXRbtz3tOb+Hz+uf/vrk+fV82/x+nz07v/N8Dzwq6aXxPjGEsBJYCdDS0lL4RHh6YxoN2QEGBwv/5zabVFEur0IIbdnXDuAB4Cxgh6RmgOxrR4zaUjOlKp0r4JqEajErgkl/R0mqlVQ3/Bi4ENgIrAGuyk67CnhwsmtL0fJlaayCkPB2RGY5izEF0QQ8IGl4/N+FEP4i6VlgtaRrgP8BX4xQW3KWLp5OZQX0R14N8anT3AvCLG+THsAhhM3A6WMc3wWcP9n1pG5wMBy4S3gUra/sjV2CWeH4/5SJe+CpDlJow7C/dzCZ26LNisIBnLjHN+yOXcIITwGb5ctvqcSlsi09QG2NG2mb5ckBnLjG6ZWxSxjR1tUXuwSzQnEAJ2750obYJYzY0t4TuwSzQnEAJ+6VrftilzBiYVPcrZHMisYBnLg3tqdz1bl4Xm3sEswKxQGcuIoKt4A0KyoHcOI6d6fTjrKtM52rcbMicAAn7vjGqtgljCh3Q3azXDmAE3f1iubYJYyorvA6YLM8OYATd9K8Wprq468Fnj+zmuOmeUcMszw5gEvA7d88hRPnxF0CdvWKOVHHNysiB3AJeH7zXja3x22Ec9vatqjjmxWRA7gE3Lz6zdglsDuhzUHNisIBXALe2R9/b/rg7eDMcucATlzXnn4GEugHPJBOUzazwnAAJ+7R57pilwDAQIDuXqewWZ4cwImbNzOdBjhVlX65mOXJ76jEVSV099k7++LPRZsViQM4cX/b+HbsEka8uq07dglmheIATlwKKyCGLVs8LXYJZoXiAE7cOUuOi10CALXVUF7ul4tZnvyOStzypfWUJTANfM3Fc2OXYFY4DuDESeL7V34oag1z6iuT2pvOrCgcwCXg7FNn8NULZ0cbv/2tfu748/Zo45sVlQO4BNz1yHZWPdIRtYZUbggxKxIHcAm49/G44QsQcDMIs7w5gBM3kEIjCKC7N7DftyKb5coBnLiuhNpAvt7mGzHM8uQATtxzr+yJXcKIJQumxi7BrFAcwIlb/UT8+d9hfe96HtgsTw7gxA0688wKywGcuI+cUBu7BADmNpYzpdrb0pvlyQGcuIFELoHbdnkFhFneHMCJW7poeuwSAAjAlh1eBWGWJwdw4pYva6ChriJ2GQBMq/EUhFmeHMAl4NbrTyJ2J8i5jVU0zqiKW4RZwTiAS0B5magsj9uT8rpL3I7SLG8O4BJw3xM76OmP+2Hcmmd2Rh3frIgcwIkbGAg8tH5X7DLo3N0XuwSzwnEAJ+7h1q4k7kDbsqOXPd3p7E9nVgQO4MS9vHV/7BKAoWVobTt7Y5dhVigO4MSdd2Yam3LC0IeBZpYfB3DiTj+xjqqKNIKvubE6dglmheIALgFXXtAUuwQA+hOYizYrEgdwCUilJeXb+/whnFmeHMCJe3XbfvZ0x9+WqLpSLGyqiV2GWaE4gBP328faY5cAQG9/oL3LqyDM8uQATtyc+jT6L5SXQa2b8ZjlygGcuCsvaKbyELnX3DC+gK4c1VDtopb69ywpmzqOH3HF8jnUTU2jK5tZUSiE0v1ku6WlJbS2tsYuY8INDAbuWdfO86/vZdG8Gk5dWEdtdTm1NWWcsqCWNzt7ePKF3Sw6fgq9/YGe/kEa6iro7hskBFgwu4am+kpefGMfc+qrmD+7hp7eAdY8s4vG6RWcv7SB7bt6Wbt+JxXlokxi/uwaplSV0f5WHx87eTpzZ3oJmtkxGHMtqQPYzGzijRnAnoIwM4vEAWxmFokD2MwskuQCWNIKSS9Lek3Sd2LXY2Y2UZIKYEnlwK+AzwJLgK9IWhK3KjOziZFUAANnAa+FEDaHEPqAe4HPR67JzGxCpBbAc4E3R32/NTs2QtK1kloltXZ2dk5qcWZmeUotgMdaK/eehcohhJUhhJYQQsusWbMmqSwzs/ylFsBbgfmjvp8HtEWqxcxsQqUWwM8CiyWdIKkK+DKwJnJNZmYTIrlbkSVdDPwcKAdWhRB+fIhzO4Etk1VbiZsJ7IxdhBWKX1PjtzOEsOLAg8kFsE0MSa0hhJbYdVhx+DV17FKbgjAz+8BwAJuZReIA/uBYGbsAKxy/po6R54DNzCLxFbCZWSQOYDOzSBzABef2npY3SaskdUjaGLuWUucALjC397QJcifwvpsK7Mg5gIvN7T0tdyGEvwJdsesoAgdwsR22vaeZxeMALrbDtvc0s3gcwMXm9p5mCXMAF5vbe5olzAFcYCGEd4HrgYeB/wCrQwj/jluVlTpJ9wDPACdL2irpmtg1lSrfimxmFomvgM3MInEAm5lF4gA2M4vEAWxmFokD2MwsEgewJUHSgKQNkjZKul/S1Ng1jSZp75EcNxsPB7ClojuEcEYI4TSgD7huvE/Mur6ZlRwHsKXoSWARgKQrJP0juzq+bThsJe2V9ENJ64FzJN0kaZOkFyT9LDtnoaR12bF1khZkx++UdKukpyVtlnRZdnxadt4/Jb0o6ag6xx1i3EskrZf0L0mPSWrKjt+Y9dh9IqvnhmP9A1ppcABbUiRVMNS/+EVJpwJfAj4RQjgDGAAuz06tBTaGEM4GNgGXAh8OIXwU+FF2zi+BX2fH7gZuHTVUM/BJ4HPATdmxHuDSEMJS4FzgZkljNTQ6nION+xTw8RDCmQy1Bv32qOecAlzEUAvRH0iqPIpxrcRUxC7ALDNF0obs8ZPAHcC1wDLg2SwHpwAd2TkDwO+zx+8wFJ63S1oL/Ck7fg7whezxb4CfjhrvDyGEQWDT8JUoQ93jfiLp08AgQ607m4D2I/xdDjbuPOA+Sc1AFfDGqOesDSH0Ar2SOrJxtx7huFZiHMCWiu7sKndEdvV5Vwjhu2Oc3xNCGIChnheSzgLOZ6jh0PXAeWM8Z/R9972jh8q+Xg7MApaFEPol/ReoOZpf5iDj/gK4JYSwRtJngBsPUs8Afm9+IHgKwlK2DrhM0mwASQ2SFh54kqRpwIwQwkPA14HhIH+aoUCGoXB96jDjzQA6svA9F3jfWON0sHFnANuyx1cd5c+2AvG/spasEMImSd8DHpFUBvQDXwO2HHBqHfCgpBqGrma/kR2/AVgl6VtAJ3D1YYa8G/ijpFZgA/DSOMqcKmn0VMEthxj3RuB+SduAvwMnjOPnW4G5G5qZWSSegjAzi8QBbGYWiQPYzCwSB7CZWSQOYDOzSBzAZmaROIDNzCL5P1dBdtFwUJdpAAAAAElFTkSuQmCC\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# Lets try income vs loan\n", "sns.catplot(y='Income', x='Personal Loan', data=df_original)\n", "# Quite evident, people whose Income is between 100 and 200 tend to take loan more compared to ones present in lower income.\n", "# SO field relation to income has proven to have good influence on personal loan, lets see what else fields we have relation to\n", "print(df_columns)" ] }, { "cell_type": "code", "execution_count": 29, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 29, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "sns.catplot(y='CCAvg', x='Personal Loan', data=df_original)\n", "# People whose credit card average is between 2 - 6 seems to have more personal loans \n", "# that other range as seen from graph below" ] }, { "cell_type": "code", "execution_count": 30, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# One more column we have in our dataset which doesnt corresponds to any income values but is the one which affect it\n", "# Family can we say that people where more family members are present have takne personal loan\n", "# sns.relplot(x='Personal Loan', y='Family', data=df_original, fit_reg=False)\n", "sns.relplot(x=\"Family\", y=\"Income\",hue=\"Personal Loan\", data=df_original);\n", "\n", "# We can conclude from this graph that, people who have 3 or 4 family members and whose income is above ~100 to ~200 tend to opt\n", "# for personal loan more than a different ranges as observed from graph.\n" ] }, { "cell_type": "code", "execution_count": 31, "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", "
