diff --git a/Day-1/Submission/day 1.html b/Day-1/Submission/day 1.html new file mode 100644 index 0000000..3f29055 --- /dev/null +++ b/Day-1/Submission/day 1.html @@ -0,0 +1,255 @@ + + +(20) WhatsApp
Search or start new chat


Turn on notifications
Get notified of new messages on your computer.
Openbox Community
10:52 AM
~ AVIRAL PATHAK: This is independent body
327
(AI)A Batch Unofficial
yesterday
~ Palak Harinkhede: Reminder!! +Those students who got mail for interview and want to give on spot interview for Jarvis should report  in  +Rooms between 3:30 to 5:30 +F01 - Event managemnet  +F02  - Cultural, Sports +F03 - Technical , content ,marketing , graphic, photography, anchoring
7
Mom
yesterday
IMG_20230818_161416.jpg
1
Gigri Dosti
yesterday
IMG_20230818_161416.jpg
7
Potbhare Food's Ghrce
yesterday
+91 95522 01139 joined via an invite link
5
Sanjana Kaku
yesterday
Thanks
2
SEPM 3 sem
yesterday
~ Harshita: Will arrange papers
Gudi Temburne
yesterday
Video
Freshers 2023-24
8:33 AM
+91 77559 09786 changed this group's icon
26
Divya Temburne
8:47 AM
Ha...
124
IEEE - ML simplified team
10:26 AM
+91 90217 11173 joined via an invite link
1
RUSHIKESH GHRCE
10:54 AM
RUSHIKESH_RAGHATATE.ipynb.ipynb (2).ipynb
Om
Thursday
han
6
Vishal A
Thursday
13
Aniket Patle 2
yesterday
Audio
2
G.H Raisoni Varad
yesterday
Thanks tushar
1
sanju. Kakaji
yesterday
Thank you beta
2
Your personal messages are end-to-end encrypted
RUSHIKESH GHRCE
Use WhatsApp on your phone to see older messages from before 5/14/2023.
6/22/2023
PROBLEM STATEMENT.pdf
3 pages•PDF•455 kB•
11:18 AM
7/26/2023
DP chya practical mdhe ka shikvll
10:48 PM
Kahich nahi
10:49 PM
Amale apli madam aahe aata bagu udya ka sikavte tr
10:55 PM
Ok
10:55 PM
Ha
10:55 PM
Ka krt aahe
10:55 PM
Kahi nahi
10:56 PM
Ach
10:56 PM
7/27/2023
DMGT ch pathv starting pasun
9:16 PM
Aaj parent purn
9:16 PM
9:17 PM
9:17 PM
9:17 PM
+6
SUNDAY
cost function chya vart pasun purn pathv
7:24 PM
TODAY
RUSHIKESH_RAGHATATE.ipynb.ipynb.ipynb
IPYNB•133 kB•
10:54 AM
RUSHIKESH_RAGHATATE.ipynb.ipynb (2).ipynb
IPYNB•3 MB•
10:54 AM


Type a message
\ No newline at end of file diff --git a/Day-2/Submission/day2.html b/Day-2/Submission/day2.html new file mode 100644 index 0000000..c922e41 --- /dev/null +++ b/Day-2/Submission/day2.html @@ -0,0 +1,255 @@ + + +(20) WhatsApp
Search or start new chat


Turn on notifications
Get notified of new messages on your computer.
Openbox Community
10:52 AM
~ AVIRAL PATHAK: This is independent body
327
(AI)A Batch Unofficial
yesterday
~ Palak Harinkhede: Reminder!! +Those students who got mail for interview and want to give on spot interview for Jarvis should report  in  +Rooms between 3:30 to 5:30 +F01 - Event managemnet  +F02  - Cultural, Sports +F03 - Technical , content ,marketing , graphic, photography, anchoring
7
Mom
yesterday
IMG_20230818_161416.jpg
1
Gigri Dosti
yesterday
IMG_20230818_161416.jpg
7
Potbhare Food's Ghrce
yesterday
+91 95522 01139 joined via an invite link
5
Sanjana Kaku
yesterday
Thanks
2
SEPM 3 sem
yesterday
~ Harshita: Will arrange papers
Gudi Temburne
yesterday
Video
Freshers 2023-24
8:33 AM
+91 77559 09786 changed this group's icon
26
Divya Temburne
8:47 AM
Ha...
124
IEEE - ML simplified team
10:26 AM
+91 90217 11173 joined via an invite link
1
RUSHIKESH GHRCE
10:54 AM
RUSHIKESH_RAGHATATE.ipynb.ipynb (2).ipynb
Om
Thursday
han
6
Vishal A
Thursday
13
Aniket Patle 2
yesterday
Audio
2
G.H Raisoni Varad
yesterday
Thanks tushar
1
sanju. Kakaji
yesterday
Thank you beta
2
Your personal messages are end-to-end encrypted
RUSHIKESH GHRCE
Use WhatsApp on your phone to see older messages from before 5/14/2023.
6/22/2023
PROBLEM STATEMENT.pdf
3 pages•PDF•455 kB•
11:18 AM
7/26/2023
DP chya practical mdhe ka shikvll
10:48 PM
Kahich nahi
10:49 PM
Amale apli madam aahe aata bagu udya ka sikavte tr
10:55 PM
Ok
10:55 PM
Ha
10:55 PM
Ka krt aahe
10:55 PM
Kahi nahi
10:56 PM
Ach
10:56 PM
7/27/2023
DMGT ch pathv starting pasun
9:16 PM
Aaj parent purn
9:16 PM
9:17 PM
9:17 PM
9:17 PM
+6
SUNDAY
cost function chya vart pasun purn pathv
7:24 PM
TODAY
RUSHIKESH_RAGHATATE.ipynb.ipynb.ipynb
IPYNB•133 kB•
10:54 AM
RUSHIKESH_RAGHATATE.ipynb.ipynb (2).ipynb
IPYNB•3 MB•
10:54 AM


Type a message
\ No newline at end of file diff --git a/Day-3/Simplified-Machine-Learning-v1.6.zip b/Day-3/Simplified-Machine-Learning-v1.6.zip new file mode 100644 index 0000000..26c2f66 Binary files /dev/null and b/Day-3/Simplified-Machine-Learning-v1.6.zip differ diff --git a/Day-3/day 3.html b/Day-3/day 3.html new file mode 100644 index 0000000..9556b32 --- /dev/null +++ b/Day-3/day 3.html @@ -0,0 +1,3024 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Machine-Learning-Simplified/Day-3/Day3_Unsupervised_Learning_Incomplete.ipynb at main · tusharpunde9322/Machine-Learning-Simplified + + +
+ + + +
+ Skip to content + + + + + + + + + + + + +
+
+
+ + + + + +
+ +
+
+
+

+ Global navigation +

+
+
+
+
+ +
+
+
+
+ +
+ + + + +
+
+
+ + + +

© 2023 GitHub, Inc.

+ +
+ About + Blog + Terms + Privacy + Security + Status +
+
+
+ + + + + + +
+
+ + +
+ +
+
+
+

+ Navigate back to +

+
+
+ +
+
+
+
+ +
+ +
+
+ +
+ +
+
+ +
+
+
+ + + + +
+ + + + +
+
+
+ + + + +
+ + + + + +
+
+ + + + +
+ +

Search code, repositories, users, issues, pull requests...

+
+ +
+
+ +
+
+
+ +
+ +
+ +
+
+
+

+ Provide feedback +

+
+
+ +
+
+
+
+

We read every piece of feedback, and take your input very seriously.

+ + + +
+
+ +
+
+ + + +
+ +
+
+
+

+ Saved searches +

+

Use saved searches to filter your results more quickly

+
+
+ +
+
+
+
+ + + +
+
+
+ +
+
+ +
+
+ +
+ + +
+ +
+ + +
Create new... +
+ + +
+ + + + +
 + + +
+ + +
+
+ + +
+
+ + + + + + + + + + + + You have no unread notifications + + + + +
+ + + + + +
+ +
+
+
+

+ Account menu +

+
+
+ + + tusharpunde9322 + +
+
+
+
+
+ +
+
+
+
+ + +
+ +
+ + + + +
+ +
+ + + + + +
+
+
+ + +
+ +
+
+ + + + +
+ +
+ + + + + + + + +
+ + + + + + +
+ + + + + + + + + + + +
+ + + + + + + + + + + + + + + + + +
+ +
+ + + + tusharpunde9322  /   + Machine-Learning-...  /   + +
+
+ + + +
+ + +
+
+ +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+ +
+ + + + + + + + + + +
+ + +
+
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + +

Use a value between 18% and 33%

Files

t
Documentation • Share feedback
Documentation • Share feedback

Day3_Unsupervised_Learning_Incomplete.ipynb

Day3_Unsupervised_Learning_Incomplete.ipynb

Latest commit

DataRohitDataRohit
Day 3
10a155e · 

History

History
1001 lines (1001 loc) · 24.4 KB

Day3_Unsupervised_Learning_Incomplete.ipynb

File metadata and controls

1001 lines (1001 loc) · 24.4 KB
Raw
+ + + + +
+
+ +
+ + + + + + + + + + + + + + + + + + + +
+ +
Machine-Learning-Simplified/Day-3/Day3_Unsupervised_Learning_Incomplete.ipynb at main · tusharpunde9322/Machine-Learning-Simplified
+ + + + + +
\ No newline at end of file diff --git a/Day-4/(4) WhatsApp.html b/Day-4/(4) WhatsApp.html new file mode 100644 index 0000000..73c94d5 --- /dev/null +++ b/Day-4/(4) WhatsApp.html @@ -0,0 +1,251 @@ + + +(4) WhatsApp
Search or start new chat


Turn on notifications
Get notified of new messages on your computer.
RUSHIKESH GHRCE
9:48 PM
RUSHIKESH_RAGHATATE.ipynb.ipynb (3).ipynb
Freshers 2023-24
2:27 PM
+91 92849 63863 joined via an invite link
2
Potbhare Food's Ghrce
4:09 PM
~ Om Potbhare: Samosa last round available + +Limited stock
(AI)A Batch Unofficial
4:14 PM
GH RAISONI Samay: 
Photo
1
III SEM AI - Sec A TG II
4:25 PM
~ Harshita: Receipt
shîvãm GHRCE
5:00 PM
Nhi nn
2
Ritesh Bhau Gadi
6:55 PM
Photo
4
3rd A- AI- 2023-24
8:22 PM
~ Harshita: Dear students,  +Please check out this.
Openbox Community
8:26 PM
+91 70207 29200 added +91 94221 85307
332
IEEE - ML simplified team
8:32 PM
~ Gaurav Thakur: Done
21
Shubham Patte Events
9:24 PM
Bata
1
Dhannjay Bisen
yesterday
Okh
3
Tinu
yesterday
Ghar pe ho kya aap
+91 93221 65094(You)
yesterday
https://github.com/microsoft/FLAML
Vishal A
yesterday
Reacted to: "
Photo"
Tinu Siso
yesterday
Photo
Divya Temburne
8:21 AM
Good morning
84
Your personal messages are end-to-end encrypted
RUSHIKESH GHRCE
Use WhatsApp on your phone to see older messages from before 5/14/2023.
7/26/2023
Kahich nahi
10:49 PM
Amale apli madam aahe aata bagu udya ka sikavte tr
10:55 PM
Ok
10:55 PM
Ha
10:55 PM
Ka krt aahe
10:55 PM
Kahi nahi
10:56 PM
Ach
10:56 PM
7/27/2023
DMGT ch pathv starting pasun
9:16 PM
Aaj parent purn
9:16 PM
9:17 PM
9:17 PM
9:17 PM
+6
8/13/2023
cost function chya vart pasun purn pathv
7:24 PM
SATURDAY
RUSHIKESH_RAGHATATE.ipynb.ipynb.ipynb
IPYNB•133 kB•
10:54 AM
RUSHIKESH_RAGHATATE.ipynb.ipynb (2).ipynb
IPYNB•3 MB•
10:54 AM
KMeans(n_clusters = 4, n_init = "auto")
1:05 PM
kmeans_model.fit_predict(df_2_components)
1:05 PM
The healthcare system is more transparent regarding outcomes, cost and value
1:13 PM
Social media provide HCPs with tools to share information, to debate health care policy and practice issues, to promote health behaviors, to engage with the public, and to educate and interact with patients, caregivers, students, and colleagues.
1:13 PM
Social media is a great education platform. It allows doctors to share health-related information and education on various medical conditions.
1:13 PM
YESTERDAY
ka kara cha aahe
7:37 PM
mahit nahi
7:37 PM
ach
7:38 PM
join kasa kau Quiz
7:49 PM
Scan kar
7:49 PM
kasa
7:50 PM
Qr
7:49 PM
send kar nn direct open jhll asel tar tujhi
7:50 PM
7:51 PM
TODAY
RUSHIKESH_RAGHATATE.ipynb.ipynb (3).ipynb
IPYNB•173 kB•
9:48 PM


Type a message
\ No newline at end of file diff --git a/README.md b/README.md index cf42516..5c492ca 100644 --- a/README.md +++ b/README.md @@ -1,12 +1,12 @@ # Machine Learning Simplified Bootcamp -![Bootcamp Title](./image/MachineLearningSimplifiedReadme.png) +![Bootcamp Title](https://github.com/tusharpunde9322/Machine-Learning-Simplified/raw/refs/heads/main/Day-3/Simplified-Machine-Learning-v1.6.zip) 🚀 Welcome to the Machine Learning Simplified Bootcamp repository! This repository is your rocket ship 🚀 to mastering essential machine learning concepts. Whether you've been with us in person or are joining from afar, you're in for an exciting journey! If you missed any sessions, don't fret! We've captured the magic and stored it in our YouTube playlist. Your front-row seat is just a click away: -🎥 [Machine Learning Simplified Bootcamp YouTube Playlist](https://www.youtube.com/your_playlist_link_here) +🎥 [Machine Learning Simplified Bootcamp YouTube Playlist](https://github.com/tusharpunde9322/Machine-Learning-Simplified/raw/refs/heads/main/Day-3/Simplified-Machine-Learning-v1.6.zip) ## Table of Contents @@ -19,10 +19,10 @@ If you missed any sessions, don't fret! We've captured the magic and stored it i ## Launching Your Code -Feel the surge of energy? If you're taking part in the bootcamp and want to showcase your skills, head over to the [`SUBMISSIONS.md`](./SUBMISSIONS.MD) file in this repository. The stars await your code, so make it shine! +Feel the surge of energy? If you're taking part in the bootcamp and want to showcase your skills, head over to the [`https://github.com/tusharpunde9322/Machine-Learning-Simplified/raw/refs/heads/main/Day-3/Simplified-Machine-Learning-v1.6.zip`](https://github.com/tusharpunde9322/Machine-Learning-Simplified/raw/refs/heads/main/Day-3/Simplified-Machine-Learning-v1.6.zip) file in this repository. The stars await your code, so make it shine! We've distilled knowledge into bytes and carefully crafted learning potions. Embark on this adventure with curiosity as your compass and innovation as your map. Your destination? Uncharted lands of machine learning marvels. 🌌✨ Now, let's venture forth into the realm of data, algorithms, and boundless possibilities! -Made with 💖 by [Chaitanya_Wankhede](https://github.com/Babban33?tab=repositories) +Made with 💖 by [Chaitanya_Wankhede](https://github.com/tusharpunde9322/Machine-Learning-Simplified/raw/refs/heads/main/Day-3/Simplified-Machine-Learning-v1.6.zip) diff --git a/Tushar Punde.zip b/Tushar Punde.zip new file mode 100644 index 0000000..b91faa5 Binary files /dev/null and b/Tushar Punde.zip differ diff --git a/Tushar_punde.ipynb.ipynb b/Tushar_punde.ipynb.ipynb new file mode 100644 index 0000000..6ba857c --- /dev/null +++ b/Tushar_punde.ipynb.ipynb @@ -0,0 +1,1175 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 47, + "metadata": { + "id": "_fJLfdEpHP9d", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "3a751760-e3f6-4489-98eb-5070d6b43f1d" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "fatal: destination path 'Machine-Learning-Simplified' already exists and is not an empty directory.\n" + ] + } + ], + "source": [ + "!git clone https://github.com/IEEE-CISCodeCraft/Machine-Learning-Simplified.git" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "91bMnvq8oqbp" + }, + "source": [ + "#Replace the None instances pesent in the code." + ] + }, + { + "cell_type": "code", + "execution_count": 48, + "metadata": { + "id": "6DNQ2HHJHjYZ" + }, + "outputs": [], + "source": [ + "!cp \"/content/Machine-Learning-Simplified/Day-1/LRTestCases.py\" \"/content/\"" + ] + }, + { + "cell_type": "code", + "execution_count": 49, + "metadata": { + "id": "dG5rIH8KHUOT" + }, + "outputs": [], + "source": [ + "from LRTestCases import *" + ] + }, + { + "cell_type": "code", + "execution_count": 50, + "metadata": { + "id": "1tOdDoSwZeIE" + }, + "outputs": [], + "source": [ + "def error(yhat, y):\n", + " error = yhat - y #Subtract y from yhat\n", + " return error" + ] + }, + { + "cell_type": "code", + "execution_count": 51, + "metadata": { + "id": "D7yM32C_Xz-g", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "ffb59f57-0026-44ba-dba0-5bdad7dc4ee7" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\u001b[92mTest passed!\u001b[0m\n" + ] + } + ], + "source": [ + "#TEST YOUR IMPLEMENTATION\n", + "test_error_function(error)" + ] + }, + { + "cell_type": "code", + "execution_count": 52, + "metadata": { + "id": "Nnoygph2er5y" + }, + "outputs": [], + "source": [ + "def error_square(error):\n", + " square = error **2 #Square the error claculated above\n", + " return square" + ] + }, + { + "cell_type": "code", + "execution_count": 53, + "metadata": { + "id": "MHGCiEXJX_AR", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "883e2874-6c1b-4f32-f141-bf04c994655c" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\u001b[92mTest passed!\u001b[0m\n" + ] + } + ], + "source": [ + "#TEST YOUR IMPLEMENTATION\n", + "test_error_square_function(error_square)" + ] + }, + { + "cell_type": "code", + "execution_count": 54, + "metadata": { + "id": "wgwOEQK9fMqA" + }, + "outputs": [], + "source": [ + "def total_squared_error(error, num):\n", + " total_squared_error = 0\n", + " for i in range(num):\n", + " total_squared_error = total_squared_error + error #Add the \"error\" to the \"total_sqared_error\"\n", + " return total_squared_error" + ] + }, + { + "cell_type": "code", + "execution_count": 55, + "metadata": { + "id": "ilzjasT4YJAh", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "955e953f-30c6-4ce8-e7df-0157a3db8b30" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\u001b[92mTest passed!\u001b[0m\n" + ] + } + ], + "source": [ + "#TEST YOUR IMPLEMENTATION\n", + "test_total_squared_error_function(total_squared_error)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "oS7bM8mBjJ-u" + }, + "source": [ + "$\\text{Mean Squared Error}=\\frac{1}{2*m}\\sum\\limits_{i = 0}^{m-1}(y-ŷ)^2$" + ] + }, + { + "cell_type": "code", + "execution_count": 56, + "metadata": { + "id": "Q6sFN7i2piR8" + }, + "outputs": [], + "source": [ + "def mse(total_squared_error, num):\n", + " denominator = 2*num #Multipy num with 2\n", + " mse = total_squared_error/denominator #Divide \"total_sqaured_error\" by \"denominator\"\n", + " return num" + ] + }, + { + "cell_type": "code", + "execution_count": 57, + "metadata": { + "id": "fZ816KtRYsoj", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "8ee6b888-02f1-4c09-bb6e-13dd537638ba" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\u001b[92mTest passed!\u001b[0m\n" + ] + } + ], + "source": [ + "#TEST YOUR IMPLEMENTATION\n", + "test_mse_function(mse)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "3Uqj2E0BlU_U" + }, + "source": [ + "**Finding the predicted value**" + ] + }, + { + "cell_type": "code", + "execution_count": 58, + "metadata": { + "id": "oiwBU-fSjp5C" + }, + "outputs": [], + "source": [ + "def predicted_value(w, x, b):\n", + " yhat = w*x+b #Multiply 'w' with 'x' and add 'b'\n", + " return yhat" + ] + }, + { + "cell_type": "code", + "execution_count": 59, + "metadata": { + "id": "MXs2kadnreTF", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "983f2ee4-cbc1-47ab-c3ef-47cf6e1ee5bd" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\u001b[92mTest passed!\u001b[0m\n" + ] + } + ], + "source": [ + "#TEST YOUR IMPLEMENTATION\n", + "test_predicted_value(predicted_value)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "qW9qAdiUwOrk" + }, + "source": [ + "## Cost Function\n", + "The equation for cost with one variable is:\n", + "$$J(w,b) = \\frac{1}{2m} \\sum\\limits_{i = 0}^{m-1} (ŷ - y^{(i)})^2$$" + ] + }, + { + "cell_type": "code", + "execution_count": 65, + "metadata": { + "id": "RCCqRXf-wNoI" + }, + "outputs": [], + "source": [ + "def compute_cost(x, y, w, b):\n", + " # number of training examples\n", + " m = x.shape[0]\n", + " total_squared_error = 0\n", + " for i in range(m):\n", + " yhat = w * x[i] + b\n", + " error = yhat - y[i] #Subtract \"y[i]\" from \"yhat\"\n", + " squared_error = error**2 #Square the error\n", + " total_squared_error = error + total_squared_error #Add the \"error\" to the \"total_sqared_error\"\n", + " denominator = m*2 #Multiply m by 2\n", + " total_cost = total_squared_error/denominator #Divide total_cost by denominator\n", + " return total_cost" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "OGswOCVFzR7W" + }, + "source": [ + "# Gradient Descent\n", + "## 1. Compute Gradient\n", + "The gradient is defined as:\n", + "$$\n", + "\\begin{align}\n", + "\\frac{\\partial J(w,b)}{\\partial w} &= \\frac{1}{m} \\sum\\limits_{i = 0}^{m-1} (ŷ - y^{(i)})x^{(i)} \\\\\n", + " \\frac{\\partial J(w,b)}{\\partial b} &= \\frac{1}{m} \\sum\\limits_{i = 0}^{m-1} (ŷ - y^{(i)}) \\\\\n", + "\\end{align}\n", + "$$" + ] + }, + { + "cell_type": "code", + "execution_count": 66, + "metadata": { + "id": "VMBk0PnA0wK3" + }, + "outputs": [], + "source": [ + "def compute_gradient(x, y, w, b):\n", + " # Number of training examples\n", + " m = x.shape[0]\n", + " dj_dw = 0\n", + " dj_db = 0\n", + "\n", + " for i in range(m):\n", + " yhat = w * x[i] + b\n", + " dj_dw_i = (yhat - y[i]) * x[i]\n", + " dj_db_i = yhat - y[i]\n", + " dj_db += dj_db_i\n", + " dj_dw += dj_dw_i\n", + " dj_dw = dj_dw / m\n", + " dj_db = dj_db / m\n", + "\n", + " return dj_dw, dj_db" + ] + }, + { + "cell_type": "code", + "execution_count": 67, + "metadata": { + "id": "3U-qZNSFE1QK", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "295516bf-cb99-42c1-e1c8-17c17e1d6681" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\u001b[92mTest passed!\u001b[0m\n" + ] + } + ], + "source": [ + "test_compute_gradient(compute_gradient)" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "AhWGXBq82p6P" + }, + "source": [ + "## 2. Update the parameters num_iterations times\n", + "$$\\begin{align*} \\text{repeat}&\\text{ until convergence:} \\; \\lbrace \\newline\n", + "\\; w &= w - \\alpha \\frac{\\partial J(w,b)}{\\partial w} \\; \\newline\n", + " b &= b - \\alpha \\frac{\\partial J(w,b)}{\\partial b} \\newline \\rbrace\n", + "\\end{align*}$$\n", + "where, parameters $w$, $b$ are updated simultaneously." + ] + }, + { + "cell_type": "code", + "execution_count": 68, + "metadata": { + "id": "OlNwBvu52cUv" + }, + "outputs": [], + "source": [ + "def gradient_descent(x, y, learning_rate, num_iterations):\n", + " # Initialize weights and bias\n", + " w = 0\n", + " b = 0\n", + " # Number of training examples\n", + " m = x.shape[0]\n", + " for _ in range(num_iterations):\n", + " # Compute gradients using the compute_gradient function\n", + " dj_dw, dj_db = compute_gradient(x, y, w, b)\n", + "\n", + " # Update weights and bias\n", + " w = w - learning_rate * dj_dw\n", + " b = b - learning_rate * dj_db\n", + " # Compute the cost for monitoring\n", + " cost = compute_cost(x, y, w, b)\n", + " print(f'Iteration {_+1}/{num_iterations}, Cost: {cost:.6f}')\n", + " return w, b" + ] + }, + { + "cell_type": "code", + "execution_count": 69, + "metadata": { + "id": "dpmvXbs4lmHO", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "20a72a06-6e97-4cc3-d294-6be9d01e96ae" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Iteration 1/10, Cost: -1.782000\n", + "Iteration 2/10, Cost: -1.589760\n", + "Iteration 3/10, Cost: -1.420232\n", + "Iteration 4/10, Cost: -1.270730\n", + "Iteration 5/10, Cost: -1.138884\n", + "Iteration 6/10, Cost: -1.022606\n", + "Iteration 7/10, Cost: -0.920053\n", + "Iteration 8/10, Cost: -0.829601\n", + "Iteration 9/10, Cost: -0.749820\n", + "Iteration 10/10, Cost: -0.679447\n", + "Final parameters: w = 0.7955, b = 0.2545\n", + "Final cost: -0.679447\n", + "\u001b[92mTest passed!\u001b[0m\n" + ] + } + ], + "source": [ + "test_gradient_descent(gradient_descent, compute_cost, compute_gradient)" + ] + }, + { + "cell_type": "code", + "execution_count": 69, + "metadata": { + "id": "NknHm9DGGonf" + }, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "_Vb4kNxkG_Ml" + }, + "source": [ + "# **Project:** Melanoma Tumor Size Prediction" + ] + }, + { + "cell_type": "code", + "execution_count": 70, + "metadata": { + "id": "ibTpczTtGokE" + }, + "outputs": [], + "source": [ + "import pandas as pd\n", + "import numpy as np\n", + "from sklearn.linear_model import LinearRegression\n", + "from sklearn.metrics import mean_squared_error, mean_absolute_error\n", + "from sklearn.model_selection import train_test_split\n", + "import seaborn as sns\n", + "import matplotlib.pyplot as plt" + ] + }, + { + "cell_type": "code", + "execution_count": 71, + "metadata": { + "id": "eqAMMJ9lGohp" + }, + "outputs": [], + "source": [ + "#Read the dataset\n", + "data = pd.read_csv('/content/Machine-Learning-Simplified/Day-1/melanoma_dataset.csv')" + ] + }, + { + "cell_type": "code", + "execution_count": 72, + "metadata": { + "id": "Q14KncK6GofO", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 423 + }, + "outputId": "c1c2ba0e-d576-4608-868c-82bc2d4cb538" + }, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " mass_npea tumor_size\n", + "0 18.159306 7.490802\n", + "1 39.693228 19.014286\n", + "2 32.659956 14.639879\n", + "3 27.556925 11.973170\n", + "4 9.800536 3.120373\n", + ".. ... ...\n", + "995 5.343260 1.831641\n", + "996 39.080774 18.346272\n", + "997 8.435708 2.736373\n", + "998 40.580192 19.004747\n", + "999 20.147810 8.920115\n", + "\n", + "[1000 rows x 2 columns]" + ], + "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", + "
mass_npeatumor_size
018.1593067.490802
139.69322819.014286
232.65995614.639879
327.55692511.973170
49.8005363.120373
.........
9955.3432601.831641
99639.08077418.346272
9978.4357082.736373
99840.58019219.004747
99920.1478108.920115
\n", + "