Family1234
Personal Loan
0136511908771088
1107106133134
\n", "
" ], "text/plain": [ "Family 1 2 3 4\n", "Personal Loan \n", "0 1365 1190 877 1088\n", "1 107 106 133 134" ] }, "execution_count": 31, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Little More exploration using categorical columns\n", "pd.crosstab(df_original['Personal Loan'],df_original['Family'])" ] }, { "cell_type": "code", "execution_count": 32, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 32, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "#Box Plot family and personal loan coparison\n", "sns.boxplot(y=\"Family\", orient=\"v\", x=\"Personal Loan\", data=df_original)\n", "# People are from 3-4 most probably these are people, having 1 more children seems to have opeted for personal loan" ] }, { "cell_type": "code", "execution_count": 33, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 33, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "#Income and Personal Loan\n", "sns.boxplot(y=\"Income\", orient=\"v\", x=\"Personal Loan\", data=df_original)" ] }, { "cell_type": "code", "execution_count": 34, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 34, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# Lets Analyse using count plot\n", "sns.countplot(x='Personal Loan',data=df_original)\n", "# Even though we have established alot ot relationship between family, age, income, ccavg, income and decided to go further.\n", "# But the content of our data seem insufficient, we have very few cases of People who have opted for personal loan and\n", "# More cases of people who have rejected personal loan offer from bank. This imbalance sometimes can affect in model building\n", "# But in our case this is acceptable, because in real life people who take pl would be less." ] }, { "cell_type": "code", "execution_count": 35, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 35, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYsAAAEGCAYAAACUzrmNAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjMsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+AADFEAAAa2UlEQVR4nO3dfZBU9b3n8fdHREeven1g8CIDGTCYBIE7mhEpoxYbXEWyikmuuSCrGLDQFEZdtDbEm1I0sZKNJuYSXS2yonJDQCNyRdeHSwjoJRERlCAPPoyCOkABQhY1qJHxu3/0GWihZ04zme4zY39eVV3T/e3fOf0NU/Ez5/x+fY4iAjMzs9YckHUDZmbW8TkszMwslcPCzMxSOSzMzCyVw8LMzFIdmHUDpdKtW7eora3Nug0zs05j+fLl70REdaH3PrNhUVtby7Jly7Juw8ys05D0Zkvv+TSUmZmlcliYmVkqh4WZmaX6zM5ZmFll+Pjjj2lsbOTDDz/MupVOo6qqipqaGrp27Vr0Ng4LM+vUGhsbOfzww6mtrUVS1u10eBHBtm3baGxspE+fPkVv59NQZtapffjhhxxzzDEOiiJJ4phjjtnvI7GShYWkXpIWSlorabWkq5P60ZLmS3ot+XlUUpekqZIaJK2UdHLevsYm41+TNLZUPZtZ5+Sg2D9t+fcq5ZHFLuDaiPgSMASYKKk/MBlYEBH9gAXJa4BzgX7JYwJwF+TCBbgROBUYDNzYHDBmZlYeJQuLiNgUES8kz98D1gI9gZHA/cmw+4ELkucjgRmRswQ4UlIP4BxgfkRsj4g/A/OB4aXq28w6vy5dulBXV8eAAQO48MIL2blzZ9Ytfcphhx22X/WOoCwT3JJqgZOA54BjI2IT5AJFUvdkWE/g7bzNGpNaS/VCnzOB3FEJvXv3Lrq/i25YVPTYjuA3Nw/NugWzDu2QQw5hxYoVAIwZM4a7776bSZMmFbVtU1MTXbp0KWV7nVLJJ7glHQbMAa6JiHdbG1qgFq3U9y1GTIuI+oior64ueHkTM6swZ5xxBg0NDQD8+te/ZvDgwdTV1XH55ZfT1NQE5P6iv+GGGzj11FN59tlnmTx5Mv3792fQoEFcd911ALz55psMGzaMQYMGMWzYMN566y0ALr30Uq666ipOO+00+vbty0MPPQTA+++/z7Bhwzj55JMZOHAgjzzySJv6b+lzH330UU499VROOukkzjrrLDZv3gzAlClTGDduHEOHDqVv375MnTq17f94eUoaFpK6kguKmRHxcFLenJxeIvm5Jak3Ar3yNq8BNrZSNzNr1a5du3jiiScYOHAga9eu5YEHHuAPf/gDK1asoEuXLsycOROAv/zlLwwYMIDnnnuO/v37M3fuXFavXs3KlSv5wQ9+AMCVV17JJZdcwsqVKxkzZgxXXXXV7s/ZtGkTixcv5rHHHmPy5Nw0bFVVFXPnzuWFF15g4cKFXHvttbTlNtYtfe7pp5/OkiVLePHFFxk1ahQ//elPd2/z8ssv89RTT7F06VJuuukmPv744zb/GzYr5WooAfcAayPi53lvzQOaVzSNBR7Jq1+SrIoaAuxITlc9BZwt6ahkYvvspGZmVtAHH3xAXV0d9fX19O7dm/Hjx7NgwQKWL1/OKaecQl1dHQsWLOCNN94AcnMc3/zmNwE44ogjqKqq4rLLLuPhhx/m0EMPBeDZZ5/loosuAuDiiy9m8eLFuz/vggsu4IADDqB///67/8KPCK6//noGDRrEWWedxYYNG3a/tz9a+tzGxkbOOeccBg4cyK233srq1at3b/O1r32Ngw8+mG7dutG9e/c2fe7eSjln8RXgYuAlSSuS2vXAT4AHJY0H3gIuTN57HBgBNAA7gW8DRMR2ST8Enk/G3RwR20vYt5l1cvlzFs0igrFjx/LjH/94n/FVVVW75ykOPPBAli5dyoIFC5g9ezZ33HEHv//97/fZJn/56cEHH/ypzwGYOXMmW7duZfny5XTt2pXa2tp2+ZZ58+d+97vfZdKkSZx//vksWrSIKVOmFOynS5cu7Nq162/+3FKuhlocEYqIQRFRlzwej4htETEsIvolP7cn4yMiJkbE8RExMCKW5e1rekR8PnncW6qezeyza9iwYTz00ENs2ZI78719+3befHPfK3K///777NixgxEjRvCLX/xid+icdtppzJ49G8gFwemnn97q5+3YsYPu3bvTtWtXFi5cWPCzitHS5+7YsYOePXNrfe6///4Wt28vvtyHmVWE/v3786Mf/Yizzz6bTz75hK5du3LnnXfyuc997lPj3nvvPUaOHMmHH35IRHD77bcDMHXqVMaNG8ett95KdXU1997b+t+tY8aM4bzzzqO+vp66ujq++MUvpva4c+dOampqdr+eNGlSi587ZcoULrzwQnr27MmQIUNYt27d/v6T7Be1ZcKlM6ivr49ib37kpbNmndfatWv50pe+lHUbnU6hfzdJyyOivtB4XxvKzMxSOSzMzCyVw8LMzFI5LMzMLJXDwszMUjkszMwslb9nYWZWQHsvqS92yfuTTz7J1VdfTVNTE5dddtnua01lzUcWZmYdRFNTExMnTuSJJ55gzZo1zJo1izVr1mTdFuCwMDPrMJYuXcrnP/95+vbty0EHHcSoUaPafGnz9uawMDPrIDZs2ECvXnvuyFBTU8OGDRsy7GgPh4WZWQdR6PJL+Ve3zZLDwsysg6ipqeHtt/fcRbqxsZHjjjsuw472cFiYmXUQp5xyCq+99hrr1q3jr3/9K7Nnz+b888/Pui3AS2fNzArK4urOBx54IHfccQfnnHMOTU1NjBs3jhNPPLHsfRTisDAz60BGjBjBiBEjsm5jH6W8B/d0SVskrcqrPSBpRfJY33y7VUm1kj7Ie+/uvG2+LOklSQ2SpqqjzPaYmVWQUh5Z3AfcAcxoLkTEPzc/l/QzYEfe+Ncjoq7Afu4CJgBLyN2nezjwRAn6NTOzFpTyHtzPANsLvZccHXwLmNXaPiT1AI6IiGcjt6ZsBnBBe/dqZmaty2o11BnA5oh4La/WR9KLkp6WdEZS6wk05o1pTGoFSZogaZmkZVu3bm3/rs3MKlRWYTGaTx9VbAJ6R8RJwCTgN5KOAArNT7R40/CImBYR9RFRX11d3a4Nm5lVsrKvhpJ0IPAN4MvNtYj4CPgoeb5c0uvACeSOJGryNq8BNpavWzMzg2yWzp4FvBwRu08vSaoGtkdEk6S+QD/gjYjYLuk9SUOA54BLgF9m0LOZVZhXb7u0Xfd3wnX3pY4ZN24cjz32GN27d2fVqlWp48uplEtnZwHPAl+Q1ChpfPLWKPad2D4TWCnpT8BDwBUR0Tw5/h3g/wANwOt4JZSZfUZdeumlPPnkk1m3UVDJjiwiYnQL9UsL1OYAc1oYvwwY0K7NmZl1QGeeeSbr16/Puo2CfG0oMzNL5bAwM7NUDgszM0vlsDAzs1S+6qyZWQHFLHVtb6NHj2bRokW888471NTUcNNNNzF+/Pj0DcvAYWFm1kHMmtXq5fIy5dNQZmaWymFhZmapHBZm1unl7mBgxWrLv5fDwsw6taqqKrZt2+bAKFJEsG3bNqqqqvZrO09wm1mnVlNTQ2NjI76HTfGqqqqoqalJH5jHYWFmnVrXrl3p06dP1m185vk0lJmZpXJYmJlZKoeFmZmlcliYmVkqh4WZmaUq5W1Vp0vaImlVXm2KpA2SViSPEXnvfV9Sg6RXJJ2TVx+e1BokTS5Vv2Zm1rJSHlncBwwvUL89IuqSx+MAkvqTuzf3ick2/1tSF0ldgDuBc4H+wOhkrJmZlVEp78H9jKTaIoePBGZHxEfAOkkNwODkvYaIeANA0uxk7Jp2btfMzFqRxZzFlZJWJqepjkpqPYG388Y0JrWW6gVJmiBpmaRl/janmVn7KXdY3AUcD9QBm4CfJXUVGBut1AuKiGkRUR8R9dXV1X9rr2Zmlijr5T4iYnPzc0m/Ah5LXjYCvfKG1gAbk+ct1c3MrEzKemQhqUfey68DzSul5gGjJB0sqQ/QD1gKPA/0k9RH0kHkJsHnlbNnMzMr4ZGFpFnAUKCbpEbgRmCopDpyp5LWA5cDRMRqSQ+Sm7jeBUyMiKZkP1cCTwFdgOkRsbpUPZuZWWGlXA01ukD5nlbG3wLcUqD+OPB4O7ZmZmb7yd/gNjOzVA4LMzNL5bAwM7NUDgszM0vlsDAzs1QOCzMzS+WwMDOzVA4LMzNL5bAwM7NUDgszM0vlsDAzs1QOCzMzS+WwMDOzVA4LMzNL5bAwM7NUZb2tqplZvotuWJR1C/vtNzcPzbqFTJTsyELSdElbJK3Kq90q6WVJKyXNlXRkUq+V9IGkFcnj7rxtvizpJUkNkqZKUql6NjOzwkp5Guo+YPhetfnAgIgYBLwKfD/vvdcjoi55XJFXvwuYQO6+3P0K7NPMzEqsZGEREc8A2/eq/UdE7EpeLgFqWtuHpB7AERHxbEQEMAO4oBT9mplZy7Kc4B4HPJH3uo+kFyU9LemMpNYTaMwb05jUzMysjDKZ4Jb0L8AuYGZS2gT0johtkr4M/LukE4FC8xPRyn4nkDtlRe/evdu3aTOzClb2IwtJY4H/BoxJTi0RER9FxLbk+XLgdeAEckcS+aeqaoCNLe07IqZFRH1E1FdXV5fqf4KZWcUpa1hIGg58Dzg/Inbm1asldUme9yU3kf1GRGwC3pM0JFkFdQnwSDl7NjOzEp6GkjQLGAp0k9QI3Ehu9dPBwPxkBeySZOXTmcDNknYBTcAVEdE8Of4dciurDiE3x5E/z2EVzuv0zcqjZGEREaMLlO9pYewcYE4L7y0DBrRja2Zmtp98uQ8zM0vlsDAzs1QOCzMzS+WwMDOzVEWFhaQFxdTMzOyzqdXVUJKqgEPJLX89ij3fqD4COK7EvZmZWQeRtnT2cuAacsGwnD1h8S5wZwn7MjOzDqTVsIiIfwX+VdJ3I+KXZerJzMw6mKK+lBcRv5R0GlCbv01EzChRX2Zm1oEUFRaS/g04HlhB7nIckLv6q8PCzKwCFHu5j3qgf/NVYs3MrLIU+z2LVcA/lLIRMzPruIo9sugGrJG0FPiouRgR55ekKzMz61CKDYsppWzCzMw6tmJXQz1d6kbMzKzjKnY11Hvsuff1QUBX4C8RcUSpGjMzs46j2COLw/NfS7oAGFySjszMrMNp01VnI+Lfga+mjZM0XdIWSavyakdLmi/pteTnUUldkqZKapC0UtLJeduMTca/JmlsW3o2M7O2K/aqs9/Ie/yTpJ+w57RUa+4Dhu9VmwwsiIh+wILkNcC5QL/kMQG4K/nso8ndv/tUckczNzYHjJmZlUexq6HOy3u+C1gPjEzbKCKekVS7V3kkMDR5fj+wCPheUp+RfPFviaQjJfVIxs6PiO0AkuaTC6BZRfZuZmZ/o2LnLL7djp95bERsSva7SVL3pN4TeDtvXGNSa6m+D0kTyB2V0Lt373Zs2cysshV7GqpG0txk/mGzpDmSatq5FxWoRSv1fYsR0yKiPiLqq6ur27U5M7NKVuwE973APHL3tegJPJrU2mJzcnqJ5OeWpN4I9MobVwNsbKVuZmZlUmxYVEfEvRGxK3ncB7T1T/d5QPOKprHAI3n1S5JVUUOAHcnpqqeAsyUdlUxsn53UzMysTIqd4H5H0n9nz6TyaGBb2kaSZpGboO4mqZHcqqafAA9KGg+8BVyYDH8cGAE0ADuBbwNExHZJPwSeT8bd3DzZbWZm5VFsWIwD7gBuJzdf8EeS/5i3JiJGt/DWsAJjA5jYwn6mA9OL7NXMzNpZsWHxQ2BsRPwZdn/34TZyIWJmZp9xxc5ZDGoOCsidGgJOKk1LZmbW0RQbFgfkf2s6ObIo9qjEzMw6uWL/g/8z4I+SHiI3Z/Et4JaSdWVmZh1Ksd/gniFpGbmLBwr4RkSsKWlnZmbWYRR9KikJBweEmVkFatMlys3MrLI4LMzMLJXDwszMUjkszMwslcPCzMxSOSzMzCyVw8LMzFI5LMzMLJXDwszMUjkszMwslcPCzMxSlT0sJH1B0oq8x7uSrpE0RdKGvPqIvG2+L6lB0iuSzil3z2Zmla7s96SIiFeAOgBJXYANwFxyt2m9PSJuyx8vqT8wCjgROA74naQTIqKprI2bmVWwrE9DDQNej4g3WxkzEpgdER9FxDqgARhclu7MzAzIPixGAbPyXl8paaWk6Xl35usJvJ03pjGp7UPSBEnLJC3bunVraTo2M6tAmYWFpIOA84HfJqW7gOPJnaLaRO7ufJC72dLeotA+I2JaRNRHRH11dXU7d2xmVrmyPLI4F3ghIjYDRMTmiGiKiE+AX7HnVFMj0CtvuxpgY1k7NTOrcFmGxWjyTkFJ6pH33teBVcnzecAoSQdL6gP0A5aWrUszMyv/aigASYcC/xW4PK/8U0l15E4xrW9+LyJWS3qQ3C1ddwETvRLKzKy8MgmLiNgJHLNX7eJWxt8C3FLqvszMrLCsV0OZmVkn4LAwM7NUDgszM0vlsDAzs1QOCzMzS+WwMDOzVA4LMzNL5bAwM7NUDgszM0vlsDAzs1QOCzMzS+WwMDOzVA4LMzNL5bAwM7NUDgszM0vlsDAzs1QOCzMzS5VZWEhaL+klSSskLUtqR0uaL+m15OdRSV2SpkpqkLRS0slZ9W1mVomyPrL4LxFRFxH1yevJwIKI6AcsSF4DnAv0Sx4TgLvK3qmZWQXLOiz2NhK4P3l+P3BBXn1G5CwBjpTUI4sGzcwqUZZhEcB/SFouaUJSOzYiNgEkP7sn9Z7A23nbNia1T5E0QdIyScu2bt1awtbNzCrLgRl+9lciYqOk7sB8SS+3MlYFarFPIWIaMA2gvr5+n/fNzKxtMjuyiIiNyc8twFxgMLC5+fRS8nNLMrwR6JW3eQ2wsXzdmplVtkzCQtLfSTq8+TlwNrAKmAeMTYaNBR5Jns8DLklWRQ0BdjSfrjIzs9LL6jTUscBcSc09/CYinpT0PPCgpPHAW8CFyfjHgRFAA7AT+Hb5WzYzq1yZhEVEvAH8Y4H6NmBYgXoAE8vQmpmZFdDRls6amVkH5LAwM7NUDgszM0vlsDAzs1QOCzMzS+WwMDOzVA4LMzNL5bAwM7NUDgszM0vlsDAzs1QOCzMzS+WwMDOzVA4LMzNL5bAwM7NUDgszM0vlsDAzs1QOCzMzS1X2sJDUS9JCSWslrZZ0dVKfImmDpBXJY0TeNt+X1CDpFUnnlLtnM7NKl8VtVXcB10bEC5IOB5ZLmp+8d3tE3JY/WFJ/YBRwInAc8DtJJ0REU1m7NjOrYGU/soiITRHxQvL8PWAt0LOVTUYCsyPio4hYBzQAg0vfqZmZNct0zkJSLXAS8FxSulLSSknTJR2V1HoCb+dt1kgL4SJpgqRlkpZt3bq1RF2bmVWezMJC0mHAHOCaiHgXuAs4HqgDNgE/ax5aYPMotM+ImBYR9RFRX11dXYKuzcwqUyZhIakruaCYGREPA0TE5ohoiohPgF+x51RTI9Arb/MaYGM5+zUzq3RZrIYScA+wNiJ+nlfvkTfs68Cq5Pk8YJSkgyX1AfoBS8vVr5mZZbMa6ivAxcBLklYkteuB0ZLqyJ1iWg9cDhARqyU9CKwht5JqoldCmZmVV9nDIiIWU3ge4vFWtrkFuKVkTZmZFenV2y7NuoX9csJ197XLfvwNbjMzS5XFaSizitbZ/jKF9vvr1DovH1mYmVkqh4WZmaVyWJiZWSqHhZmZpXJYmJlZKoeFmZmlcliYmVkqh4WZmaXyl/I6IX+py8zKzUcWZmaWymFhZmapHBZmZpbKYWFmZqkcFmZmlsphYWZmqTpNWEgaLukVSQ2SJmfdj5lZJekUYSGpC3AncC7Qn9z9uvtn25WZWeXoFGEBDAYaIuKNiPgrMBsYmXFPZmYVQxGRdQ+pJP0TMDwiLkteXwycGhFX7jVuAjAhefkF4JWyNlo+3YB3sm7C2sy/v87ts/z7+1xEVBd6o7Nc7kMFavukXERMA6aVvp1sSVoWEfVZ92Ft499f51apv7/OchqqEeiV97oG2JhRL2ZmFaezhMXzQD9JfSQdBIwC5mXck5lZxegUp6EiYpekK4GngC7A9IhYnXFbWfrMn2r7jPPvr3OryN9fp5jgNjOzbHWW01BmZpYhh4WZmaVyWHQikqZL2iJpVda92P6T1EvSQklrJa2WdHXWPVlxJFVJWirpT8nv7qaseyo3z1l0IpLOBN4HZkTEgKz7sf0jqQfQIyJekHQ4sBy4ICLWZNyapZAk4O8i4n1JXYHFwNURsSTj1srGRxadSEQ8A2zPug9rm4jYFBEvJM/fA9YCPbPtyooROe8nL7smj4r6S9thYZYBSbXAScBz2XZixZLURdIKYAswPyIq6nfnsDArM0mHAXOAayLi3az7seJERFNE1JG7gsRgSRV1KthhYVZGyfnuOcDMiHg4635s/0XE/wMWAcMzbqWsHBZmZZJMkt4DrI2In2fdjxVPUrWkI5PnhwBnAS9n21V5OSw6EUmzgGeBL0hqlDQ+655sv3wFuBj4qqQVyWNE1k1ZUXoACyWtJHetuvkR8VjGPZWVl86amVkqH1mYmVkqh4WZmaVyWJiZWSqHhZmZpXJYmJlZKoeF2V4kNeUtbV0haXKBMUMltevSyWSfp+W9vkLSJe35GWZt1Sluq2pWZh8kl3Uot6Hkrir8R4CIuDuDHswK8pGFWZEkDZf0sqTFwDfy6lMkXZf3elVyoUAkXSJpZXIfhH9LaudJek7Si5J+J+nYZPwVwP9IjmbOyN+vpDpJS5J9zZV0VFJfJOl/JfdaeFXSGWX657AK47Aw29che52G+mdJVcCvgPOAM4B/SNuJpBOBfwG+GhH/CDTf7GgxMCQiTgJmA/8zItYDdwO3R0RdRPznXrubAXwvIgYBLwE35r13YEQMBq7Zq27Wbnwaymxf+5yGklQHrIuI15LXvwYmpOznq8BDEfEOQEQ034ukBngguRnSQcC61nYi6e+BIyPi6aR0P/DbvCHNFyRcDtSm9GTWJj6yMCteS9fG2cWn/79UlfxUC9v8ErgjIgYCl+eNb6uPkp9N+A9AKxGHhVlxXgb6SDo+eT067731wMkAkk4G+iT1BcC3JB2TvHd0Uv97YEPyfGzeft4DDt/7gyNiB/DnvPmIi4Gn9x5nVkoOC7N97T1n8ZOI+JDcaaf/m0xwv5k3fg5wdHIXte8ArwJExGrgFuBpSX8Cmi9LPgX4raT/BN7J28+jwNebJ7j36mkscGty1dM64Ob2/B9slsZXnTUzs1Q+sjAzs1QOCzMzS+WwMDOzVA4LMzNL5bAwM7NUDgszM0vlsDAzs1T/H1DoEigFcXICAAAAAElFTkSuQmCC\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "sns.countplot(x='Education', hue='Personal Loan',data=df_original)\n", "# From Graph it is evident 3 > 2 >1 where\n", "# 3: Working, 2: Graduates, 1: Under Graduates" ] }, { "cell_type": "code", "execution_count": 36, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 36, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAEGCAYAAABo25JHAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjMsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+AADFEAAAWVklEQVR4nO3dfZBV9Z3n8ffXpqWtUeOKzWhoIrA6Y/AJnRYdoylK3MSgYmbUDQ6jErTIpDSaRSvjOCkDVrYySaZiYrDiMqWJRkesoE7U8WFNhBgzCjaIRMBEdoyxldIWMyhRgrTf/aMvpGlu0xfs07fb835V3erz8DvnfLm39HN/5+F3IzORJJXXHvUuQJJUXwaBJJWcQSBJJWcQSFLJGQSSVHLD6l3ArjrggANyzJgx9S5DkoaUZcuWvZ6ZzdXWDbkgGDNmDG1tbfUuQ5KGlIh4sbd1nhqSpJIzCCSp5AwCSSq5IXeNQFJ5vPvuu7S3t7Np06Z6lzJkNDU10dLSQmNjY83bGASSBq329nb22WcfxowZQ0TUu5xBLzNZv3497e3tjB07tubtPDUkadDatGkTI0aMMARqFBGMGDFil3tQBoGkQc0Q2DW7834ZBJJUcgaBpCGloaGBCRMmcMQRR3Duuefy9ttv17uk7ey99967tHww8GLxIPPrf55R7xJ22Z9d+YN6l6AS2WuvvVixYgUA06dP58Ybb2T27Nk1bdvZ2UlDQ0OR5Q1J9ggkDVknn3wya9euBeC2225j4sSJTJgwgc997nN0dnYCXd/Er7nmGo4//nieeOIJrrrqKsaPH89RRx3FlVdeCcCLL77I5MmTOeqoo5g8eTK//e1vAZgxYwaXXXYZJ554IuPGjWPhwoUAbNy4kcmTJ3Psscdy5JFH8uMf/3i36u/tuPfddx/HH388xxxzDKeeeiqvvvoqAHPmzGHmzJlMmjSJcePGcf311+/+m9eNQSBpSNqyZQsPPvggRx55JGvWrOHOO+/kF7/4BStWrKChoYHbb78dgN///vccccQRLFmyhPHjx3PPPfewatUqVq5cyZe//GUALr30Ui644AJWrlzJ9OnTueyyy7YdZ926dTz++OPcf//9XHXVVUDXvfr33HMPy5cvZ9GiRVxxxRXszs/+9nbck046iSeffJKnn36aadOm8Y1vfGPbNs899xwPP/wwS5cuZe7cubz77ru7/R5u5akhSUPKO++8w4QJE4CuHsFFF13E/PnzWbZsGccdd9y2NiNHjgS6rimcffbZAOy77740NTVx8cUXc/rpp3PGGWcA8MQTT3D33XcDcP755/OlL31p2/E+/elPs8ceezB+/Pht38wzk6uvvprHHnuMPfbYg5dffplXX32VAw88cJf+Lb0dt729nc985jOsW7eOzZs3b/dMwOmnn87w4cMZPnw4I0eO5NVXX6WlpWXX3sQeDAJJQ0r3awRbZSYXXnghX/va13Zo39TUtO26wLBhw1i6dCk//elPWbBgAfPmzePRRx/dYZvut2AOHz58u+MA3H777XR0dLBs2TIaGxsZM2ZMvzz9vPW4X/jCF5g9ezZTp05l8eLFzJkzp2o9DQ0NbNmy5X0f11NDkoa8yZMns3DhQl577TUA3njjDV58ccdRlzdu3MiGDRuYMmUK3/72t7cFyoknnsiCBQuArv/Jn3TSSTs93oYNGxg5ciSNjY0sWrSo6rFq0dtxN2zYwKhRowC45ZZbdmvfu8IegaQhb/z48Xz1q1/lE5/4BO+99x6NjY3ccMMNHHzwwdu1e+uttzjrrLPYtGkTmcl1110HwPXXX8/MmTP55je/SXNzM9///vd3erzp06dz5pln0trayoQJEzjssMP6rPHtt9/e7hTO7Nmzez3unDlzOPfccxk1ahQnnHACL7zwwq6+JbskducCRz21trbmB/mHabx9VPqjNWvW8NGPfrTeZQw51d63iFiWma3V2ntqSJJKrrAgiIimiFgaEc9ExKqImFulzfCIuDMi1kbEkogYU1Q9kqTqiuwR/AE4JTOPBiYAp0XECT3aXAT8LjMPAa4Dvl5gPZKkKgoLguyysTLbWHn1vCBxFrD1kvhCYHI41KAkDahCrxFERENErABeAx7JzCU9mowCXgLIzC3ABmBElf3Mioi2iGjr6OgosmRJKp1CgyAzOzNzAtACTIyII3o0qfbtf4fbmDJzfma2ZmZrc3NzEaVKUmkNyHMEmflfEbEYOA14ttuqdmA00B4Rw4APAW8MRE2Syutvrlncr/v712sn9dnmoYce4vLLL6ezs5OLL75427hFg0GRdw01R8R+lem9gFOB53o0uxe4sDJ9DvBoDrUHGySpD52dnVxyySU8+OCDrF69mjvuuIPVq1fXu6xtijw1dBCwKCJWAk/RdY3g/oi4NiKmVtrcBIyIiLXAbGDwRKQk9ZOlS5dyyCGHMG7cOPbcc0+mTZu220NXF6GwU0OZuRI4psrya7pNbwLOLaoGSRoMXn75ZUaPHr1tvqWlhSVLet47Uz8+WSxJBat2xnsw3SlvEEhSwVpaWnjppZe2zbe3t/PhD3+4jhVtzyCQpIIdd9xxPP/887zwwgts3ryZBQsWMHXq1L43HCAOQy2pdGq53bM/DRs2jHnz5vHJT36Szs5OZs6cyeGHHz6gNeyMQSBJA2DKlClMmTKl3mVU5akhSSo5g0CSSs4gkKSSMwgkqeQMAkkqOYNAkkrO20cllc6v/3lGv+7vz678QZ9tZs6cyf3338/IkSN59tln+2w/kOwRSNIAmDFjBg899FC9y6jKIJCkAfDxj3+c/fffv95lVGUQSFLJGQSSVHJeLNag1d+/KzsQBnowM6k/2COQpJKzRyCpdGq53bO/nXfeeSxevJjXX3+dlpYW5s6dy0UXXTTgdVRjEEjSALjjjjvqXUKvPDUkSSVnEEhSyRkEkga1zKx3CUPK7rxfXiOQ+lF/j2FTtHpcNN0VTU1NrF+/nhEjRhAR9S5n0MtM1q9fT1NT0y5tV1gQRMRo4FbgQOA9YH5mfqdHm0nAj4EXKovuzsxri6pJ0tDS0tJCe3s7HR0d9S5lyGhqaqKlpWWXtimyR7AFuCIzl0fEPsCyiHgkM1f3aPfzzDyjwDokDVGNjY2MHTu23mV84BV2jSAz12Xm8sr0W8AaYFRRx5Mk7Z4BuVgcEWOAY4AlVVb/ZUQ8ExEPRsThvWw/KyLaIqLNLqIk9a/CgyAi9gbuAr6YmW/2WL0cODgzjwa+C/xbtX1k5vzMbM3M1ubm5mILlqSSKTQIIqKRrhC4PTPv7rk+M9/MzI2V6QeAxog4oMiaJEnbKywIouter5uANZn5rV7aHFhpR0RMrNSzvqiaJEk7KvKuoY8B5wO/jIgVlWVXAx8ByMwbgXOAz0fEFuAdYFr69IgkDajCgiAzHwd2+gRIZs4D5hVVgySpbz5ZLEkMvafCof+eDHesIUkqOXsEkgox1H5qdM6+9a6gfuwRSFLJGQSSVHIGgSSVnEEgSSVnEEhSyRkEklRyBoEklZxBIEklZxBIUskZBJJUcgaBJJXcB3qsoaE21gmUe7wTSfVhj0CSSs4gkKSSMwgkqeQMAkkqOYNAkkrOIJCkkjMIJKnkDAJJKrnCgiAiRkfEoohYExGrIuLyKm0iIq6PiLURsTIiji2qHklSdUU+WbwFuCIzl0fEPsCyiHgkM1d3a/Mp4NDK63jge5W/kqQBUliPIDPXZebyyvRbwBpgVI9mZwG3Zpcngf0i4qCiapIk7WhArhFExBjgGGBJj1WjgJe6zbezY1gQEbMioi0i2jo6OooqU5JKqfAgiIi9gbuAL2bmmz1XV9kkd1iQOT8zWzOztbm5uYgyJam0Cg2CiGikKwRuz8y7qzRpB0Z3m28BXimyJknS9oq8ayiAm4A1mfmtXprdC1xQuXvoBGBDZq4rqiZJ0o6KvGvoY8D5wC8jYkVl2dXARwAy80bgAWAKsBZ4G/hsgfVIkqooLAgy83GqXwPo3iaBS4qqQZLUN58slqSSqykIIuKuiDg9IgwOSfqAqfV/7N8D/gZ4PiL+KSIOK7AmSdIAqikIMvMnmTkdOBb4DfBIRPxHRHy2couoJGmIqvlUT0SMAGYAFwNPA9+hKxgeKaQySdKAqOmuoYi4GzgM+CFwZrd7/e+MiLaiipMkFa/W20fnZeaj1VZkZms/1iNJGmA7DYKI+Otq01v1MmyEJGkI6atHcOZO1iVgEEjSELfTIMhMh3yQpA+4vk4N/W1m3hYRs6ut38lgcpKkIaKvU0N/Uvm7T9GFSJLqo69TQ/+n8nfuwJQjSRpotT5HMBb4AjCm+zaZObWYsiRJA6XW5wj+ja4fmbkPeK+4ciRJA63WINiUmdcXWokkqS5qDYLvRMRXgP8L/GHrwsxcXkhVkqQBU2sQHEnXz06ewh9PDWVlXpI0hNUaBH8FjMvMzUUWI0kaeLUOQ/0MsF+RhUiS6qPWHsGfAs9FxFNsf43A20claYirNQi+UmgVkqS6qSkIMvNnRRciSaqPmq4RRMQJEfFURGyMiM0R0RkRb/axzc0R8VpEPNvL+kkRsSEiVlRe1+zOP0CS9P7U/AtlwDTgR0ArcAFwaB/b/KCy3a07afPzzDyjxhokSQWo+cfrM3Mt0JCZnZn5fWBSH+0fA954f+VJkopWa4/g7YjYE1gREd8A1vHHIarfj7+MiGeAV4ArM3NVP+xTkrQLau0RnF9peynwe2A0cPb7PPZy4ODMPBr4Ll0D21UVEbMioi0i2jo6Ot7nYSVJ3e00CCLiIwCZ+WJmbsrMNzNzbmbOrpwq2m2VfW2sTD8ANEbEAb20nZ+ZrZnZ2tzc/H4OK0nqoa8ewbZv6RFxV38eOCIOjIioTE+s1LK+P48hSepbX9cIotv0uF3ZcUTcQdcF5QMiop2uh9IaATLzRuAc4PMRsQV4B5iWmbkrx5AkvX99BUH2Mt2nzDyvj/Xz6Lq9VJJUR30FwdGVB8cC2KvbQ2QBZGbuW2h1kqTC9fXj9Q0DVYgkqT5qfqBMkvTBZBBIUskZBJJUcgaBJJWcQSBJJWcQSFLJGQSSVHIGgSSVnEEgSSVnEEhSyRkEklRyBoEklZxBIEklZxBIUskZBJJUcgaBJJWcQSBJJWcQSFLJGQSSVHIGgSSVnEEgSSVnEEhSyRUWBBFxc0S8FhHP9rI+IuL6iFgbESsj4tiiapEk9a7IHsEPgNN2sv5TwKGV1yzgewXWIknqRWFBkJmPAW/spMlZwK3Z5Ulgv4g4qKh6JEnV1fMawSjgpW7z7ZVlO4iIWRHRFhFtHR0dA1KcJJVFPYMgqizLag0zc35mtmZma3Nzc8FlSVK51DMI2oHR3eZbgFfqVIsklVY9g+Be4ILK3UMnABsyc10d65GkUhpW1I4j4g5gEnBARLQDXwEaATLzRuABYAqwFngb+GxRtUiSeldYEGTmeX2sT+CSoo4vSaqNTxZLUskZBJJUcgaBJJWcQSBJJWcQSFLJGQSSVHIGgSSVnEEgSSVnEEhSyRkEklRyBoEklZxBIEklZxBIUskZBJJUcgaBJJWcQSBJJWcQSFLJGQSSVHIGgSSVnEEgSSVnEEhSyRkEklRyBoEklVyhQRARp0XEryJibURcVWX9jIjoiIgVldfFRdYjSdrRsKJ2HBENwA3A/wDagaci4t7MXN2j6Z2ZeWlRdUiSdq7IHsFEYG1m/mdmbgYWAGcVeDxJ0m4oMghGAS91m2+vLOvp7IhYGRELI2J0tR1FxKyIaIuIto6OjiJqlaTSKjIIosqy7DF/HzAmM48CfgLcUm1HmTk/M1szs7W5ubmfy5SkcisyCNqB7t/wW4BXujfIzPWZ+YfK7L8Af1FgPZKkKooMgqeAQyNibETsCUwD7u3eICIO6jY7FVhTYD2SpCoKu2soM7dExKXAw0ADcHNmroqIa4G2zLwXuCwipgJbgDeAGUXVI0mqrrAgAMjMB4AHeiy7ptv0PwD/UGQNkqSd88liSSo5g0CSSs4gkKSSMwgkqeQMAkkqOYNAkkrOIJCkkjMIJKnkDAJJKjmDQJJKziCQpJIzCCSp5AwCSSo5g0CSSs4gkKSSMwgkqeQMAkkqOYNAkkrOIJCkkjMIJKnkDAJJKjmDQJJKziCQpJIzCCSp5AoNgog4LSJ+FRFrI+KqKuuHR8SdlfVLImJMkfVIknZUWBBERANwA/ApYDxwXkSM79HsIuB3mXkIcB3w9aLqkSRVV2SPYCKwNjP/MzM3AwuAs3q0OQu4pTK9EJgcEVFgTZKkHiIzi9lxxDnAaZl5cWX+fOD4zLy0W5tnK23aK/P/r9Lm9R77mgXMqsz+OfCrQooeHA4AXu+zlQYrP7+h64P+2R2cmc3VVgwr8KDVvtn3TJ1a2pCZ84H5/VHUYBcRbZnZWu86tHv8/IauMn92RZ4aagdGd5tvAV7prU1EDAM+BLxRYE2SpB6KDIKngEMjYmxE7AlMA+7t0eZe4MLK9DnAo1nUuSpJUlWFnRrKzC0RcSnwMNAA3JyZqyLiWqAtM+8FbgJ+GBFr6eoJTCuqniGkFKfAPsD8/Iau0n52