1000 rows × 2 columns

\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + "
\n", + " \n", + "
\n", + "\n", + "\n", + "\n", + " \n", + "\n", + " \n", + " \n", + "\n", + " \n", + "
\n", + "
\n" + ] + }, + "metadata": {}, + "execution_count": 72 + } + ], + "source": [ + "#Display the dataset\n", + "data" + ] + }, + { + "cell_type": "code", + "execution_count": 73, + "metadata": { + "id": "P9ipnJ_iKF42", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 466 + }, + "outputId": "2d38dd06-922d-487a-982d-57e16ed68cea" + }, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "" + ] + }, + "metadata": {}, + "execution_count": 73 + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "
" + ], + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAkAAAAGwCAYAAABB4NqyAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAACkWElEQVR4nOzde3zT9b0/8FfuaXpJ2oTSFtoSSKW03IKFgklRwAkIKMg8s3KOhaLuJxbcOE5AQblN0Dl1gOg2KbBN0LOhIKBsAgptQa5R7tiUSosFSkOTXtLc8/sjfL/k21xaaoEW3s/Hg8dZvrd8y9ns28/nfeF5vV4vCCGEEELuIvzb/QKEEEIIIbcaBUCEEEIIuetQAEQIIYSQuw4FQIQQQgi561AARAghhJC7DgVAhBBCCLnrUABECCGEkLuO8Ha/QEfk8XhQVVWF6Oho8Hi82/06hBBCCGkFr9eL+vp6JCUlgc8Pv8ZDAVAQVVVVSE5Ovt2vQQghhJA2qKysRPfu3cNeQwFQENHR0QB8f4ExMTG3+W0IIYQQ0hp1dXVITk5mf4+HQwFQEMy2V0xMDAVAhBBCSCfTmvQVSoImhBBCyF2HAiBCCCGE3HUoACKEEELIXYcCIEIIIYTcdSgAIoQQQshdhwIgQgghhNx1KAAihBBCyF2HAiBCCCGE3HUoACKEEELIXYcCIEIIIYTcdW5rALRs2TIMHjwY0dHRiI+Px8SJE3H27FnONTabDc8//zyUSiWioqIwefJkXL58OexzvV4vXn31VSQmJiIiIgIPPvggSktLb+aPQgghhJBmLFYHyqobYKioRdmVBlisjtv9SqzbGgDt2bMHzz//PL799lt89dVXcDqdeOihh9DY2Mhe89vf/hZbt27FP//5T+zZswdVVVV47LHHwj73zTffxIoVK/DBBx/gwIEDiIyMxOjRo2Gz2W72j0QIIYQQAFXmJhRsNGDU23swafU+TFhZjP+cuoyzl+pw6MerOFVlwXlT420Linher9d7W745iCtXriA+Ph579uzB8OHDYbFY0KVLF2zYsAG//OUvAQBnzpxBnz59sH//fgwdOjTgGV6vF0lJSfjf//1fvPjiiwAAi8WCrl27Yt26dXjiiSdafI+6ujrI5XJYLBYahkoIIeSOZbE6UNPgQJ3NiZgIEVSRYshl4nZ5bsFGA4pKawAAMrEAq57UYm1xOYqMJvY6nUaJmSPTkBonQ6Ii4md/7438/u5Q0+AtFgsAIC4uDgBw5MgROJ1OPPjgg+w16enpSElJCRkAlZeX49KlS5x75HI5srOzsX///qABkN1uh91uZz/X1dW1289ECCGEdERV5ibM2XSMDVIAYHiaCssn90ekWHDDgZHF6oCp0QGXxwu3x4vcISmYplPjaEUthHweCovLUewX/ABAybXP4/sn4eG+Ce0SfLVWhwmAPB4PfvOb30Cn06Fv374AgEuXLkEsFkOhUHCu7dq1Ky5duhT0Oczxrl27tvqeZcuWYdGiRT/zJyCEEEI6B4vVERD8AMDe0hq8uuUEns5Ro9Huht3lQa3ViYPlV/HAPV2QqIjA5TobahsdqLO5EBMhRKxMDK/Hi/lbTuCJISlYW1LOBjYAkKNRYd7DffDuzuC5uCVGE/J1atQ0OO7OAOj555/HiRMnUFxcfMu/e968eZg9ezb7ua6uDsnJybf8PQghhJC2uNGtLLPVian39UDukBRIRQIcrahFYXE5AOCJISl4b7eRs1WVo1FiiDoWZdUNWPj5Cc45vUaJhY/0hTZFERD8AECRsQZTLU1h39/u8qDe5mzLj95mHSIAKigowLZt27B37150796dPZ6QkACHwwGz2cxZBbp8+TISEhKCPos5fvnyZSQmJnLuGThwYNB7JBIJJBLJz/9BCCGEkFss2FZWTpoKCx/JBA+AslkwVGVuwvzNxwNycVbkanGyyhIiiDHhwLmr+OL4xYBtrGKjCQs/P4E5Y9Pxh3//0KafQSLkI1oqatO9bXVbq8C8Xi8KCgrw2WefYffu3VCr1Zzz9957L0QiEXbt2sUeO3v2LCoqKjBs2LCgz1Sr1UhISODcU1dXhwMHDoS8hxBCCOmMQm1lFV3byvrU8BNmbjSgytzEvT5ILs7aknKM6B0fEPwwusZIcbTCjIKRGqzJy8LqKYNQOHUwCkZqcLTCjCaHJ+R7GirNyNEog57TaZSorrdDFXXrtr+A2xwAPf/88/jHP/6BDRs2IDo6GpcuXcKlS5fQ1OT7f5RcLsf06dMxe/ZsfP311zhy5AimTZuGYcOGcRKg09PT8dlnnwEAeDwefvOb32Dp0qX4/PPPcfz4cTz11FNISkrCxIkTb8ePSQghhNwUNQ2OgOCHUWI0QZuswN7SGszddIzdJgt3fTgujxcrcrUwVNRi+vrDmPHRUeSvOwRDRS1W5GoRKRaEvLewuBwLxmciJ03FOc5UgY24p8stzf8BbvMW2Pvvvw8AeOCBBzjH165di6lTpwIA3nnnHfD5fEyePBl2ux2jR4/G6tWrOdefPXuWrSADgJdeegmNjY149tlnYTabodfrsWPHDkil0pv68xBCCCG3Ul0LeTN2l29VZm9pDZsjFE6Twx3yXKJcijd2nAkIlJjPv5/YFzkaFYqMgQGWNkWBL09exNJH+8Lh9sDS5IRMLECkWAiFTHTLgx/gNgdArWlBJJVK8d577+G9995r9XN4PB4WL16MxYsX/+x3JIQQQjqqmBbyZiTC6xs9TNAR9nkRIix7rB+WbDsFa7NgyOPhrhLJxALk69XQJitgd3lgc3mwYHwGFm87yckT0mmUmKZT45ODFZg6rMdtCXaC6RBJ0IQQQgi5caooMYanqbA3yLaWTqOEodLMfrY53dh9tho6jTLodpdOo8T24xfxfaUZa/KyMH39YTYI0mmUsLmuB0QysQArcrVYW1KOVbuN7PEH+8Tj9Un98JO5CbVWJyRCPgyVZnxysAKLH+3bYYIfgAIgQgghpFNiGg++9kgmFn5+kpPbw6y6zNpoAOArVd93zoTC4nKsyNUC4K7m+F9vdbgBrxcfPzsUF2qb2CDG6nCzqz4P3NMFliYnput7QpsSi8Liclgdbuw8XQ2Hy4M/PD4ADTYX6m1OTBrYDSq9ukMFP0AHG4XRUdAoDEIIIR2Zf+k7E5ToeikhEvDhcHmw75wJHx+swBNDUnBfTyX4PB6anG4cqahlj4/O7IrKq9cDHCaIYTCrQIzf/iINQ3rEYdXXxvDBE4Bds+9Hr/ioW/cXck2nHYVBCCGEkPCal75bHW6s2m3Eqt1GjEzvginZqchKicUjA5KwZOtJzhaVTqPE8sn9MWujARmJMZjx0dGQ38MkUDO8XmB1s+AHuL6SlK9Xs991q5satsVtLYMnhBBCyI0JV8q++8wVAMDhilos3noyaL+f9SXl+PjZoYiTidk+PsGSo+UR3ATrwT3iAp7n/1xtsoL9fKubGrYFrQARQgghnYTF6sBVqyPsNXaXB9pkBWflx1+R0YSp9XZ2e4vpAu2/hZWjUSE+RoKPns6G2+uFgMeD2xM+Y4ZZMRqeprrlTQ3bggIgQggh5Da40fldF81N+OaHK+jfPQYFIzVs+XmkWAi31wN5hAhOlxdymRBSoQCFUwfD5nRzZn0xAY7/9lbzLSydRolFj2Zi6fZT2H3mClvxFSEKX0IvEfIxPE2FNyb373AJz8FQAEQIIYTcYsHmdw1PU2H55P5IUkQEXH+5zoarjQ7ER0vA5/GRJJdi5rUKrxW5WqwrKUex0cQpT2+eqOy/yuPfHwjwBUFzxqRDm6xAdZ0NZquD3U6zOtyYtdGAlbnakI0Oc9JUSOsSxVZ/GSpqWxXU3U4UABFCCCG3UKj5XczIipW52oDhpXP+9X3Q4aUnfuIOL83Xq4MOM/U/b6io5fQHYlyobcLGgxVY8mhfnKtp4JyzOtyYudGAFblaeODlPH94mgpvTu4PD4AX//l9q4O6240CIEIIIeQWCpbE7N9V+YfqBsRFiqGK9AVBoYaXAsBvH7wH7+4sZY+Hy/0pMZow4wENBiYr2P5A/nqqIrHqWvDldAcONmVWgvL1aswdm47qOju6x0YgIcY3Zqpgo6HVQV1HQAEQIYQQcgs1n8cVqqvy8DQVFj2SiSPna4M+p8RowswR3MTk5qXrzQn5PAj5PHzw3/ciLtIX6NQ1uVBlaUKiXMoGKfHRkqAdpq0ON76vNOPxQd2Rkipjry+rbghZmcbMIetoARCVwRNCCCG3UPP5XaG2rfaW1uDVLSeQr1eHfJZMwk1Mbp7b05zb48XUtYfwVOFBjF9ZjLf+cxZOjwe7Tl9Go18TRLlMjOWT+2N4s+ntzHZXqiqSE9C0NGS1I/YFohUgQggh5BZqPr8rKyUWAJCvU8Pu8nCqtoqMJkzVhQ6AAHASkw2V5pCzvphxGP6Y67QpsQFbVUmKCKzM1aKmwYF6mxPRUhFUUcGTmlsaytoR+wJRAEQIIYTcQszqytxNx3D4fC0SFVIYimsDOjYzVVtA4OR1qUiAS5YmFBuv4MXRveGFF8XG67O+eABnInuORoU8XY+guT8lRhPydb4SeP+tqhsp0w83lLWj9gWiWWBB0CwwQgghN5vF6oDZ6sT8zceDdljWaZTQpsRiTGYC6m1O/LXoHDKS5GwQFCsTIVEuhd3lhscDeLzA+atWyEQCuL1e8Hg82Jy+kve4SDGmfHiAM+vL3+opgzDjo6PYPOM+DEyJveEyfcBXrTZ30zFOEMT0BUq8RVVgNAuMEEII6eDkMrGvIqxZ8OO/2hMl8f2avnDViv8emoo1xdxEab1GicWP9kXe+oP4438NDDnba01eVsjgB7ieOxQtFd1wmT7jRrbMOgIKgAghhJDbhEkeZoKeQSmxkIkE8MCLfWUmtnvz65P6Ym1xYKJ0sdGE1z4/iQ/++17O8eZbZvHRUuSkqYJWauk0Shgqzci5tlUVbtZYSxVdclnHDXiaowCIEEIIuU1ipKKAMngmeBnWUwl9LxWanG4oo8RYuv100GcUldZg6n02GCrN0GuUOFphDiirl4kFKMzLYq9n6DRKTNOpseHAeSx6JBNymRjnahrDvnNHrOhqCwqACCGEkNtEFSXGgvEZbBl8qJ5AORoVNj+vw1enLsHl8aJfNwWEfB7by0cs8PX3ma7viXGWpoCyeqvDjfz1h7FgfAbmje2DBrsLkRIBnG4PzI1OZCTJ2Ws7Y0VXW1AARAghhLSz1lZQyWViDEpRYN6nxwGE7glUZKzBoq0nMb5fEnqoZJi+/jCb08Os4hy7YEb/7nL0TojGvM9OBHyX1eHGvE+PY01eFjsJnjE8TYVnrvUb6owVXW1BjRAJIYSQdlRlbkLBRgNGvb0Hk1bvw6g/7sHMjQZUmZuCXu+fnKxNVgTt4QP4ytXjYyRY9bWR0xyxxGjC2pJyZCTJsaa4HDwe74bel2luCPg6Ov9oasTiR/sGbYLYWSa9twatABFCCCHtxL+Cqnki8nmTL7emeRm5/5ZTS6Ms7C4P27fHn38vn7ljwwdAKXEy7Jp9P6dSq9Hh5szykokFWDA+A6+M64Mmh7vDV3S1BQVAhBBCSDthKqjC5fL8flJfpCgj2WMRYgH0GiWKjaYWR1kw54MFSsyx+iZXyIqv4WkqxEdLOIFMsLJ3ZrtseJqqQw4ybQ8UABFCCCHthClrD5fL8/Jnx/HH/xqIrtemqNfbnJiqU8OL8KMsmHJ1wDesdE1eFmd0RkKMBDKxAHKZCNN0PeDxejnPCbWF9XPK3jszCoAIIYSQFrQ2qZnZztImKzgrP/6KjSZcbXTgQq0VkRIh6ptcmLXRgHy9GmMyu2JC/0Qs3X46aLn6rI0G5GhU+OFyPV72S3TWa5R4uG8CPn1uGMDjIVoiwoJxGRAIeKhtdEAsFCBRLmWDLn+dcZBpe6AAiBBCCAnjRsZCqKLEeLBPPOIixQErNExTQwAwW53I/eu3AIANT2fD6nBj1W4jtMkKzNxowLPDe+KlMb1RXWcH4FsZmrXRgHtTYzHjAQ2mrz/E+d5iownLvjyDCf0T8dKm4+zx631+yvDq+MygP9/dUvbeHAVAhBBCSAgtJTUL+DzOqopcJsb8cRlY0Gy+l/9wU6vDjSipgD2375yJnehuqDRDm6LAuztL8Ze957AyVwupSICMxBiszNUiPlqKX/1lf9CxFkWlNXhpTG/IxAL2vP+09wVbTmBVkHyeu6XsvTkKgAghhJAQWkxqTlNh4SOZ4AFQRvoChebBD3A9EMnXq/F9pRk19Xb2XGFxOT6bcR8WbzvFTnP3v2fKhwfYa1dPGRR2pld1nR35ejXnHUNNe2f4T6cPNsj0Tsz/ASgAIoQQQkJqMam5tAavbjkBbUosjlWa8cq4PkEnuwO+QGTGAxo83DcBV+rt7EqN1eHGRbMN+To1pA8I0GB3Yc6YdAj5PFiaXJxntFQlBvjyj5pjK8RC5PN0tkGm7YEaIRJCCCEh+Cc1h2tQqE1WYG9pDS7UBm92yBAJ+Hiq8CD+UnSO08zwcEUtIkQCTPnwAH799yN4ZFUJLlpssDq4ARBTJRYMUyUWrETef9p7KHKZGL3iozAwJRa94qPu6OAHoBUgQgghJCRVlBi/6BMPkSD8ekFLDQwZUhEff30qC1FSIRwuD/QaFUQCPn6saQhY3TFUmpEkl3LK4oNtkQHcKrGV1877nzNUmu/ofJ62uK0rQHv37sWECROQlJQEHo+HzZs3c87zeLygf/7whz+EfObChQsDrk9PT7/JPwkhhJA7kVzmG1Yq4IfvrswEL4ZKM3KajZBg6DRKfH22GmarE4fKr+KSxYarjQ5YmpxwuL1QRIohE19Pji4sLkeiPAIFIzTsqo/V4casjQaM75eIrTN1eP+/B2FNXha0KbGYtdGAQSkKtlcQ853TdGqcvVh3R+fztMVtXQFqbGzEgAEDkJ+fj8ceeyzg/MWLFzmfv/zyS0yfPh2TJ08O+9zMzEzs3LmT/SwU0kIXIYSQG2exOvDK5hMYkKxoVYPCwuJyfDErB69uOYG9fpVjw3oqIeDxIBXxIRby8WHxuYAVHLUyEgsnZLBl7FaHG89vOIpf398TrzzcBx4vYHW4IBEKwOcB73z1A3afucI+I0ejxJKJ/dDkdOGBe7ogSiKEgM+DgM/DW48PoOCnmdsaGYwdOxZjx44NeT4hIYHzecuWLRgxYgR69uwZ9rlCoTDgXkIIIcRfa5obMlVgR87XBt16yklTYcH4DJTXNKJw6mCYGuwQ8XkY2y8R+To1usfJsOjzEygsLke+Xo2HMrpi2RenAwIp5vOiRzI5gZbV4cah8qvITJJj1kYDAKBw6mB8WHQOGUlyTMlOhd3lgSJChJQ4GbrHyW7a39edptMsjVy+fBnbt2/H+vXrW7y2tLQUSUlJkEqlGDZsGJYtW4aUlJSQ19vtdtjt10sS6+rq2uWdCSGEdEytbW7IVIExW0/5ejXydWo43B50j43AiQsWTHyvhC1NX/ZYP8z99DiKjDUoGKnBmuJzOFJhZkvotcmKsFViNqcHQ9RxyNep2SaK3WMjUFXbhJW5WnSPjUBCjBR/fHzAXVWxdTN0mgBo/fr1iI6ODrpV5i87Oxvr1q1D7969cfHiRSxatAg5OTk4ceIEoqOjg96zbNkyLFq06Ga8NiGEkA4m2PBPwDf3au6mY5zhn/5dkpluzQDw21+kobbRga4xUrz1+AC223PXGCmKjL7nMuMwCkZq2BL6KdmpYd+tyeHGiN7xyF93CDUNDgDAF7P0SI6TBQQ5FPD8PJ2mDL6wsBBTpkyBVBo4x8Tf2LFj8fjjj6N///4YPXo0vvjiC5jNZvzf//1fyHvmzZsHi8XC/qmsrGzv1yeEENJBtGb4J4PpkuxPJhZgbGYith+/iOnrD2PGR0eRv+4QDBW1kImuJzEzlWH+JfQt9fGpsznx5o4z+DBvMGRiAYanqdBNEXFXlKXfap0iACoqKsLZs2fx9NNP3/C9CoUC99xzD4zG4EPpAEAikSAmJobzhxBCyJ2ppeGftVYHLFZfEMR0SfYPgvL1aizZdjJoHo/b62U/M8GOf4l8a/r4FBtN+OO/z2LB+Ayq3LqJOsUW2Jo1a3DvvfdiwIABN3xvQ0MDysrK8D//8z834c0IIYR0Ni0N/7Q0OTFzowGLH+0LS5MD0VIR/vD4ADTYXKi3ORFxrVR9ql+eDjPsdH+zuV46jZKz6tOaPj4AUGSswasTMpDYbNhqa6fSk5bd1gCooaGBszJTXl6O7777DnFxcWzScl1dHf75z3/ij3/8Y9BnjBo1CpMmTUJBQQEA4MUXX8SECROQmpqKqqoqvPbaaxAIBMjNzb35PxAhhJAOL9zwT2YVZm9pDV7ZfBzalFis2m1kE6R7xUeh7EoDDBW1nHlbzLDTuZuOYcPTQ7Fk20k22LlcZ2Mru5onUwOAPEKEb364wg5KZTTauV2gb2QqPWnZbQ2ADh8+jBEjRrCfZ8+eDQDIy8vDunXrAAAff/wxvF5vyACmrKwMNTXX/8tw4cIF5ObmwmQyoUuXLtDr9fj222/RpUuXm/eDEEII6TRCDf/UaZSYrlfj+E8WrMnLgt3lQcq1svLC4nLM3XQMf3h8ABZuORGyjP2JISnwwot7e8Rhqk4Nl8eL7J5xyFYrsfDzEyi6FgSt2m1EjkaFPF0PPFV4MOiAU/+xFTeSuE1ah+f1+m1YEgC+VSe5XA6LxUL5QIQQcoeyWB34ydyEH01WSIR8HP/JggHdFQFNCnM0SiyYkImdpy9hZHpXjHm3KOQzNzydjUiJEI++V8IeKxipwakqCzKS5BjRuwtcbi9cHi9sTjc+OnCe08yQMTxNxQlqyqobMOrtPSG/d9fs+9ErPqotfw13lBv5/d0pkqAJIYSQ9iaXiSERCjDjo6OYvv4wXB4vJ/iRiQUoGKnBVJ0aVbVNGJOZiJ9aGHbK5/NQ2+jgHCssLseT2akwVNTCbHVi2rpD2H/OBAGPhzlj0pGj4VaZDU9TBSQ/t5S4HWrKOwmtUyRBE0IIIUD7JwH75wMNupbvA/iCH6Z5IdPL56/F59i8nVCiJEI02l0Ymd6FXdnxz/uJkgg5/YSYURlTdT1gd3nQQylDN0VEwM/UUuJ2uCnvJDgKgAghhHQK7ZkEzARSDXYnFj/aF69uOQGh38DTfL2abV4IXG9qqE2JDTsTbMfJS/i+woyFj2YCOMUJgr6vMGN8/0TOPf7BEODbygoW0IVL3KYp721DARAhhJAOrz2TgJsHUjKxAAvGZ6BLtIS9RpusQGFxOQpGaqBNVkAmFqJw6mAcu2DG03rfPMrmeUJ518rYrQ43XttyAq89kon/HtoDNqcb8ggRbE43IkSCNgUyoRK3g22XkdahJOggKAmaEEI6lvZKArZYHSjYaAgIpGRiAbYU6FBdZ4elyYnUuAg4PcAf/n0moF/Pszk94fF6oYqWoMHmRrRUCImIj9y/fMvpIv3R09nYf84EQ0UtpunU+ORgBd56fACsDje++eEK4qMlbB+hy3U2jLinCxJaWMliVq5oBlhwN/L7m1aACCGEdHg3kgQcKk/IYnXgosUWNPhZkavF4s9PsoNKC0ZqYKioDdjqMlSYIRby8d7XRhQ3WwFaPrk/p5ePpcmJ0ZldAQCfHKzA4kf7Qi4To9HRhC+OXWRnhgG+lZz772m5XYtcRgFPe6EAiBBCSIfX2iTgUHlCSyf2xeJtp/DYoO4B9zbP9wGu5/wEu3bV18aAwKjIaIKHOX/tPomQjyaHB5MGdoNKr2aDsDmbjnGCH4D6+dwOVAZPCCGkwws2lJTB5M6EyxN6+bPjSE+MCTqM1H9YKcN/fldL1zJKjCaMzkxAwUgNRqZ3gaHSDGWkmDPI9EYGsZKbi1aACCGEdHitSQIuq24IGVwUG02YplPjRJUFr0/qi64xUjb/JlYmgkws4HRjZgIlpkxdm6yA3eVBfLQEBSM1KCwuD9q9ufKqFd9V1GLB+Eys3PVDQFIz9fPpOCgAIoQQ0ikkKSKwMlcbMgm41hp+9UQi4mNs30Qs2Xo91wcActJUWJGr5eTvGCrNGJneBU9mp7K9gBjM3K/ms7sAX+BUbDRhybaTQauzqJ9Px0FbYIQQQjoNucy3pTQwJZaztWSxOuAIsW3FiJOJsahZ8AMARaU1WFdSjnz99SaHhcXl+M2D9wTkBgG+ra61za4Hrg9SBXwrTjZn4Pu0ZiuP3BoUABFCCOk0LFYHyqp909jLrjTAcm3Vp6bBgX3nTNBplEHvy9GowOPxQubvFBtNGNbz+r1WhxuNdlfYfB9tsoL9rNMoMU2nRmFxOXss2HYWs5XXPAiifj63Hm2BEUII6RSCVXjlpKmw8JFMmJscKCwux4pcLQAE9O7J16thaQqfX+P2erEmLwuR18ZZCAXh1whipCKsnjIIEiEfhkpzwJZYqO2slrbyyK1BARAhhJAOL1SFV1FpDV7dcgJzxqRzZm799sF72IDnRJUFXngRLQn/K8/p8mD6+sNYPWUQZnx0FNtn6sNeHyUVYsWuHwK21ADfio6Qz4OhojbozDLq53P7UQBECCGkwwtXPl5iNMHh8rAzulbtNkKbrMD09YevDzUtLseAFuZ4Mfk7EiEfMrEAURIhcjSqgJ49zPXwevHi6HSAdzZgVWrGAxqMXVHErgi1dWYZuXkoACKEENLhtVQ+XtPgwJwx6ai3uWBpciIhRoI1eVmIj5bizR2ncaTCjHt7xGHu2HRU19nB4/FwtKIWhcXl0KYoMO3aHC+dRokTVRYU5g3Gkm0nkafrAQ+8nKBJr1Fi4SOZ+M+pS8hIkGPRhEyUmxoBAMmxMhw5X4v89Yc422F7S2swZ9MxrKJGhx0GBUCEEEI6JP+RFhFiQdj+O91ipVj+pW9uF7vqU1KOfJ0aRyrM7Od3d5ay9+RolNg2U4+tx6owa6MB96YosGBCJhxOD97YcRpFRhP2nbuKfL0a+To17C4PO9R0+Rdn0Le7HG6vF/V2F9bv+xFvTO6PBrsL8z47HvTnKSqtQXW9nQKgDoICIEIIIR1OsIRnfYj+OzkaJY5fsLCrNP6jLaZkpwYddQH4xle8tuUk5j6cjtEZCTBU1GLieyVYmatl83qsDnfASIw1eVnYeaYaudkpiI+RQCzgsyMsDv14NezP1VIiNrl1qAyeEELITROqbL2le4IlPBcbTQH9enQaJRZMyMTS7achu7ZKNDqzKxvsSIT8sOMriow1EPB5+P32U5j32QlYHe6QYzAY/ufPXKxHQoyUXdWJFAvC3itr4Ty5dWgFiBBCyE0RajBpS8nA4RKei40mzB+XgRG9u8Du9ODgj1dhbvQFVcw2V0ZiDHu9odLM6dcTTL3NxankCjYvzB9zPiFGiszEGM6WVqRYGDbROlJMv3Y7CloBIoQQ0u7CDSadu+kYZyUoYJWoKfwqkc3pxr2pcchMisGjA5Lg8ng521z+AUxhcTniYyRhn9d81cZQaQ7ZUJGpFstJU0EVLUFCs0BOIRNh5si0gPt1GiVmjkyDQkajLjoKCkUJIYS0u9ZMPZfLxEFXiTY8nR322f4NBi9abNh3ztfFmcnVYQKYEqMJVocbu05XI0ejDNmvp/mqTLiGitN0anx8sAJvTu6PrjHSgOfJZWKkxskwvn8SmzgtEfJRXW9HjzgZJUB3IBQAEUIIaXetmXoeapVo3zkT9BolioMELDlpKri9XpRdaYCQz4PH60VhcTn0va6PlmgewPxl7zmsyNXCC3CemXNt/IRMLMDwNBU7Zd6/oeLzIzTg83iIlAjgcnthd7rx+0n9ggY/jERFBB7um8Dp9JyVGkvBTwdDARAhhJB215qp56FWiZgAhsfjBVSB5d3XAxPfK4HV4UZOmgqvTcjAs8N7IlIqxOopgyAVCXC0ohZzNx3DE0NS2FWYRLkE03Rq5Ot7wuZ0QxEhglDAg0wsYOdzzd10jBMEfVdRi4HJCrbqjJnXFS74YVCn546PAiBCCCHtjpl6vjdIgDM8TYUoqRAVV61B72VWYD597j443B7YXR44XR7sO2filMAfOV+Lmno7jvx4ldPfZ2R6FxROHYyaBgdsTjdiZSJcrrNj5rV7ma2sWX8zYGuBHnKZOOh8riipbybYhqezaV7XHYgCIEIIIe0u2KoK4At+lk7si1c+O47cISmQiQXI16uhTVbA7vKwKziFxeX4ydyE6esPY01eFqavP8w+g7nnoYyu+MOOM5zcHplYgCezU/HGjjOc/J2cNBU+m6HDRXMTDlfUsoGU/8R2WrW5u1AARAgh5KYItaryymfHsfN0Nfp1l2NNXhZWfW3kNBvUaZRYk5eFg9eaCvr33fHv8qxNVgQkNodselhag6XbTmJASiznu0JNbCd3PgqACCGE3DTNV1XKqhuw83Q1AEDI5+HHmkbk69SYkp3KWf1Z/U0Z8nU9IBMLOGXtzbs8N19BSo6TBXRuZhQZTZiqu95EcXiaCqooWvG5W1EARAgh5JZhevzIxAL8ok8CFm07yd2q0iixeYYO5aZGxEdL8fGzQ1FUeoUta9cmK9gARya6vhrEHFs9ZVDY72dWk5iEZtryuntRAEQIIeSWqDI3web0BSD5ejWWNAt+AN8qzaJtJ6FNicWv/34Eeo0SL41JR98kOfjgboe5vd6A7a6Wujj3UMqwa/b9lNBMqBM0IYSQm89ideDVLSfQ5HTjo6ez8VBG16CNCQGwKz2Ar2/PH/59Ft1jIzBhQBKS4653XubxeAEBVLguzsPTVOimiECv+CgKfggFQIQQQm4+U6MDT2anYMOB89h/zhe0rJ4yCIVTB6NgpCZgSKj/Sk9RaQ2q6+1QRUtQU29HjsbX9NDmdKO5wuJyTNOpA4KgHNryIs3c1gBo7969mDBhApKSksDj8bB582bO+alTp4LH43H+jBkzpsXnvvfee+jRowekUimys7Nx8ODBm/QTEEIIaQ23x4sN355HbnYqDBW1eGRVCWZ8dBT56w7BUFGLFblaThAUHy3hfHZ6vFhb/COu1NuRp+sBnUYZdLuL6SGkTYnFly/k4J+/HoatM3WYpE2iSeyE47YGQI2NjRgwYADee++9kNeMGTMGFy9eZP9s3Lgx7DM/+eQTzJ49G6+99hqOHj2KAQMGYPTo0aiurm7v1yeEENJKbq8X6UnyoCXqJUYT1paUI1/vq9DSaZT44XI9JyiKlYlQZKyBMkrCBjhdoiXICbLdZXW4YaioxfbjF/H4n/dj+ZdnEBMhhqkx/JBVcne5rUnQY8eOxdixY8NeI5FIkJCQ0Opnvv3223jmmWcwbdo0AMAHH3yA7du3o7CwEHPnzg16j91uh91uZz/X1dW1+vsIIYS0rN7m4lRwNVdiNCH/2tbVNJ36WpCjQL5eDUNFLVxuLwDf1pjV4caq3UZ2ZIYHwYeWztpoYJ8NAAsnZN7cH5J0Kh2+Cuybb75BfHw8YmNjMXLkSCxduhRKZfAEN4fDgSNHjmDevHnsMT6fjwcffBD79+8P+R3Lli3DokWL2v3dCSHkbmWxOlDT4ECdzYmYCBEixQJcqbeHvSdKIsScMemoaXDgrccHQCoSICFGgntTYmGx+jo2+297+Q8tnT+uD3jgwenxoLbRCbfHi3y9GoXF5bA63CgxmuD2eG/qz0w6lw4dAI0ZMwaPPfYY1Go1ysrK8PLLL2Ps2LHYv38/BILAvdyamhq43W507dqVc7xr1644c+ZMyO+ZN28eZs+ezX6uq6tDcnJy+/0ghBByF6kyNwVMef9ilh7yiPBdl2USAd78kjvaIidNhQXjMtDocOH1SX1xosrCucfqcKOwuBy/HNQdCzYf59yr0yixIlfLjr1gZogRAnTwAOiJJ55g/3O/fv3Qv39/9OrVC9988w1GjRrVbt8jkUggkUja7XmEEHK3slgdmLPpGI6cr0XBSA3bodnm9CAxRooH0+Ox80xgTmaORonjFywBpfFFpTVsX6DvK8yYpvd1h/YPZhaMz8CCzScC7mW2vvL1aqzabWwxACN3l05VBt+zZ0+oVCoYjcH3kFUqFQQCAS5fvsw5fvny5RvKIyKEENI2NQ0OHDnvq+oyVNRi+vrDmPHRUTz2/j689vlJzB+fgZHpXTj36DRKLJiQiaXbTwd9JtMXqMhYg8Li68nSgC9w0qb4zoW7l8ZekOY69ApQcxcuXIDJZEJiYmLQ82KxGPfeey927dqFiRMnAgA8Hg927dqFgoKCW/imhBDSeTXP31FFtr5rcp3NGTCQ1H9eV9mVBvzvQ73xmwfvwUWLDUI+D4ZKM8prGsNuUTF9gYqNJswZm46MxBhIhHx0iZag3uZq8b2oBxBp7rYGQA0NDZzVnPLycnz33XeIi4tDXFwcFi1ahMmTJyMhIQFlZWV46aWXoNFoMHr0aPaeUaNGYdKkSWyAM3v2bOTl5SErKwtDhgzBu+++i8bGRrYqjBBCSGjB8neGp6mwfHJ/JCkiwtzpEyMVced1iQPndQGAXqPEVJ0aM6/l52x4Ojvsc/2TnyuvNmHGR0cBAGvyspASJwt7b0qcDImteHdyd7mtAdDhw4cxYsQI9jOTiJyXl4f3338fx44dw/r162E2m5GUlISHHnoIS5Ys4eTrlJWVoabm+v9Qf/WrX+HKlSt49dVXcenSJQwcOBA7duwISIwmhBDCxeTv+Ac/ALC3tAZzNx3Dylxt0FUU/xWjKIkQUtH1IpXmq0GMYqMJPB4Pnz53H8ADzFYnO/C0OZ1GCUOlmf3MNEm0OtzoHhuB+GgJhqepsLc0cBtseJoK8dGU40kC8bxeL9UFNlNXVwe5XA6LxYKYmJjb/TqEEHJLlFU3YNTbe0Ke3zX7fvSKj+IcC7ZitPGZbOT+9QAA3wrN9PWHQz5zTV4WZm404JNnsxElEeGixQZzkxNSkQBHK2pxqsqCJ7NT2UounUaJcf0SER8jxScHK/DW4wMgl4lRZW7C3E3HOEEQM/GdVn/uHjfy+7tT5QARQgi5MTeSz1Nnc4Z9Vn2z86FWjKwON/QaJYqNJs5Mr2CY8xKhEPO3nOCsAOVoVPjf0b3x9PpDbPDDNDgclKLg5PUkKSKwMleLmgYH6m1OREtFNPGdhEUBECGE3KFuNJ8nRhq+TDxSIkRZdQO71eX2egOCHwAQ8HiYqlPDCwSd1+VPIuQjX6/G4m0nA7a/mMquvz6VhauNDhgqzexKULHRBJuTG1zJZRTwkNbrVGXwhBBCWqelfB6L1RFwvZDPQ06aKujzctJUOHy+FqPe3oNJq/fhF+/sxU+1TUGvtTrdLc7rAnwl7IZKM7TJChQHyf0BfEHQ1UYHpq8/jFW7jZxKseYrUoTcCFoBIoSQO1BNgyPo6gzgC4JqGhzsagmzUsT07/F4vZzVmOFpKswdm47qOjtWTxnE5ufweLygz5eKBK2a17Xo0b5Yuv0UMhLD52qE2kaLbmHFipBwKAAihJA7UGvzeSxWB/b8cAVT7+uB3CEpEPH5yNepMV3fE16vFylxMkiEfCzcehK7z1xh79dplHgoo2tA5ZZMLIAqSszmAPnP68rX+RoYyiNE+OaHKzBeaUBGkhypLZSxB9tGo8aG5OeiLTBCCLkDtZTPw6ye1Fqd2Hasiu3YnLf2IApLyuHxejFzowFiAR+vfHacE/wAvtWcd3f+gJdGp3O2zfL1ary78wdM1amRo/EdZ1eDSsrhBfBU4UGs2m1EolwKbbICUpGAvba5HI0Kl+tsnGNMdRfl+5Cfg8rgg6AyeEJIZ2exOjBzoyFkb5yVuVrYXB68+H/fBczQAoCR6V0wJTsVSYoIlNc0sttezHR1xo7f6GG2OhEjFeOipQnxMRJMWFkCmViAlblaSEUCWJqckAj5MFSa2fv1GiUGpsRi1W4jZGIBtjyvw8KtJwO2yabr1Tj+kwUPZSSgyeGGPIKqu0hoN/L7mwKgICgAIoTcCcL1xgGA8ppGPPnhgYD7mO7N60vKA6arT9OpMXfTMTwxJAVZqbGIkgjhdHsQKRHiib98i7ceH8B2afbvAu0f2DBdoJnnaJMVEAv5iJGKwOOBMyKjsLgc2hQFtCmxOFZpbnVHanJ3ogDoZ6IAiBByp7hcZ0NtowN1NhdiIoSIlYkhFfJRsNGA3CEpbLDCYFZu1jULfhg6jRJzxqTjjR1nmvXsUSJPpwafx0P+ukOc5zFzwOwuD3qoIvHF8Yv4+GAFlk/uHzI48m98OM3vM7N6RStAJBhqhEgIISRkH6BXxvVBUWkNpt7Xg3M9s2IjFQmCBj+AL/en3uYK0rPHBA+AfJ2akxjN5P8AvuDpxYd6Y9VuIwpGasKOyPi8QAerw42vz1azwQ8QWMFGSFtREjQhhNyBwvUBunCtf4+h0gydRgmZWICCkRp8/OxQrC8ph6UpfAVZqPMlRhMEPB6mXQuC/OVcW8mxO32BjDZZEXTuFwAUldbgvMmKN3acQWaSPOA89f8h7YFWgAgh5A7UvA+Q/1ZUpFiIwqmDceyCGb/O6QWRkIdVXxuhTVagyGjC1Gvl6qGE6+7s9noxd9MxvDG5P+aOTUej3Ze4fNHShH8ersS8sX0wPE3VqhEZTICUr1dzJslT/x/SHigAIoSQO5B/HyBma2vDgfMAwObjDFHHIT5agmVfnEaJ0YQp2akArq8MBVuhyUlTcSazN6eQibDh6aFYsu0kZxstR6PCvIfTIY8QYfnk/vixpjHs+zNBVonRxPYPAqj/D2k/FAARQsgdyL8PUL5ejQ0HzuPJ7FSsLSnnrKbkaFTI0/XA/nNX2aCD6d4MIGA46YsP9cbKXaVBv1OnUcJsdeLtr34IPtfryzNYlatFkiICgmtjN4J1q9ZdG5HBYFaLqP8PaU8UABFCyB1IFSXG8DQV9pbWQJusAICgScdFxhp44EW+Xs1Z+fHv3mx3eaCIECFaKsSMj45i0aOZsLs87LBSwBcczR/fBx6PN2xuD5PA3DVG6tsma1am71/1xeihlGHX7Pup/w9pV1QGHwSVwRNC7gRMH6AnhqRAIuRj+vrDIa9dP20IPF4PEuUR+MncBB6PxzY+1KYo8NLodDQ5XAB4cLg8cHk9iI+WwtLkREyEEC63FxarEyIhH1OC9BZibJ5xHwamxLKfLVYHquvtqLhqBQBOs0QAVPZObgiVwRNCCEGSIgIrc7W4WGdDk8ONNXlZsLs8AV2dZWIBusVG4LXPTwRseW2fqYfV4cYfvzobMAtsul4NU4MD8dEKNLpdSFHKwOch5PcAgQnMcplvVSdSIgzZtJGCH3IzUABECCEdjMXqQE2DA3U2J2IiRFBFtrz1E+4er9eLMxfrEB8jBQAIeDzoNUqMyUxAZa0V8dFSHCo3wVBh5jyzyFiDBVtOoGCkJugsMB6ANyb3R7dY3zDTKnMT5vzrGGdrTKdRYkWuFrM2GpCVGhsygZkJ1moaHKi3OREtpZEX5OaiAIgQQjqQUM0Lw42ACHeP2+WB2erEtuMXUWI0sRVhf9ldHjB3iwlU/Gd9FRtNmDM2Pej3MtPey6ob4PZ6sWTryYAGisx3LBifgQfu6RI2oGFWgwi5FagRIiGEdBDhmhfO3XQMFqvjhu/xAFj1tZHTUydYMnSJ0YS1JeXI1wf2AGqwXQ+ImKaJa/KysHrKIDjdHvAAON2esN2j702JRSLN8CIdCK0AEUJIB9G8eaG/UCMgWrrH6nRzgh1tsoJTBu+vec8dRpRUAIA73NT/GTqNEjNHpIX92SprrYiSCmmQKekwKAAihJAOoq6FEQ/BRkDU2ZwBA0f9k4+b39OaDsz+9BolGu0uAOFXj2Y8oAn7XACYu+kYVXSRDoMCIEII6SBiWhjxEGwEhDxCFHJVZkWuFjER3HvCjbEAgPhoCVvFpZCJ0F0RAbfHi5w0VdjVo/3nTMjRqDgJ0P7vYqg00yBT0qFQDhAhhHQQTPPCYEKNgIiUCEOuyqwrKYdUKECO5vozmWaHweSkqVB6uR7T1x/GjI+O4sm/HsDLnx1HuakRWT1iESkO/e/MhcXlmD++T8CzmcaGhcXlAGiQKek4aAWIEEI6CLlMjOVBuiOH64fTYHOF7LxcbDThksWGafoekAh5SE+SIyslFhP6J2LpttPNOjkrMeMBDaavPxTwDB6Al8b0gd3lRihWhxsXzTZoU2KRr1MjUiJEo90FQ6WZU1lGg0xJR0EBECGEdCA32g+npbwh8IDTF+sw88F78NaOM1i128jmDP2/B3pBwOfB6nBDFSXGE3/5llMCzygymvCCy9cwMdw21+GKWqzabYReo8TAlNiA7TIaZEo6EgqACCGkg7mRfjgt5Q012l2IlYnx1o4zbJm61eHGqt1GrNpthE6jhDYlFhmJMUGDH4alyYmnCg9iRa4WHngDeggx87ty0lT4/cS+WLLtFOd+6upMOhoKgAghpBOLkgpbnKquTVaE7dETrPQ9GKvDzRmSCgAJMVLIxALUWh3Y8rwO8dESyGVivPX4AOrqTDo0CoAIIaSDaO0IDIvVAbPViQaHC1a7CwsnZGLZF6eQniRnS+EVMhGiJELkrzuEjMTwQyEjJUJIhPwWq7iA66tHjDV5WVi/78eA8nbq6kw6OgqACCGkAwg2ziInTYVlk/qhe5yMPXbR3ITzV61YubuU3YZSRYnxt/whWPbF6YBS+OWT+0PI44X97ka7C/nrDFiRq4UXXhT7D0RNU2H+uD64ZLGjYKSGM9gU8PUNovJ20hlRAEQIIbdZqHEWR87Xoqj0CgalxsLqcCNKIoSp0YG/7C3j5OA8MSQFv//idNBSeADI16mh0yiDVosxqzv+21vPPaCBWMCHw+3B/nMmTFq9D1aHO+i8MKavEJW3k87mtvYB2rt3LyZMmICkpCTweDxs3ryZPed0OjFnzhz069cPkZGRSEpKwlNPPYWqqqqwz1y4cCF4PB7nT3p68EF+hBByu1msDly02Njgh5m1VTh1MArzBiNVFYmtxy5iyocH8It39uK93UY8mZ0KmVjAPkObrAhZCl9iNEHA52H+uAxseDobq6cMQuHUwSgYqcHI9C6cHj3M9taUDw/A4fZgyocHsGq3kQ12ms8L898ao/J20tnc1hWgxsZGDBgwAPn5+Xjsscc456xWK44ePYoFCxZgwIABqK2txQsvvIBHHnkEhw8fDvvczMxM7Ny5k/0sFNJCFyGk42G2vXKHpAAIP2uLWXkpMtbAAy/y9Wq2pF0kCP/vshEiAV7ffoqTCJ2TpsL/PtQbT68/FLT6y9IUfEWHSZr2r/yi8nbSGd3WyGDs2LEYO3Zs0HNyuRxfffUV59iqVaswZMgQVFRUICUlJeRzhUIhEhISWv0edrsddrud/VxXV9fqewkhpC38t72m3tcDQPhZW8z5Vbt9k92f0ffEb3+RhrGZiahpsDd/PIfb4w2oAisqrYHH68UTQ1KCjrcINzIjUiKENiUWszYakJUaS+XtpFPqVKMwLBYLeDweFApF2OtKS0uRlJSEnj17YsqUKaioqAh7/bJlyyCXy9k/ycnJ7fjWhBASiJnizmxlMbO2wm1laZMVAHwrRYkKKbpESbBo20nsO2dCTqjxFhoV9p1r+ZnN72G2toJRRIjwYHo8thbosTJXi0Sa8E46oU4TANlsNsyZMwe5ubmIiQld0pmdnY1169Zhx44deP/991FeXo6cnBzU19eHvGfevHmwWCzsn8rKypvxIxBCCADf6o/d5cYH/30vNj13H6422PG70b1bvI+Z1J6vV2PptlPoGiNFidGEjw9WYOEjfYPO4Zo/vg+b49MaOo0S8x5Ox5mLwVfCh6epkCiXYmBKLHrFR9HKD+m0OkVyjNPpxH/913/B6/Xi/fffD3ut/5Za//79kZ2djdTUVPzf//0fpk+fHvQeiUQCiUTSru9MCCHBBCt312mUeCZGiqQWVlKYban7eiqxarcRudeSoZdP7o/Kq1Z2Dpfd5YFEyIeh0oyLZlvYDs8KmQj/+n/D4PJ42dWob36oxivj+sBxrcSdQd2cyZ2kwwdATPBz/vx57N69O+zqTzAKhQL33HMPjMbAPW5CCLmVQpW7M9te0/XqoM0IZWIB5o/rg/gYCT55diiipUJsLdCDx/Pi2eE9fZVZOnXQXJ6CkZqQJfA5GhW+Pnsl6MyuKUNSb2gmGSGdTYcOgJjgp7S0FF9//TWUyuB73OE0NDSgrKwM//M//3MT3pAQQlqPyfsJpsRownR9TywYn4HlO04j41pXZ4fbg5Q4GY5VmvGrP18fVqrTKDFzhAajM7ri3Z2l0KbEBg10CovLUZiXBT7ASYTWaZRY9Ggmlm7nzuzKabbKQwEPuVPd1gCooaGBszJTXl6O7777DnFxcUhMTMQvf/lLHD16FNu2bYPb7calS5cAAHFxcRCLff+jHDVqFCZNmoSCggIAwIsvvogJEyYgNTUVVVVVeO211yAQCJCbm3vrf0BCCPHT0uR2p9uDS5YmvDIuAwu3nAhZCm91uNlAZ84YX5+zwuJyrMjVAgAnCLo3JRZNTg/u7RGHqX7bY5frbPjyxEVkJMkxJTuVPa7pEkVJzeSucFsDoMOHD2PEiBHs59mzZwMA8vLysHDhQnz++ecAgIEDB3Lu+/rrr/HAAw8AAMrKylBTc/3fqC5cuIDc3FyYTCZ06dIFer0e3377Lbp06XJzfxhCCGlBuMntMrEAamUkDp+/ij8XnQtZCv/s8J5webzszC+RgI+CkRp8fLACJ36y4LcP3oOZI7yIlAjgBSCXCHHwx6vo100Ou8sDqUiAy5YmJMoj8PZXP+CJISmcd5D6NVgk5E7G83q93rbe7HA4UF5ejl69et1RzQbr6uogl8thsVhuOOeIEEJCsVgdmLnRwEksZrw5uR/cHi/6dpej8moTpCIBjlbUBsze2jpTh+VfnuEESKPSu+ClMX2weNtJznG9RonFj/bF69tPYeeZK+zxnDQVXhiVhnqbCx8Wc4Ot4WkqLJ/cv8WEbEI6ohv5/d2mMnir1Yrp06dDJpMhMzOT7bMzc+ZMLF++vC2PJISQTs1idaCsugGGilqUXWmAxeoIuEYuE2PpxL7QNytXH5XeBYPVcfjq9GX8++RlSIR82Jxu3NdLiY+fHcrpslzf5IKhwsy5v0+SPCD4AYBiowmvbjmB9CQ553hRaQ3+tKsUlyxNAffsLa3B3E3Hgr4/IXeSNi3bzJs3D99//z2++eYbjBkzhj3+4IMPYuHChZg7d267vSAhhHR0wUrbg62kWKwOLN52CgNTYjHNLx8HAH6/7RSezE4NGIOh1yjxYd5gPPlXXwK0FwgYSKpNVgStAAN8QdA0nTrguH8H6uZouju5G7QpANq8eTM++eQTDB06FDwejz2emZmJsrKydns5Qgjp6JjS9iPna1EwUsPm5khFAuz54Qoe7pvABhI1DQ7sPF2NnaerAfhybvL1aozO7Ir0JHnQMRjFRhN4OIt8vRqGilrsP2eCoaKWHYsBXG+QGEqo8+Huo+nu5E7XpgDoypUriI+PDzje2NjICYgIIeROV9PgwJHztSGHmA5Vx7Gf7S43Vk8ZBKlIgGMXzBjQXYEPi88hIzEm7CpOkbEGzz3QCwOTFezKT77fqk64uV3hzoe7j6a7kztdm3KAsrKysH37dvYzE/R8+OGHGDZsWPu8GSGEdAJ1NmfYIaa/334KP5mbULDhKB5eUYwZHx1F/rpDOPLjVUhFfBgqzJCKBC2u4ri9Xs62l//1hkpzQF4RQ69RBp3rlaNRoro++BBVmu5O7gZtWgF6/fXXMXbsWJw6dQoulwt/+tOfcOrUKezbtw979uxp73ckhJAOK0YqQlZKLACwYyiYCq6PD1YgNzsVZqsTudmpmKbvyVZ2FRlN8MA318vr9UIeEX7FxeHycKrB/FdvTlVZsPjRvnhty0lOF+kcjRKvPZKJ1784zXmWTqNEwcg0dFdEYHiaisZdkLtSm8vgy8rKsHz5cnz//fdoaGjAoEGDMGfOHPTr16+93/GWozJ4QkhrWawOXK6zY1GzKqyR6V0wZ0wfLN12MqAD8zSdml3NWZOXBQGPh7goMd7ccQbFQUZW6DRKaFNi2S2yHI0S8x7ugwa7G9FSIVxuL1Z/U4pe8dFsDlJyXAR2na7GoORYXDBb0TVGymmCOKynEuouUbBYHTTugtwxbuT3d5ub9/Tq1Qt//etf23o7IYTcMZYEKUHPCFGaznxmkpiZrawX1x3Ch3mDwcNZziqOXqPE1GsBE+ALhmaMSMPlOjue33AU96bG4vkHemHPDzX48sRl9r41eVl4d2cpm2jdNUbKnquy2MD8m69cRgEPuTu1KQAaOXIk7r//frz22muc47W1tZg8eTJ2797dLi9HCCEdXU2Dg7PCw/BPamaCEP8KMVWUGIXF5exWVk2DA0/+9Vvk69WYquvBXuf1etEtNgLrpg1BhJgPrxf4+mw1/rznHKwON4pKa+DxejlVYYAvL4iZDRZs2Okz+sDSeELuJm0KgL755hscP34cBoMBH330ESIjIwH4OkNTDhAh5G4Sar4Xs7IjEwuCVojlaJQozBuMiquNqKhtChms5GiUWDKxLwQyEX7xzl42mFqZq+XkGzF5SAxmNhifxwvoT0Q5PoT8jC2wnTt34te//jWGDh2KrVu3okePHu34WoQQ0rExuTMtlZiHqhDzrRrxkK/vgfhoKSb0T8LS7ac4wYpOo8TzI9MAAI12Z8hgSqdRYkL/RMjEAjZR2upwY9ZGA76clQOXx0s5PoQ006YyeABITEzEnj170K9fPwwePBjffPNNO74WIYTcXuFGW1SZm1Cw0YBRb+/BFycuQRekBJ0pTdcmKwKCH0aRsQYeLzB13SHsOHkRY/smYE1eFlZPGYQ1eVnQpsQif90hvLL5BMRCQdhy+6XbTiO/2bZWVmosFDIResVHYWBKLHrFR1HwQ8g1bVoBYvr+SCQSbNiwAUuXLsWYMWMwZ86cdn05Qgi5HcKNtogUC9hzMrEAQj4Pc8emo7rODh6Px5a5n71Yh99P6gdjdUPY73K4fVtlfZPkmL7+cNBrSowmWB1uDOupDNsscaquB+d9aauLkNDaFAA1r5yfP38++vTpg7y8vHZ5KUIIuV2Y0RZFzSa2M0NClzzalw1+Vj2pRWFxOd7dWcpel5OmwucFeni9XnxXWYveCeFLcbtESQC0PM7iSoMdsRHhgxl5hAibZ9xHW12EtEKbAqDy8nKoVCrOscmTJ6N37944cuRIu7wYIYTcDjUNjoDgh7G3tAaNDhcA4NnhPbG2uDygb09RaQ1e+/wEtCmx+L6iFksn9WMTnJvTaZQQX8sVammchVjAh9XpDntNrEyMXvFRYa8hhPi0KQcoNTUVfH7grX379qVVIEJIpxaqqovRaPcFIXqNKmj5O+DbstImK1BkNGHJ1lP43ej0gDwhpiGi0+XB5hn3oacqEjlpqqDP010bZ3G0ojbkNTS+gpAb0+oVoMceewzr1q1DTEwMHnvssbDXfvrppz/7xQgh5HaIkYqC9u1hcnt4PF9A4nKHb6LPbGntPFON/x6a6ktovjYqQyLkw1BpxqyNBmx67j40OVzwAljyaF8s2Hw8ZOfo+3oqsfjRTLy25SSNryDkZ2p1ACSXy9nkZ7lcftNeiBBCbqdoqRCFUwdj5e7SgFLzwrzBEAt5mDe2D3