hV0sliQNDT5ZLEklZxBIUskZBINERNwcEa9Vnq3QEBIRoyNiUUSsiYhVEXF5vWtS7SKiKSKWRsQzlc9vbr1rGmheIxgkIuLjwEbg1sw8ot71qHYRcRBwUGYuj4h9gGXApzNzdZ1LUw0qoxn8SWZujIhG4HHg8sx8ss6lDRh7BINEZj6Gz1AMSZm5LjOXV6bfAtYAo+pblWqVXTZWZhsrr1J9QzYIpH5UGUH3GGBJfSvRroiIhohYAbwGPJKZpfr8DAKpn0TE3sBdwBcz881616PaZWZnZk6gawSEiRFRqtOzBoHUDyrnlu8Cbs/Mu+tdj3ZPZv4XsBg4rc6lDCiDQHqfKhcbbwLWZOa36l2Pdk1ENEfEfpXpvYBTgefqW9XAMggGiYi4A3gC+POIaI+Ii+pdk2r2MeB84JSIWFF5Tal3UarZQcCiiFhJ1xhpj2Tm/XWuaUB5+6gklZw9AkkqOYNAkkrOIJCkkjMIJKnkDAJJKjmDQKUSEZ3dbvFcERFXVWkzKSL69fbByj5P7Db/dxFxQX8eQ9pdhf1UpTRIvVMZSmCgTaJrdNn/AMjMG+tQg1SVPQIJiIjTIuK5iHgc+Otuy+dExJXd5p+tDCxHRFwQESsr49j/sLLszIhYEhFPR8RPIuJPK+3/DvhflV7Iyd33GxETIuLJyr7uiYj/Vlm+OCK+Xhkr/9cRcfIAvR0qGYNAZbNXj1NDn4mIJuBfgDOBk4ED+9pJRBwO/CNwSmYeDWz9MZrHgRMy8xhgAfClzPwNcCNwXWZOyMyf99jdrcDfZ+ZRwC+Br3RbNywzJwJf7LFc6jeeGlLZ7HBqKCImAC9k5vOV+duAWX3s5xRgYWa+DpCZW39LogW4s/JjNXsCL+xsJxHxIWC/zPxZZdEtwI+6Ndk6gN0yYEwfNUm7xR6B1KW3sVa2sP1/J02Vv9HLNt8F5mXmkcDnurXfXX+o/O3EL24qiEEgdY00OTYi/ntl/rxu634DHAsQEccCYyvLfwr8z4gYUVm3f2X5h4CXK9MXdtvPW8A+PQ+cmRuA33U7/38+8LOe7aQiGQQqm57XCP4pMzfRdSro3ysXi1/s1v4uYP/Kr1d9Hvg1QGauAv438LOIeAbYOvz0HOBHEfFz4PVu+7kP+KutF4t71HQh8M3K6JcTgGv78x8s9cXRRyWp5OwRSFLJGQSSVHIGgSSVnEEgSSVnEEhSyRkEklRyBoEkldz/B62DVViZ8BqtAAAAAElFTkSuQmCC\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "# Relation between Family& Education to personal load\n", "sns.barplot('Education','Family',hue='Personal Loan',data=df_original,ci=None)\n" ] }, { "cell_type": "code", "execution_count": 37, "metadata": {}, "outputs": [], "source": [ "# Classes for all model goes here\n", "# 1. Class Logistic\n", "# 2. Class Knn\n", "# 3. Class NaiveBayes\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "code", "execution_count": 38, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Analysing Experience column for unique value [1, 19, 15, 9, 8, 13, 27, 24, 10, 39, 5, 23, 32, 41, 30, 14, 18, 21, 28, 31, 11, 16, 20, 35, 6, 25, 7, 12, 26, 37, 17, 2, 36, 29, 3, 22, 0, 34, 38, 40, 33, 4, 42, 43]\n", "Experience values unique True\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/home/ashish/installed_apps/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:966: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", " self.obj[item] = s\n" ] }, { "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", "
countmeanstdmin25%50%75%max
Age5000.045.33840011.46316623.035.045.055.067.0
Experience5000.020.11960011.4404840.010.020.030.043.0
Income5000.073.77420046.0337298.039.064.098.0224.0
ZIP Code5000.093152.5030002121.8521979307.091911.093437.094608.096651.0
Family5000.02.3964001.1476631.01.02.03.04.0
CCAvg5000.01.9379381.7476590.00.71.52.510.0
Education5000.01.8810000.8398691.01.02.03.03.0
Mortgage5000.056.498800101.7138020.00.00.0101.0635.0
Securities Account5000.00.1044000.3058090.00.00.00.01.0
CD Account5000.00.0604000.2382500.00.00.00.01.0
Online5000.00.5968000.4905890.00.01.01.01.0
CreditCard5000.00.2940000.4556370.00.00.01.01.0
\n", "
" ], "text/plain": [ " count mean std min 25% \\\n", "Age 5000.0 45.338400 11.463166 23.0 35.0 \n", "Experience 5000.0 20.119600 11.440484 0.0 10.0 \n", "Income 5000.0 73.774200 46.033729 8.0 39.0 \n", "ZIP Code 5000.0 93152.503000 2121.852197 9307.0 91911.0 \n", "Family 5000.0 2.396400 1.147663 1.0 1.0 \n", "CCAvg 5000.0 1.937938 1.747659 0.0 0.7 \n", "Education 5000.0 1.881000 0.839869 1.0 1.0 \n", "Mortgage 5000.0 56.498800 101.713802 0.0 0.0 \n", "Securities Account 5000.0 0.104400 0.305809 0.0 0.0 \n", "CD Account 5000.0 0.060400 0.238250 0.0 0.0 \n", "Online 5000.0 0.596800 0.490589 0.0 0.0 \n", "CreditCard 5000.0 0.294000 0.455637 0.0 0.0 \n", "\n", " 50% 75% max \n", "Age 45.0 55.0 67.0 \n", "Experience 20.0 30.0 43.0 \n", "Income 64.0 98.0 224.0 \n", "ZIP Code 93437.0 94608.0 96651.0 \n", "Family 2.0 3.0 4.0 \n", "CCAvg 1.5 2.5 10.0 \n", "Education 2.0 3.0 3.0 \n", "Mortgage 0.0 101.0 635.0 \n", "Securities Account 0.0 0.0 1.0 \n", "CD Account 0.0 0.0 1.0 \n", "Online 1.0 1.0 1.0 \n", "CreditCard 0.0 1.0 1.0 " ] }, "execution_count": 38, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Remember df_main_x will be our main dataframe to be operted on df_original is the unmodified loaded data set which is pure :)\n", "# seperate data i.e input columns and to be predicted column\n", "# Drop 'Personal Loan' from dataframe as this is dependent variable and copy it alone in y dataframe\n", "\n", "df_main_x = df_original[['Age', 'Experience', 'Income', 'ZIP Code', 'Family', 'CCAvg', \n", " 'Education', 'Mortgage', 'Securities Account', 'CD Account', 'Online', \n", " 'CreditCard']]\n", "\n", "# Replace all -ve values in experience column to 0\n", "\n", "# df_main_x.Experience[df_main_x.Experience.lt(0)] = 0 \n", "\n", "# df_main_x['Experience'] = df_main_x['Experience'].map(lambda value: value if value >=0 else 0)\n", "\n", "df_main_x.loc[df_main_x['Experience']<0, 'Experience']=0 \n", "\n", "\n", "print(\"Experience values unique {}\".format(validate_column(df_main_x['Experience'].unique().tolist(), 'Experience')))\n", "\n", "df_main_y = df_original['Personal Loan']\n", "\n", "\n", "# Also remember how we removed ID column as it is just a row counter\n", "\n", "df_main_x.describe().T\n", "\n", "# Now e see that there is no -ve value in experience columns\n" ] }, { "cell_type": "code", "execution_count": 39, "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", "
AgeExperienceIncomeZIP CodeFamilyCCAvgEducationMortgageSecurities AccountCD AccountOnlineCreditCard
0251499110741.6101000
14519349008931.5101000
23915119472011.0100000
33591009411212.7200000
4358459133041.0200001
\n", "
" ], "text/plain": [ " Age Experience Income ZIP Code Family CCAvg Education Mortgage \\\n", "0 25 1 49 91107 4 1.6 1 0 \n", "1 45 19 34 90089 3 1.5 1 0 \n", "2 39 15 11 94720 1 1.0 1 0 \n", "3 35 9 100 94112 1 2.7 2 0 \n", "4 35 8 45 91330 4 1.0 2 0 \n", "\n", " Securities Account CD Account Online CreditCard \n", "0 1 0 0 0 \n", "1 1 0 0 0 \n", "2 0 0 0 0 \n", "3 0 0 0 0 \n", "4 0 0 0 1 " ] }, "execution_count": 39, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# X data frame\n", "df_main_x.head()" ] }, { "cell_type": "code", "execution_count": 40, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "0 0\n", "1 0\n", "2 0\n", "3 0\n", "4 0\n", "Name: Personal Loan, dtype: int64" ] }, "execution_count": 40, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Y Data Frame\n", "df_main_y.head()" ] }, { "cell_type": "code", "execution_count": 41, "metadata": {}, "outputs": [], "source": [ "# Training constants and general imports\n", "\n", "from math import sqrt\n", "\n", "from sklearn.linear_model import LogisticRegression\n", "from sklearn.naive_bayes import GaussianNB\n", "from sklearn.neighbors import KNeighborsClassifier\n", "\n", "from sklearn import metrics\n", "from sklearn.metrics import classification_report\n", "\n", "# taking 70:30 training and test set\n", "test_size = 0.30 \n", "\n", "# Random number seeding for reapeatability of the code\n", "seed = 29 # My BirthDate :)\n", "\n", "def isqrt(n):\n", " x = n\n", " y = (x + 1) // 2\n", " while y < x:\n", " x = y\n", " y = (x + n // x) // 2\n", " return x" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Logistic Regression" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Training General" ] }, { "cell_type": "code", "execution_count": 42, "metadata": {}, "outputs": [], "source": [ "# Why are we doing Logistic Regression, because in linear regression response of the system in continuous, where as in \n", "# logistic regression it is just limited number of possible outcomes i.e in our case [0] or [1] which is whethere a person \n", "# is likely to take loan or not [yes] or [no]\n", "\n", "# Class LogisticRegressionProcess\n", "from sklearn.model_selection import train_test_split\n", "\n", "X_train, X_test, y_train, y_test = train_test_split(df_main_x, df_main_y, test_size=test_size, random_state=seed) \n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Predicting Logistic Regression" ] }, { "cell_type": "code", "execution_count": 43, "metadata": {}, "outputs": [], "source": [ "\n", "lr_model = LogisticRegression()\n", "\n", "lr_model.fit(X_train, y_train)\n", "\n", "lr_predict = lr_model.predict(X_test)\n", "\n", "lr_score = lr_model.score(X_test, y_test)\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Evaluating Logistic Regression" ] }, { "cell_type": "code", "execution_count": 44, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Model Score\n", "0.9053333333333333\n", "Model confusion matrix\n", "[[1314 49]\n", " [ 93 44]]\n", " precision recall f1-score support\n", "\n", " 0 0.93 0.96 0.95 1363\n", " 1 0.47 0.32 0.38 137\n", "\n", " accuracy 0.91 1500\n", " macro avg 0.70 0.64 0.67 1500\n", "weighted avg 0.89 0.91 0.90 1500\n", "\n" ] } ], "source": [ "print(\"Model Score\")\n", "print(lr_score)\n", "print(\"Model confusion matrix\")\n", "print(metrics.confusion_matrix(y_test, lr_predict))\n", "\n", "\n", "print(classification_report(y_test,lr_predict))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# Naive Bayes" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Predicting Naive Bayes" ] }, { "cell_type": "code", "execution_count": 45, "metadata": {}, "outputs": [], "source": [ "nb_model = GaussianNB()\n", "\n", "nb_model.fit(X_train, y_train)\n", "\n", "y_nb_predict = nb_model.predict(X_test)\n", "\n", "nb_score = nb_model.score(X_test, y_test)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Evaluating Naive Bayes" ] }, { "cell_type": "code", "execution_count": 46, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Model Score\n", "0.876\n", "Model confusion matrix\n", "[[1240 123]\n", " [ 63 74]]\n", " precision recall f1-score support\n", "\n", " 0 0.95 0.91 0.93 1363\n", " 1 0.38 0.54 0.44 137\n", "\n", " accuracy 0.88 1500\n", " macro avg 0.66 0.72 0.69 1500\n", "weighted avg 0.90 0.88 0.89 1500\n", "\n" ] } ], "source": [ "print(\"Model Score\")\n", "print(nb_score)\n", "print(\"Model confusion matrix\")\n", "print(metrics.confusion_matrix(y_test, y_nb_predict))\n", "\n", "\n", "print(classification_report(y_test,y_nb_predict))\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "# K-NN" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Predicting K-NN" ] }, { "cell_type": "code", "execution_count": 47, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "70\n", "Knn evaluation completed, best value is 28\n" ] } ], "source": [ "knn_predict = 0\n", "knn_score = 0\n", "knn_value = 0\n", "# We have total 5000 taging \n", "print(isqrt(df_main_x.shape[0]))\n", "for i in range(isqrt(df_main_x.shape[0])):\n", " kvalue = i+1\n", " knn_model = KNeighborsClassifier(n_neighbors=kvalue)\n", " knn_model.fit(X_train, y_train)\n", " new_knn_predict = knn_model.predict(X_test)\n", " new_knn_score = knn_model.score(X_test, y_test)\n", " if new_knn_score >= knn_score:\n", " knn_score = new_knn_score\n", " knn_predict = new_knn_predict\n", " knn_value = kvalue\n", "\n", "print(\"Knn evaluation completed, best value is {}\".format(knn_value))" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Evaluating K-NN" ] }, { "cell_type": "code", "execution_count": 48, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Model Score\n", "0.9106666666666666\n", "Model confusion matrix\n", "[[1360 3]\n", " [ 131 6]]\n", " precision recall f1-score support\n", "\n", " 0 0.91 1.00 0.95 1363\n", " 1 0.67 0.04 0.08 137\n", "\n", " accuracy 0.91 1500\n", " macro avg 0.79 0.52 0.52 1500\n", "weighted avg 0.89 0.91 0.87 1500\n", "\n" ] } ], "source": [ "print(\"Model Score\")\n", "print(knn_score)\n", "print(\"Model confusion matrix\")\n", "print(metrics.confusion_matrix(y_test, knn_predict))\n", "\n", "\n", "print(classification_report(y_test,knn_predict))\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Analysis Result" ] }, { "cell_type": "code", "execution_count": 49, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Model score are \n", "{'Logistic Regression': 0.9053333333333333, 'Naive Bayes': 0.876, 'K-NN': 0.9106666666666666}\n", "Best score is for K-NN with accuracy 0.9106666666666666 \n", " with kvalue 70\n" ] } ], "source": [ "\n", "\n", "results = {'Logistic Regression': lr_score, 'Naive Bayes': nb_score, 'K-NN': knn_score}\n", "\n", "print(\"Model score are \")\n", "print(results)\n", "\n", "best_score = max(results, key=results.get);\n", "\n", "print(\"Best score is for {} with accuracy {} \".format(best_score, results[best_score]))\n", "\n", "if best_score == 'K-NN':\n", " print(' with kvalue {}'.format(kvalue))\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Analysis Report" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Our main aim was to find out people who would accept personal loan based on given data.\n", "\n", "From the output we see that K-NN turned out to be the best model with accuracy of 0.91. The other nearest accuracy is 0.90 which is of Logistic Regression. For our use case by identifying the problem state and given the option we had we can consider Logistic Regression to be the best approach, as output to be predicted was 0/1 and that is what logistic regression does, it transforms its output using sigma function. Also,, Logis Regression is parameteric dependent algorithm where as K-NN is not. Theoretically K-NN is a little slower, as we have also seen that to find the best possible k value we had to iterate, this can impact as in our case it is dependent on input data size(row count).\n", "\n", "So K-NN Would perform when there is no dependency on time constaints for finding out the best score, where as Logistic Regression would be the optimal choice for time constraints and when the target column is of binary predection asin this case." ] } ], "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": "3.7.7" } }, "nbformat": 4, "nbformat_minor": 2 }