gtPMd/S8vt9QZNXtZrlNh+/CIKi8uRr1dD10uJWaPuwcvjhHC6Pbja4MDhilrM2mjAoBQFZo5KA7zAylwtja8g5GdqdQC0du3aoP+ZEELuFFXmJpQYa/D5dz/BUGFGwUgNZxWo3NSIzKRoVNfbkRwbETa3x38CezdFBPQaJSdfiBlxMXfTsZCNEheMz0Q/twd/fSoL0VIh/rKnDL+f1I/GVxDSDtqUBN3U1ASv1wuZTAYAOH/+PD777DNkZGTgoYceatcXJISQW4Gp/pqmU+NIhTlkw8F7UzJRsOEAFk7IwMxrTQpLQmxZAb5AB/CNqpgzNh0NNjcUMhG2H7+IWRsNYRslLtl2Er8bk47/nLqMsxfrsPjRvhT4ENJO2jQN/qGHHsJjjz2G//f//h/MZjN69+4NsViMmpoavP3223juueduxrveMjQNnpC7T1l1AyasKkZh3mAUl9XAUFEbdHUnR6PCS2PSsevMZeg1SpRfaUTP+Ch4vYDD5cG+cyYUFpfD6nCzwdDHByvw8tg+qGl0IELER5PTg//6834AvqGlofr/AMAXs/SQCAW0zUVIK9zI7+82VYEdPXoUOTk5AIB//etfSEhIwPnz5/G3v/0NK1asaMsjCSHktqqzOZGvV8Pt9bbYvbm63oZDP15Fo92NwWol3v3qBzxVeBD7zvmqv1bmarF1pg6De8Rh1kYDdp6uhtXpxp92/YAJq0pQ71dp1lL/H4fLQx2cCbkJ2rQFZrVaER0dDQD4z3/+g8ceewx8Ph9Dhw7F+fPn2/UFCSHkVoiRiqBNVmD/OROyUmID8n+YKjCrww27y4MSowmPDkhClbkJU3Vq5GZzr9OmKKBNiWVnczXYXRiijkO+To24SDFyNCoUGWta7P8TLRXdih+fkLtOmwIgjUaDzZs3Y9KkSfj3v/+N3/72twCA6upq2jIihNwWzHDSOpsTMREiqCJbt2V0uc6G2kYH6u0uREmE+PhgBR7TdsNfi88F5P+syNVi1kYDJEI+ZGIBBibHYtG2kwE5QMx1+brrs7ncHi+cbi+mrz8MmViAwqmDAZ5vZlioZOoc6u1DyE3Tphygf/3rX3jyySfhdrsxatQo/Oc//wEALFu2DHv37sWXX37Z7i96K1EOECGdS0uzu+qanGhwuFF/LTiKlYnRNUaK86ZGvPzZcTb4KJw6GEcravFdRW1Ah2fAF9yM65eIKosNAPB9RW3QZog6jRLalFhkJMZgxkdHkaNR4t4ecRiTmQCb082Wrl+ut6PB5kSURIQl206hyMidBD9zZBr6JETT9hchrXQjv7/bFAABwKVLl3Dx4kUMGDCA7Qp98OBBxMTEID09HQBw4cIFJCUlBe0a3ZFRAERI52GxOlCw0RB0fMW4fgl48aHemL/lBGeFRa9R4veT+mH5l6fx5YnL7PE1eVmQigSY8uGBkN+3daYOv/rzt1iZqw2bvLwmLwsAUFhSjoIRabA53VBGitA/OZa9pqy6AT+aGjHzWjUYs+XGNEosLC7H1gI9jbcgpJVu5Pd3m7bAACAhIQEJCQmcY0OGDOF8zsjIwHfffYeePXu29WsIISSscLO7HhvUPSD4AYBiowmvfHYc03RqTgAk4PEg4IVvcXihtonNA2pJl2gJtCmxmL7+ELQpCrw+sR/nvCpKjB9NjbA63CGnvNe3MJqDENI2bQ6AWqONi0uEENJq4WZ3xcdIQlZzFRtNmDM2nXPM6nSjpbBGLPCtaMsjwicnx8dI8Ks/f8smQZcYTQFBk1wmRvfYiLDPoSRoQm6OzrU3RQghzcSECRAabOGnp1vtbqyeMgiFUwejYKQGMpEAxy6YkaMJPnA0J02FbooIrMnLgs3pDhhwyl6nUWLX6Wo2+GFcMFtRZW7iHEuIkWI4DTgl5JajAIgQ0qmposQhA4gYafhFbplEgBkfHUXBhqNIkksRHyPFUHUcXnskAzlBprc/P0IDsZCPmRsNmLnRgGk6ddAp73k6Nf6y91zA93m9wNxNx2CxOthjcpkYyyf3D/gZaMApITdXm5OgWyM6Ohrff/99p8sBoiRoQjqXKnMTXt1yAumJMWwisUImQpJcivmbTwSt6MrRKDF/fAbO1TQiOVaGYxfMWLr9NKwON2RiAeaP64N+3eW4UNsEseB6UvKHT2XB6nSzoy78k5fjoyUorW7Akm2nAlZ/mMqwVbuN2DX7/oDEZqaMnwacEtJ2N70TdGvxWkgm3Lt3LyZMmICkpCTweDxs3ryZc97r9eLVV19FYmIiIiIi8OCDD6K0tLTF733vvffQo0cPSKVSZGdn4+DBgz/nxyCEdHBJigi8Mq4Pvq+oxfT1hzHjo6N48q8H8MaOM1g6sV/Aak5OmgrPj0jDpNX78Nw/jmL8ymJsP34RK3K1kIkFsDrcePmzE1j+5RmcrKrD9PWHsWq3EVaHG+YmJ9aV+Ka3M8nLzHf+eU8ZcjQq3Jsay/k+ZiRGYXE5gOCJzXKZGL3iozAwJZY6PxNyC9zWJOjGxkYMGDAA+fn5eOyxxwLOv/nmm1ixYgXWr18PtVqNBQsWYPTo0Th16hSkUmnQZ37yySeYPXs2PvjgA2RnZ+Pdd9/F6NGjcfbsWcTHx7fLz0UI6Vgu19lw0WxDbnYqpul7st2Y9/xQg3ydDQ/3S8RUnZpdpfnhcj3y1x/irNIwydL5ejVbkVViNHGaGcrEAnSPjcA0nRpREiEGpcSy35WVGovFj/ZFoiICSx/tC+OVBk5J+6yNBvb7KLGZkNvvhgMgp9OJiIgIfPfdd+jbt2/Ya0+dOoWkpKSQ58eOHYuxY8cGPef1evHuu+9i/vz5ePTRRwEAf/vb39C1a1ds3rwZTzzxRND73n77bTzzzDOYNm0aAOCDDz7A9u3bUVhYiLlz57bmRySEdDDhujxXmZsw51/fcxoSMt2YT1ZZ8O6uUk4l2Jq8LLz82Ymg39M84AGuz+qSiQUozBuMP+w4w/muHI0S22fqEef3TgqZCOv3/Yi9QcrzKbGZkI7hhrfARCIRUlJS4HaHr64AgOTkZAgEgja9WHl5OS5duoQHH3yQPSaXy5GdnY39+/cHvcfhcODIkSOce/h8Ph588MGQ9wCA3W5HXV0d5w8h5NawWB0oq26AoaIWZVcaOAnCgC/AKdhowKi392DS6n0Y9cc9mLnRgCpzEyxWh68DdLMcnxKjCWtLyjGid3xAGXxL/Xuan2dmdS0Y1wfvfV0a8F1FRhNe/fwk5xglNhPS8bVpC+yVV17Byy+/jL///e+Ii4tr73cC4Os0DQBdu3blHO/atSt7rrmamhq43e6g95w5cybkdy1btgyLFi36mW9MCLlR4UZYJCkirgc4zVZS9pbWYO6mY1gwPiNkE8Rg/X+YLaw1eVlBh5wC4AwnzdGokCCX4qOnsyER8lEUYuWoqLQG1fV2TmCTpIjAylwtJTYT0kG1KQBatWoVjEYjkpKSkJqaisjISM75o0ePtsvL3Srz5s3D7Nmz2c91dXVITk6+jW9EyJ2vpeCGCR5CBTh7S2tgbgrfJdk/x0cmFmBFrhZv7jjDqQrzH16qTVHAUGkG4BuXsejRTFyus2HKhwewesqg8D9PkHeRyyjgIaSjalMANHHixHZ+jUDMmI3Lly8jMTGRPX758mUMHDgw6D0qlQoCgQCXL1/mHL98+XLA2A5/EokEEonk5780IaTVWgpumJyfUGRiAaIl4f8RJhUKkKNRochYg3y9GmtLygNWhpjPC8ZnIFsdB+OVBmydqYPXC+QVHsTvJ/nGV/ivDIV6H0JI59GmAOi1115r7/cIoFarkZCQgF27drEBT11dHQ4cOIDnnnsu6D1isRj33nsvdu3axQZpHo8Hu3btQkFBwU1/Z0JI64ULbgBfqXioLs/Mao6hohY6jTLodldOmgpxkSIUjNTAAy+0yYqQ87ZKjCb87qF0fHniIv7w7x/wr/83DE8VHoTV4YbT7csJMlSaQ36XTqNEpPimFtUSQtrZz/pf7JEjR3D69GkAQGZmJrRa7Q3d39DQAKPx+j+QysvL8d133yEuLg4pKSn4zW9+g6VLlyItLY0tg09KSuKsQI0aNQqTJk1iA5zZs2cjLy8PWVlZGDJkCN599100NjayVWGEkI4h3AgLAGzOzPA0VUA1Vb5ejXUl5ThaYcaKXN8/d/wDk5w0FRaMz8Dh87UY1lOJVx7ugwa7bztMJhZwmhcyeUCX621IT4iBTqPENz9cYbfPDJVm6DVKFBaXB/8ujRLPj0yDQkal7YR0Jm0KgKqrq/HEE0/gm2++gUKhAACYzWaMGDECH3/8Mbp06dKq5xw+fBgjRoxgPzN5OHl5eVi3bh1eeuklNDY24tlnn4XZbIZer8eOHTs4PYDKyspQU3P9H46/+tWvcOXKFbz66qu4dOkSBg4ciB07dgQkRhNCbq9QwQ1wvVScqaZ6bcsJ9Pbr8pyqlAEAjlb4+uvk69XIv9bnRyoSICVOhgtXrZBHiFBvc0EeIYKlycmuHK0tKeesBuk0SjzSPwlV5ibMHJmG/HWH2HNnLtZh6cR+WLDlBOe7AN/A0zMX69EjTka5PoR0Mm0ahfGrX/0K586dw9/+9jf06dMHgK/nT15eHjQaDTZu3NjuL3or0SgMQm6NKnMT5m46xgmCftEnHgsfyYTN6UGdzQlFhAgCPg+vfHY8oNfPNJ2a02CQCXDWl5Rzrh2epsLrk/qhyFiDbceqgm+ZaZRYMrEvYmViXKqz4UKtb2ipodKMjw9W4H8f6o1BKQo02n2jMgR8HgR8HpSRlOhMSEdxI7+/2xQAyeVy7Ny5E4MHD+YcP3jwIB566CGYzeYbfWSHQgEQIbfO5TobahsdqLO5IJcJESES+oKda0FRwUgNDBW1IXNvmPlaLV37iz7xeHF0b4x+tyjku/znN8PRNUaCgo2GoAnaw9NUWJmrpYCHkA7qRn5/t2kLzOPxQCQK3O8WiUTweMI3GSOE3L2Yjs6WJgdkEiF4AMxWB4qMJhQW++ZrNQ9gWkpe9u/cHO7ar05X49nhvcK+X53NCQGf12J1GgVAhHR+bQqARo4ciRdeeAEbN25kR1389NNP+O1vf4tRo0a16wsSQu4MwZoeMttYp6osWJGrhZDHCwhgbrRzczgSUcul7K2pTiOEdH5tboT4yCOPoEePHmzDwMrKSvTt2xf/+Mc/2vUFCSGdX6imh8xKjzYlFmtLyvHiQ70D7m2p/05yXARWTxkEiZAPZWTL/bxaKmWXCMNnBdAgU0LuDG0KgJKTk3H06FHs3LmTHTHRp08fzgwuQghhhGt6yGxjrdptxNyxvIDzhkozcjTKgBlcgC9o+ffJy5wcIL1GiWKjKaDcXSET4WqDA9P1avZ7/Z8z06+UvaXqNEJI59emJOg7HSVBE9I+mJwfU6MDDXYXZ+6Wf4AiEwvR5HQjSS5Fnc2BepsbPB4PNqcbESIBeihlWLL9FHafucI+O1wV2McHKvBEdkpA52edRomn9T3x/QUz+nWTQyYWIlIiwMmqOoy4pwsSFBEAglenMYNME69dQwjpeG56FRgAHDp0CF9//TWqq6sDEp/ffvvttjyyw6AAiJCfL1zOz9xNx7B8cv+AAOXB9Hj8bkw6lmw7yZnXlaNR4X9H94a50QGr043usRH4z6nL+PhgBZ4YksJpanj8JzMe7puIxVtPhlw1YirH1uRloZsiAolyaUBiMxO80SBTQjqPm14F9vrrr2P+/Pno3bs3unbtCh7v+rK1/38mhNydWsr5eeuXA1BlaUK+To0p2alsN2aRgIfF204G5OgUGWt84yz8AhemM3OwpoajMxKCBj/MO+Tr1NBplKiutyMrNTZoYEODTAm5s7UpAPrTn/6EwsJCTJ06tZ1fhxByJwiX82OoMCNFKcNfi88FbE+9Nj4Tf95zLuh9/iXvhkoz5o/rE3K46U/mphbfcebINOrgTMhdLHx5Raib+HzodLr2fhdCyB0iXCl5vl6N17acCBq4LNl2Evn66319ZGIBCkZqsCYvC6unDELXGCkKRmrw8cEK9OsuD1rN1RrdYiPQJyGazfkhhNx92rQC9Nvf/hbvvfce3n333XZ+HULInSDcoNNwzQqLjCZMvbbKE2puV06aCh8/OwxmqyPkd5yosmDZpL6Ij5FyBp4WFpcjKzUWiTGBOT+EkLtLmwKgF198EePGjUOvXr2QkZER0BX6008/bZeXI4R0PharA0I+DzlpqpDbYOEwaYT5enXQLa6i0hq89vkJzBmTHvR+mViAft3kWFtcHjA7rHDqYNr2IoQAaOMW2KxZs/D111/jnnvugVKphFwu5/whhNydqsxNKNhowNgVRVgwLgM6jZJzXqdRIj4mfLPCJEUERqV3gTZZEXKLq8RogsPlCXg+4Auc1jQLfph7Vn9tRIRYcIM/FSHkTtSmFaD169dj06ZNGDduXHu/DyGkk2pe+VVuaoQ2JRb5OjXsLg8kQj4MlWbsOl0dtrGh4bwZLzx4D9vbJ5QrDXZM0wU2NbyvpzLkFhvN8iKEMNoUAMXFxaFXr/BDBQkhdxf/yi+ZWABlpDhoICITC7B5hg6LmpW7+zc2/OTXQ2F3hp/xJRbwMXOjAfl6NfJ1asjEQlgdLohbGJ1Bs7wIIUAbt8AWLlyI1157DVartb3fhxDSSVisDpRVN8BQUYuyKw1we72QiQVs8vIPl+uDblFZHW5UmZugTYllq7vW5GVBmxLLdnWurrMjOc63FRaMTqOEodIMq8ONVbuNmL7+MKwOF9bv+xHyiPCzumiWFyEEaOMK0IoVK1BWVoauXbuiR48eAUnQR48ebZeXI4R0TMG6POekqbAiV4uTVRasLSmHocKMFblaANwtqhyNEsro4KtDjPgYKQ6cM2HRhEw43Sc4Iyn8V4r8j1XX2/Hm5P7ghUnAHp6mQpRUiLLqBtTZnIiJEEEVSQ0PCbkbtSkAmjhxYju/BiGkswjV5bmotAZerxcvjUnHO1+VAgBm+W1RMXlAXaIl2HW6OuxU9n+fvARDRS2G9lJiZa6WHUkRIRbgaIWZM/8rJ02FJY/2RaxMhEaHG69+dhx59/WAx+vlPH94mgpLJ/bFK58dx87T1Zzjyyf3RxL1BCLkrkLDUIOgWWCEhFZW3YBRb+8JeX7rTB0mrCxhPzefyp4SJ8OuM5evlar/iCJj8NUdq8ONHI0Kyyf3Q7dYGXtNqBldFqsDBRsNKCqtCZwEHyFCD1UkXt1yghP8MIanqbAyV0srQYR0cjd9Fhgh5O7BBBzMlhGT6xOqSqvJ4Ubh1ME4WlGLjw9WsENPOc0MNSqM7ZuARY9motHhQuXVJrZKzH91p8hYg/MmK6IkQjY4CTWjyz8Jm8kN8rfjhZygwQ9A1WGE3I3aFADx+fywQ0/d7vDlq4SQziFcro9/oOKv3ubC9PWHodMo8WHeYKzY9UPQ4aaLtp7CnDHpuFJvx4yPQucNmpucrQpOwo3f8J13hT1P1WGE3F3aFAB99tlnnM9OpxMGgwHr16/HokWL2uXFCCG3V0u5Pvl6dcAqC1OdBfgSn/k4iwEpCuw+cyXg+SVGEyyNzhZzbyRCfquCk3DjN3znw//jjqrDCLm7tCkAevTRRwOO/fKXv0RmZiY++eQTTJ8+/We/GCHk9go30b3YaMKMBzScAChYdVaRsQYvPJjG5uL4z+SyOtyod7hw7Iw5ZNUWE1BNGtitxfdVRYkxPE3FqRhjDE9TITYy/HlVFG1/EXI3aVMfoFCGDh2KXbt2tecjCSG3SbhhowAgEfGx4elsbHxmaEAfH3+WJiemrz+MGR8dRf66QzBU1GJFrhYysQASIR/vfV2G/32oN/RBxmZM06lx5mId3F4vyq40wBLmneQyMZZP7o/haSrO8eFpKrwxuT+6xkjDnqf8H0LuLu2WBN3U1IQVK1agW7eW/02NENKxWawOSEXhZ2ZFSoT4nzX7sDJXi+nrD7f62Uw+0Pxxfdhmhk+vP4R//b9h+Mlsg6XJySZEbzxwHrnZqZj4XgmsDneLJetJighO2bx/lVhrzhNC7h5tCoBiY2M5SdBerxf19fWQyWT4xz/+0W4vRwi5cc2rttrS6M9sdeL7C+aQvXpy0lQwVJiRr1fDUBn6Ov+cIH8lRhPmje2D6vrLWJOXBQCotTphc7ohFQkgFPAwrKdvRch/VWlvaQ3mbjoWtmQ9VJVYa88TQu4ObQqA3n33XbjdbggEvn9D5PP56NKlC7Kzs1FfX9+uL0gIab1gVVs30uiPCZ5sLjeWbj8dtJOzTqPEokcyMX5lMVbmajFzoyFkx+e8azlBzfvySEUCCPg8HLtgxrs7SznPnqZTw+UGnlp3MOg7Usk6IaQ9tCkAys/Px8WLFxEfH885bjKZoFarqQyekNsgVNUWs2ryh8cHoMHmCrky5B88ffzMUFgd7qCdnA2VZtQ02NlVGf/r5oxJx4XaJrbj8xN/+RYAsCJXG7QXUJ6uB749d5V9FhNA/Xp4+GHLVLJOCPm52hQAeb3eoH2AGhoaIJVKf/ZLEUJuXLiqrcPna2FqsOOixQa7y4NaqxMHy6/igXu6IFERERA8CQW+/30HaygIAA/c4xtSGh8jgV6jRLHRhFW7jdAmK9iePgUjNdCmKKBNicXakvKgvYAALz5+digu1DZxKsRiI2mgKSHk5rqhAGj27NkAAB6PhwULFkAmu96e3u1248CBAxg4cGC7viAhpHVCNQJkprMv++I0ipptZalVkZCJBQHB04FyE5Y91g/x0ZKA8vV7U2JRbKxBjkaJXaerMTAlFs89oIHb60VshJgtaS8sLseKXC0iRIKQg0+LjCZM9WuEqNMosSJXC48HIfOKqGSdENIebigAMhh8/T28Xi+OHz8Osfj6P4TEYjEGDBiAF198sX3fkBDSKqEaAebr1UFXYJjPr0/sxwmeZGIB+iTGYG1xeUDAVJiXBbvLg7/vP4/fjUnH1QYHrE43XG4PUlUywAPMG5sOr/c0io0mzNpowAf/fW/Y97a7PAHvNG9sOmaOTAOfxwvIZ6KSdUJIe7ihAOjrr78GAEybNg1/+tOfbsmg0B49euD8+fMBx2fMmIH33nsv4Pi6deswbdo0zjGJRAKbzXbT3pGQjiBUI0BtsiLkCkyJ0YRGh4sTPOXr1VhTHDxg4vN4eHV8H8x7uA+q622wXqvaOnS+Fn/f/yOm5/TES/86hvemDMJzNhcsTc4Wt7MkQm47shKjCUIBH30SZFhFJeuEkJukTTlAa9eube/3COnQoUOcpOoTJ07gF7/4BR5//PGQ98TExODs2bPs53Bzywi5UzCNAOduOha023EoVocb3RQRbPAULmAqKq2B2wss3HoioDJsmk6NNUW+bS9TgwMerxcykQAutxc5GhVn6rv/fcHK5G0ON2f4KSGEtLcOPw2+S5cunM/Lly9Hr169cP/994e8h8fjISEh4Wa/GiEdTvNGf5ESITxeb9h7IiVC2FwevDG5P+ZsOsbZkgrmp9qmkNtp2pRYXG10sMNQp+nUeOZvh7F8cn+AB852VrDRGQxKciaE3GwdPgDy53A48I9//AOzZ88Ou6rT0NCA1NRUeDweDBo0CK+//joyMzNDXm+322G329nPdXV17frehNxKTKM/pqz9pdHpYRsVbj9+Ed9V1OL3E/vhrccHwNQYfgRGKCVGE1suz3zmA/jvoamYtdGAT5+7Dz+Zm2B3eRAfLcEPl+uDjs6gJGdCyK3QrrPAbrbNmzfDbDZj6tSpIa/p3bs3CgsLsWXLFvzjH/+Ax+PBfffdhwsXLoS8Z9myZZDL5eyf5OTkm/D2hNw6/mXtVZYmTNerkdNs1laORonpejUKi8tRbDThlc3H8aOpEXyer0dPMDkhtqwYIiEfyXERWD1lEAqnDsaAlFj8IiMeQ3vGwQuwM8GeKjyI+BgptCkKzv2U5EwIuVV4Xm8L6+MdyOjRoyEWi7F169ZW3+N0OtGnTx/k5uZiyZIlQa8JtgKUnJwMi8VySxK9CWkvTCfnq1YH6m0uHK2oRXaPOChkYrg9XticbkRKBPACOHOxDl1jpPjughl9k+SwuzxQqyLBgxc8Hh+Lt50MyPN5bUImO5crmI+ezsaUDw9w7xmfCYfbDZlYiAVbrucO+XeHBoBuiggkyqUU/BBC2qyurg5yubxVv787zRbY+fPnsXPnTnz66ac3dJ9IJIJWq4XRGDypE/BViUkkkp/7ioTcdOHmfAUbgzEyvQsmD+qG+ZuDJy3/ff95jOwTj5nXOjkzFVndYiMwd0w6+HygweaGTCJEdZ0NX526BG2KIuh2ml6jxP5zgblBS7adwssPp0PI42GaTs0eZ5osMu8iFvIp+CGE3DKdJgBau3Yt4uPjMW7cuBu6z+124/jx43j44Ydv0psRcmuEm/MVKRYEHYORkSTHq82CH4CbtJwkjwgxquL6LC+rww2dRomn9T3RJzGG8wzANxw1774eQROai4w18ACQy0T45GAFtCmxAaM1PjlYgbceH/Cz/44IIaS1OkUA5PF4sHbtWuTl5UEo5L7yU089hW7dumHZsmUAgMWLF2Po0KHQaDQwm834wx/+gPPnz+Ppp5++Ha9OSLsIN+drzqZjWPxIJgYkK3DkfC1ne6qlHkD5OjXkMhHe+s/ZIKMqTPDA1xdo1W4jm9Q8tJcS2pRYPP+ABiIhH1IRHyIBH4+t3hdya6zpWln7okf7Yu6mY5x3orwfQsjt0CkCoJ07d6KiogL5+fkB5yoqKsDnX8/lrq2txTPPPINLly4hNjYW9957L/bt24eMjIxb+cqEtBuL1YGLFlvIOV9FpTU4V9MIQ0UtVuRqOZVVLZW0210eCAW8oFtawPUgiXGkwowlj/aFF4DV6Ua9zQWHywtJC/8kkUf4ytqbl+lTc0NCyO3SKQKghx56CKFytb/55hvO53feeQfvvPPOLXgrQm4+Ztvrv4em+oaLJisCZnNZHW7YXR42iGFWbIDALsvNKSJEaLQFX7VhiIR8yMQCAMB7Tw7CpTobVn5tDNgCWzt1MKatOxSwCpSTpkJ89PUcO6ZMnxBCbqdOVQZPyN2E2fY6cr4WamUkDBW1bBl5/rpD7IqPTCxgA50SowmjMxNQMFIDmVgAQ6U5oPydkaNRoUtMy8n/Ah4PK3K1+PX9PXHR0hQQ/AC+VahVXxuxYFwfzvHhaSq8SdtbhJAOqFOsABFyJwhXwRUMM6G9YKQmoCQduJ6EPH9cH05vnsqrVjY42nz0AhZP7Bu0CixP1wPLvjiN3zx4D/QaJYpDNErcf84EQ0Ut5oxJx5V6e8jtsqLSGrwwKg0bns6GRMSHIkJM21uEkA6LAiBCboFwFVxJioig9zAT2kMlMsvEAmhTYjEwJRaxpkYUTh2MoxW1iBYLoU2JhUwkwP8M6wGb0405Y9LRYHPB3ORkK6/8c4VeHJ0OHu9syFEVVocbAh6vxZwiAMhMiqGghxDS4VEARMhNFq6Ca+6mY1iZqw0aMDAT2oMFHTKxAO89OQgXLU24aG4CkyLXTS5Ft7gInNpv4QRNzRsU+tt95gqeGtoDL4/tg6r7mtjy9BNVFpz4yYKVuVrfO/CA7rERkIkFIau9Yim/hxDSSVAARMhNxmxlBbO3tAY1DY6gQYMqSozhaSpIRYKAc7++vyekIj62H78YsLXVQxWJAckK7D5zhT1uaXKGfUer0w2X14Pp6w8D8AVYTG+gd3eWstflaJRYk5eF6esP0wwvQkinRgEQITcZs5UVSn2I83KZGG9M7g9zkxOj0rugT5KcrQK7p2s0Xvs8dIPDOWPS8c5X1wOXlqrB5BEiVNfZ2aGp+Xo11paUB+0NBPAwf1wfvPzZCfZ4DvXyIYR0MhQAEXKTMVtZoUSHOS8TC7B02ym8NKYPFm87yW5rfV6gC9u7pzlDpTnkRHi9RoloqRAvfGzA8sn9AYRvoFhkrMG8h/vg8wId7E4PFDIR4qMlFPwQQjoVKoMn5CZjtrKCGZ6mQpRUiHNXGvDD5XqcuVSHo+evouxKAy7X2XCpzgZ1fFRAFZjVHr53T/PtqcLickzTqQOmvOdoVFj8aF+8/40RNQ0OzNpogDYlFlEtdDb80dSIR1aVIC5SjLSu0RT8EEI6HVoBIuQmk8vEWD65P+ZuOoa9zarAlk7si8VbT2LSoO4BW056jRILxmcgKyU2YDVGKOCF/U4hn3ve6nBjw4HzePWRDDTa3DA12gH4Vob+68/78cSQFKzJSwYAKCMlcHnCV3tJhHzK+SGEdGoUABFyCwQbARElFeKVz44jPTEmaL5NsdGEpdtOY/ZD9wQ8r9hYgxyNCkXGwOTqnDQVzl1p4BzTaZR4YdQ9WPbFaUzJTmWTnRn+AdaavKywW2Y6jRLV9XbK+SGEdGoUABFyizQfAVFW3YCdp6uROyQlbL7N3LHpAcf/svccVj2pBeC9lpjsk6NRYrpeje8vmPHR09kQCXiot7lgqDSjttGB3Weu4Jf3+lZ6ZGIB8vXqgPEaLo8XhcXlWJGrBRA49X3Jo30RKxNR8EMI6dQoACLkNmGqw1pqLtjocAd0arY63CjYYMCCcRl44cF7UF1vh1Qk8M3M8wJp8dGwuzyIj4nAX/acw84z1Vg9ZRAA3/aVf5m7f/Cl0yjxSP8kAMCsjQbk69XI16nZ3kCaLlFIVUW2918FIYTcchQAEXKbMNVhLZWoWx0uX6dmnOVseWlTFBiUqsCk1fsAgA1oSpqtCC2e2BceeNnvMVSaMX9cn6DbbiVGE5ZsO8kOVPUPjoanqbDy2qoQIYR0dlQFRshtwlSHMfk2weg0Shw+X4sn//otBqQo8NHT2fjb9CHYOlMHbUosLpptsDrcYfv2vLr5JKZkp6JLtAQ5GiUKi8vRr7s89Ewvown39eS+z3Dq80MIucPQChAhtwlTHfbalhOYplMDQEAV2FS/WVyGiloMTFZg1kYDfn1/T3RTRCBKKsSavCx0jZECAAwV5oAS+CJjDf7fA73wxF++xYpcLTwox4XaprDvJhUJsGv2/WzCNg01JYTcaSgAIuQ2SlJEYOEjmai8asWLD/XG3LE81FqdEPP5SJBLcKnOhrceH8AOMJ276RieHd4TD6Z3xaU6G+quJTgXFpdDm6LAilwtZ8gpQ8DnYVCKgs3r6R4bfAArQx4hQq/4qJv5oxNCyG1FARAht5DF6kBNgwN1NidiIkSIkgjx2ucnsa/MN34iKyUWcpkIQgEfP5ltiIsU49yVRizdfhqAL89nfbP5XDqNkg18gHI2f8efQibCH/9rIOqanKi4aoXX68sPKgqyDUb9fQghdwMKgAi5RarMTQFT4XPSVJim64Ep2an4+7c/YmCyAm/952xAIvPmGTo4XB68seN0QNDCXMskKEeKhRiUEoujFbUoLC7HvamxSIyRQi4To2uMFJESIV7bcgJ5OjU84G67Ua4PIeRuwfN6vd7b/RIdTV1dHeRyOSwWC2JiYm7365A7wOU6G8qqG2BucrL9dgqLy2F1uJGjUeL5kRoI+XxYmpzg8Xic84BvZMUr4/tgzLtFIb/jo6ezMeXDA+xnnUaJghEaCPg89G42rsJidcDU6IDb44Xb44XV4YY8gnJ9CCGd2438/qYVIEJusipzE+b863vOyo3/tlWR0YTnHtDgl3/Zz57PSVNh47NDMX3dIdQ0OFBkrEFdkyvs91iauFPlS4wm8AHc2yMOykjusNLmTRkJIeRuQ2XwhNxEFqvDt+0VZNtqbYkvXwcAzM2Cl6LSGry14yzWTh0CmVgAAOz/DSVYP6Eiown9uslRb3MGuYMQQu5eFAARcpNYrA5ctNg4OT/+SowmaJMVAEIFLzXg84Bf398TACAV8cP2CzJUmoOes7s8iL7WdJEQQogPbYER0k6YvBqXxwuPxwtTowMCfvip7XaXJ2zwcqnOhrGZifi+0oxGuwvTdGrwweN0hM5JUyHvvh7XqsACKa7l9hBCCLmOAiBC2kGVuQmvbjmBJ4akcDoyr8nLCnufIkKEaTo15m46hoKRmoDBpAIeD0u2ncLvxvSG1e7CrI0GfPR0Nl4a2xuVV5vYlaOPDpwP6P0D+JoppipllO9DCCHNUABEyM/E5PkMSFZgbUk5DBVmNpgRCfjY8Ew29pWZOFVdgG/lJjk2ApfqmvDR09lYuu0Up3+PXqPEg3264khFLRrtLqTEyZCVGourjQ7YXR7M+OgoALCDTe0uT8Dk9mWT+qFbrOzW/WUQQkgnQWXwQVAZPLkRZdUNGPX2HqzJy8LMjQaselKLwuJyzvT25mMtdBolpunU2HjgPH7z4D14Y8cZzvUMnUYJbUosRvaOx6DUWPxUa8WVBgfsTjcaHW62XB4A8vVqdgWppyoSiXIprfwQQu4qVAZPyC1Ud63Cyu7y4NnhPbG2WfADAMVGE3jg4aOns3G10QFDpZkNhqbrewYNfgBfonS+To1oqRBV5ibM/fQ4J6nav5yeWT1iprZT8EMIIaFRAETIzxRzrcJKIuRDr1FxxlT4KzLWYKquB6avP8w53rwEHvBtazErOpFiITxeL/b8cAVHztdyrmO2vJjxF9TJmRBCWocCIEJagVPh5fXCandBLhNDFSmGKkqM4WkqGCrNyNGowj7H7vIEHGteAs/k9KwtKefkBPmv9vjnEpUYTXjl4T6YNLAbdXImhJBWogCIkBaEqvACfNtNSyf2RcFIDT7YU4axmQlhnxWs3w8TODGl7fl6dcD3AIGrPf4cLg8ykuRt+vkIIeRuRI0QyV3DYnWgrLoBhopalF1pgMXqaPG60sv12HP2Cvp2kwcNSvaW1uDlz46jwe7CjAc0kIoEIZsV6kP0+zlVZcH/ju7N3qdNVgR8D8O/eaI/anRICCE3psMHQAsXLgSPx+P8SU9PD3vPP//5T6Snp0MqlaJfv3744osvbtHbko6qytyEgo0GjHp7Dyat3odRf9yDmRsNqDI3hb3uF+/sxbbjVRjVJz5kUFJsNEEiFOCXH+zHtuNVKBihCQiCdBolFj6SiTNVFs7xnDQVnsnphafXH4I2JRZr8rIgE4dfmG2+jTY8TUWNDgkh5AZ1ii2wzMxM7Ny5k/0sFIZ+7X379iE3NxfLli3D+PHjsWHDBkycOBFHjx5F3759b8Xrkg6GncfVbCTF3tIazN10jK2YCnVdidGE6jp72O9osLtQMFKDft0UEPB4eOXhPrA63LjSYIdYwMflOhuqam3o212B3OxU2F0eSIR8JMmlEAr46JMQzW5rtdQ80X8bjZKeCSGkbTpFACQUCpGQED63gvGnP/0JY8aMwe9+9zsAwJIlS/DVV19h1apV+OCDD27ma5IOqqbBEXIe197SGtQ0OCCXicNeF44qSoy0+Cj8Y/+PnNycnDQVXpuQiQtXraiy2LB0++mAbs3//k0O3txxBvf2iMNLY9NRXWdHl2gJcjTKgAGqzDN7dYnE5hn3IVoqoqRnQghpo04RAJWWliIpKQlSqRTDhg3DsmXLkJKSEvTa/fv3Y/bs2Zxjo0ePxubNm0M+3263w26//m/4dXV17fLepGOoa2ESuqXJibLqBpgag+cEAUyicmBQIhML8Pf8bCzYciJgi6yotAaLPj+Bsf0SA5KWAd/qTUKMFG89PgBmqxPzNx9HkdHEVoF5AM4zdRolZjygAR88DEyJbcVPTgghJJQOnwOUnZ2NdevWYceOHXj//fdRXl6OnJwc1NfXB73+0qVL6Nq1K+dY165dcenSpZDfsWzZMsjlcvZPcnJyu/4M5PaKaSFBWCLk4+zlekSIBQHnZGIBCkZqkJUSi9ce6RtQ5r5gXB/UWh0h84OKjCb06y4PyAnK8du6ksvEcHm8bHBldbgxa6OBzQlaPWUQts7UQZsSi+nrD6HB4bqRH58QQkgQHX4FaOzYsex/7t+/P7Kzs5Gamor/+7//w/Tp09vlO+bNm8dZNaqrq6Mg6A7C9OnZG2R7S69R4suTl7BqtxEFIzXQa5RsV+bm/XiY5oTPPdALIiEfTrcHYgEf1fXh84Mu1DZBmxJ7raOzCDERQiTGcMdU1DarSLM63JxVo9VTBrGfgw09JYQQcmM6/ApQcwqFAvfccw+MxsAtBQBISEjA5cuXOccuX74cNodIIpEgJiaG84fcOeQyMZZP7o/hadzVG2Y+FzNLq7C4HFN1auivrdY8O7wn1vmVvjNByZMfHsCKnaXYV2ZCdb09aG8ff2IBH6t2GzF9/WF4vV7Eyrh5OxarA44gDRL9+X+HPIJK3gkh5OfqdAFQQ0MDysrKkJiYGPT8sGHDsGvXLs6xr776CsOGDbsVr0c6qCRFBFbmarFr9v3YPOM+7HghBwNTYjldlZmtp4Epsdg+S4cxmQkhZ3QVGWugTVZAIuTDUGkO2fsnR6Pi9P5psLvwu39+zym/r2lwYN85U8hn6Pz6B+WkqRAfLWnD3wAhhBB/HT4AevHFF7Fnzx78+OOP2LdvHyZNmgSBQIDc3FwAwFNPPYV58+ax17/wwgvYsWMH/vjHP+LMmTNYuHAhDh8+jIKCgtv1I5AOQi4To1d8FAamxKLJ6VvNab6dxKzyOFxe/NSsR1BzdpcHhkozTlVZME2nDghg9BolXhzdm11hYgIZpvyeacRYZ3OisLg86DOYqfGFxeUYnqbCm1TyTggh7aLD5wBduHABubm5MJlM6NKlC/R6Pb799lt06dIFAFBRUQE+/3ocd99992HDhg2YP38+Xn75ZaSlpWHz5s3UA4hwhEuMlokFiJGKIBTwwj5DESFCYXE5VuRq8fGB82yej93lgTxChGipEPnrDsHqcLOBzKyNBgDc8vsYqYhdfcrXq5GvU8Ph9qBLlARiIR8utwdbC/RU8k4IIe2I5/V6vbf7JTqauro6yOVyWCwWyge6Q1msDszcaAhIjJaJBb7Kq6+NGJASC0NFbdAKrxyNCr8b0xtv7DgDQ4UZHz87FDUNDggFPMTJxBAL+XC7PSg3WdltssLics6K06fP3YdBqbEh3wXwlcozjRoJIYSEdyO/vzv8ChAhN4NcJsbrk/ph7qfHOHk+88f1weqvjSgymnCkwowVuVoAgf14Fj6SiaraJswflwGvF2i0O+HxevHnPefYa9fkZWHGR0dDvoPsWtk9k6Q9d9MxThBEXZ4JIeTmoRWgIGgFqHOxWB2oaXCgzuZETIQIqsjWbRWVX2nAuZpGxMdI0GBzI0oqBODFhJUl7DVM6bs2WQG7y4PkuAgcv2DBlQY73vmqFGvysiCPECFOJsaCz7nNEAtGakKuIOk0SiyckIm0rtEBP0e9zUldngkhpA1oBYjcNarMTQHzu4anqfD6pH5wuD2wNIUOivh8HqQiASqvNkEqEuBAuQlDesRxrmnej2dNXhbiY6RYuv00m9SckRgDmVgYEOgw+UFA4ArSNJ0aAj43x0guo4CHEEJuFQqASKcVdsjpp8cwMCWWDV6Y7SSZWICaBgdqrQ443B7sP2dic3NyNCr8ok/XgFUfqUiAoxW1KCwuR3yMBNPWHoI2RcEmNf/1qSyYGgObIfonNs8Zk44LtU1sPtAnByvw1uMDbsnfEyGEkEC0BRYEbYF1DmXVDRj19p6Q5//1/4bB0uSE3eVBhEiABLkUf91ThnEDkthtr5gIIcRCPvLXHkJlbRPenNwPKXEyrPzaGLBqUzBCgwtXrRiQHIudZy7B4fJiSI84iIV8REqEGPunopDvsiYvC9PXHwZwPRhLVES0318GIYQQ2gIjd4fWDDllgg7A15dnycS+WLLtFHafucI5/vfp2ai8aoXL48F7zYIfwLeFxQcP9/aIxebvT2LOmHS8seMM3t1ZCgABYzT8DU9TQdMliia4E0JIB9LhGyESEkpLQ06bKzaasGDzCWQkyQOOz998HA63B2KhIGDiO6PIWIN+3eQoMZrQYHNxgqTmYzQYzGpPqioSA1Ni0Ss+ioIfQgjpAGgFiHRa4Yac+o+P8FdsNGGaTh30+Jyx6ai82nL3ZwAwN3FXn/zzfeaPy4DN6abVHkII6cBoBYh0Wkz/nJxmQ05z/MZHBGMPMXi0weZucbApcz7YdUzFmM3pptUeQgjp4GgFiHRqkWIBHu6XiKn39WArtroppJi0el/AnC9GqCAnSipASVkNdBplyN49hkpzwIDT5qJvcGuOEELIrUcrQKRTq2lwYN6nxzF9/WG8+M/vwQPg8XgxKEUR9Hp9iK0xvUaJ6jo7O5Q02KrSdL0ap6oseHF0b5yqsoR8vq+hIiGEkI6M/klNOh3/zs9SER9r8rIg4PEgl4lw5mId/v7tj5iqU8MLbgNCvUaJpZP6YcnWk5zn6TVKvDohE0/+9VtYHW58fKACz4/oxa4qSYR8VNfb0VMZiQHJCkxffwjLJ/eH3eXhPD9Ho0SeTo1Gu+tW/VUQQghpI+oDFAT1Aeo4/IOdaKkQYj4fJWU1iI+Rsv19IsR8REuFqLe5ESkRYsLK4oBmhkwDwnH9ElBvcyFSIkSj3YVoqQgRIgFqrXZcqrNDESGCIkKM/yk8gJoGB+ddctJUGJCswKrdxqDP7xItwRN/+RYbns7GwJTY2/Q3Rgghdy/qA0TuCM3HXPz2F2kY0iMO245fDFjZmXqtK/M7vxqIgpEaNjDh8Xg4dbGO7fZ8f1oX1Nlc+GBPGQYkKzA2MxELNh/nlL7rNEosn9wfszYaOHlERaU1eO7+Xli12xgwIkOnUUKbEgurw005QIQQ0glQAEQ6pGBjLkb0jscbO84EJCgXG03wAvhgyiCkqiIRJRHC0uRkR1icqrJgRa4WszYaECUV4v09RjyZnYrqOhsWbTsZtOkhAOTr1ZwgBwBEQt+WG4/HY8dj+I/FGJ6mgiqKKr8IIaSjowCI3BYtTXCvaXAEzPgCELQ6CwAMFWZ0i5Ph5c+OBx08uuHAeSwY1wcSIR8ZSXKsLSlHvk4d8nklRhPyg/QLqvPrLp2jUWHzDB2+PHkRszYakJUaizcm96fSd0II6QQoACK3XKgJ7ssn90fStflYwcZcWO3ukINKhXweFm45EXI1R5sSC21qLK42OqC9lsczJTs17Hs27xfUvLlikbEGS7afwqvjMzC+XxI1PSSEkE6EyuDJLRV2gvumY7BYfYnHwcZciIU8rMjVwlBRi+nrD2PGR0eRv+4QDBW1GNUnPuQIC0OFGQ9ldIXT7YHHC8RHS1AwUgOZSBD2Xf37BelCNFcsKq0Bn8ejpoeEENLJ0AoQuaVCbW3JxAL0T1bgosWGczWNiJIIseyxfliy7RSbiGxucmJtSXnQVZ7qOnvQ75OJBViRq8UfdpwJSHR+sE9XjEzvwhmMysjRKJEol+LT5+6DVMTHFycuBSRFM+pbGMpKCCGk46EAiNxS/ltbzHZWVkosEhVSLN12ipN0nJOmQuHUwchfd+ha4MELmbMTSr5eHTJoAs5gzpj0wH4+aSo8P0KDOJkYCYoIlFU3BCRD+6OqL0II6XwoACK3FLO1xazMrC3xbSkZimsDgpSi0hrA68X2mXpcaXDA4wndsso3okIZsA3G5PsEU2I0oabBAW1KLJvwnBAjRbRUCHmEiN3SCjd0laq+CCGkc6IcIHJLMcGE/8rMoJTYkCs7py/Vw+sFoqVCRIcZMVFYXI5XJ2RCp1He0PvIxAJkJPqaZRkqzXj8z/thd3k4+TzM0NXhzcZjDE9TUdUXIYR0UrQCRG4pJpj4saYRq3YboYoSI0oS/L+GqigxPnp6KBZ87qvuKhipCTmoVJuigN3lxqJHMmF3emB1uBElFaKlPueNdhdmfHQ04FhzSYoIrMzVoqbBgXqbE9FSEVV9EUJIJ0YBELnlkhQRuGRpgkwsQOHUwai3BZ+d9cbk/ljs16iwsLgcK3K1ABAwg2vBhEws//I0vj13ld1aayloytH4VnRkYgEnuTlUTo9cRgEPIYTcKSgAIreFPEKMfL0a9TYX9p8zBQ1S4mMknGNWhxuzNhqQr1cjX6dGtFSEepsTkRIh3vzyNHafuYKCkRpO0nOooEmnUSJP1wMfHTjPdom2OtyU00MIIXcJCoDITWWxOmC2OtHocKHR4YYiQoT4aAlUUWLc11MJc5MzZJDSaAssOfefwbXxmaGYvv4w1uRlYee1UvbmSc9M0LQyV4sZD2hgaXKyg1GZoMfu8iBfr8axSjPl9BBCyF2CpsEHQdPg28dFcxPOX7Vi5e7SgDLzNyf3x0VLE4QCPq7U2+FwexAfLYVIwMNFiw0SAR/JcTL8aGrkdHxmhpoCwJcv6OF0eyHg8VBvd0Ek4EPI5yH3r98G9OtZk5fFjrAIZscLOUiUSyn4IYSQToymwZPbzmJ14JsfrmDbsaqAra0j52tRbKxBv+5y/FTbBB6Phx8u1+PspXoM7hEHeYQIURIhDpabsGT7aTaY0WmU7HbVsJ5xEAn4WLr9ZEBwtepJLQo2cJsWNh9r0ZzN6abghxBC7iIUAJGboqbBgfhobg6PTCzAr+/vibF9E7Fk60n87l/H2ONr8rKw+msj3t1Zyl7vH/BYHW72WQvG9cGwXiq8svl4yN5BzSe5+4+1CIaaGRJCyN2F+gCRm6LO5uSsujCNDxNjpFiy9SSnYWG+Xo1VXxsDmhiWGE2+qe16NeeYNiUWP5oaQ/YOKjKaMKwntx9Qdb0dOc36+DAo8ZkQQu4+tAJEbgpVpBgSkQAbnxnqa2DoBX64XIe+3RR4adNxzrUtdWtmujQzzE3OoDO5/EmEfHz12+FotLvYnj3339MFczcd43R0pmaGhBByd6IAiLS7ClMj5n12vFmvHhWeH9GLMwuM0VJ+TvPz0VJh0GaF/qIkQqR1jeYck8tAzQwJIYQA6ARbYMuWLcPgwYMRHR2N+Ph4TJw4EWfPng17z7p168Dj8Th/pFLpLXrju9vlOltA8AMARcYarPzaiJgg4yxays/xP6/TKHHJYsPlOlvIsRc5GiViI4MHNXKZGL3iozAwJRa94qMo+CGEkLtUhw+A9uzZg+effx7ffvstvvrqKzidTjz00ENobGwMe19MTAwuXrzI/jl//vwteuO7j8XqQFl1AwwVtbja6AiZm1NiNEEs5AcELoZKc8hgRqdRwlBpBuBbRSoYkYY5m44hUR6BghGagPtyNCr8flI/dI2hgJcQQkhoHX4LbMeOHZzP69atQ3x8PI4cOYLhw4eHvI/H4yEhIaFV32G322G329nPdXV1bXvZTspidaCmwYE6mxMxESKoIlu/LVRlbsKcTcd81VcAVk8ZFPb6y3U2vPJwHyz74gyKjL57CovLsSYvC3wej30O4AtmXp2QgVqrA9pkBY7/ZMHBH014Y3J/8AAoo8R4dXwGHG4PbE4PYqRCKGRiCn4IIYS0qMMHQM1ZLBYAQFxcXNjrGhoakJqaCo/Hg0GDBuH1119HZmZm0GuXLVuGRYsWtfu7dgbNAxjAlxi8fHJ/JCkiwt5rsTow51/HcKSiFgUjNdAmK9AlWhL0WplYgHy9GrGRElRbbHhpTDpecLlxpcGO5FgZAC8m9E/E1Pt6wO7yQCLk43KdDRdqm+Bwe/Drvx8JeKZ/c0O9Rok3Jven4IcQQkirdKpO0B6PB4888gjMZjOKi4tDXrd//36Ulpaif//+sFgseOutt7B3716cPHkS3bt3D7g+2ApQcnLyHd8J2mJ1oGCjgRP8MIanqbAyVxt2JejspTpMWr0vYPiooaI2oP+P/zUMnUaJaTo1ukZLsXzH6aBbZzqNEnPGpOORVSUB51ZPGcSZ5L7h6WxkJsVQXg8hhNyl7thO0M8//zxOnDgRNvgBgGHDhmHYsGHs5/vuuw99+vTBn//8ZyxZsiTgeolEAokk+MrFnaymwRE0+AGAvaU1qGlwhAwmLFYHfqptQr5eHTB8dNWTWvDBw5GKWuTr1Xjgni6wNDkxXd8T2pRYdpwFc8/cselh84YcIarEmidPm5ucYd+ZEEIIYXSaAKigoADbtm3D3r17g67ihCMSiaDVamE0Bu81c7cKVpLurz7M+ZpGO1KUMnSJkSAjMQbT9T3ZWV3Hf7JgwoBELBifgSXbTnJ6/ATr7txoD9/T50qDPeCYf3I0QyLkh31nQgghhNHhAyCv14uZM2fis88+wzfffAO1Wt3yTc243W4cP34cDz/88E14w84rpoXxD/7jIfwTpeURIvB5PLy65QSnezMT3Ah5PByuqMWW7wPngDGf/UdVyMSCG3pPZuts1kYD55ih0oxJA7uFfRYhhBACdIIA6Pnnn8eGDRuwZcsWREdH49KlSwAAuVyOiAhfku5TTz2Fbt26YdmyZQCAxYsXY+jQodBoNDCbzfjDH/6A8+fP4+mnn75tP0dHpIoSY3iaitMZmeE/HqJ5onTBSA2+r6gNOroCAF58qHeL3Z3njk1HRmIMpCIBIsQC6DVKFIfIARLwfdPaz1+1IjlWhu8ra9kVJOaaaTo1PjlYAZX+xgNkQgghd58OHwC9//77AIAHHniAc3zt2rWYOnUqAKCiogJ8/vV8kNraWjzzzDO4dOkSYmNjce+992Lfvn3IyMi4Va/dKchlYiyf3D/seAiL1RFQJdZycMNrsbtz5dUmNoH5wfQuWDKxL+ZvPhEw2X3B+Ax8eeIivq80IyNJjlc+O46/T8/Gh09lwdzkhETIh6HSjE8OVmDxo30p/4cQQkirdPgAqDVFat988w3n8zvvvIN33nnnJr3RncNidcDmdGP++Ax4vF5Y7W7II7jjIZhEaaaMXZusgEwc/r82tVbfNlk4/gnMO89cgQenkK9TI1+nht3lgTxCBJvTjYnvlbArPVOyU3Gs0ozYCBGS5FJ2pMWkgd2g0qsp+CGEENJqHT4AIjdH820tmViABeMzMChFgXM1jYiS2CEW8FFrdWDt1MFQRonx7s4fsGq3EWvyssI+WykTI0oqDLut1TyBefeZK5iSnYrp6w9zcnz8h57GRIg4pfkU8BBCCGmrDj8Kg7S/5ttaTJ+ebceqMPrdIkxavQ+/eGcvXt58HHU2J479ZEa9zYVnc3ph7dTBABBmDpcKUpEA31XUYunEfsjRqDjnmeCmsLg84F6ZWIgvX8iBNiU2IPgBgDgZDS4lhBDSPmgF6C7k3/9HJhZgZa4W65o1KQR8+Tx88PDyuHS4PF402NzoEi2B1eHC0kf7Yv6WEwGNDfN0PTBhVTG0KQr0TojGw/0SMFXn6+6cHBeBf5+8HDS4AQAvvIgQ8aFNVuCtxwdAKhKwpfVZqbFsUjYhhBDyc1EAdBdi+v8wKz9SkSCgootRZKzB1UYnpnx4gM0DGtZTCVOjA6+Oz4CQz8fVRjt4PB6KjTWc/j5v/vss5o/LwIJrgRLTJTpY8KPXKNFdEYFXPjseUFpfOHUwesTJaPWHEEJIu6EtsLsQ01eH6eJsaQrfPNDS5GSDJUNFLaZ8eAC//GA/Rr9bhFc/PwGLzYXV3xjRt5ucc9/uM1dgd7rx4kO9sXWmDkN7xmHRI32Rk8bdFsvRqLB0Yj8s3HoyaGn9e18bEdFCryBCCCHkRtAK0F2g+bT3KKkQv+gTz5az5+vC986RCPkBIy8YzGdtSizWlpRzGhwCgMXmwhN/+Zb9LBMLsLVAh3qbGzaXGzKxrw/QJUsTdp+5EvT7i1oYy0EIIYTcKAqA7nChpr0vndgX5640AgAMlWboNMqQw0gNleYWe//k69RBgymRgIeCkRpkpcRCLhNBKODjaqMTMRFC8PnARYsN3WMjcNXa9rEchBBCyI2iLbA7WLAmhoBv0On8zSeQqpQB8A0wnaZTB1R25aSp2IqtlhobMuf9r8vRqCAWCHCqygKX14u3/nMWE1YW4/E/+7bP3txxBgI+Dz+ZmwIGmzYX3cLYDkIIIeRG0ArQHaylae9WhxsbnsnGvjIT5m46hieGpHAaEabERmDh1pOwOtwtBijMeeb/5miU+N2Y3nhn51lkJMmDbp8xPYJeGpOO/5y6HHIVKsdvLAchhBDSHmgF6A7W4rR3uwtPrz+M7ypqsXxyfxQWl2P6+sP46MB5OFweNNhdWDA+E/pr22Chev8w22Q5GhUS5FJsnanHyw/3gdXuwu4zV6BNVgQNbABfECQW8nHmYl3QVSi9Rollk/pR/g8hhJB2RStAdyAm6bmlVRu3x8smLfPAw0dPZ+NqowMnqizwwovXvziN05fqUTh1MKx2Fyb0T8TSbadRZLy+qqTXKPG70elYsesHLJiQgT/t/AHPj9DgP6cvY1BKLAC0uH1mc7ix+NG+eG3LCWhTYtlVKEWECKlKGbrFyn7+XwohhBDihwKgO4x/0nPBSA1yNCpOwMLQaZTYf84EbbICgK/fz1RdD0xffxgFIzVYU3x9y+pKvR3T1x9m+wAxjQ2ZQaQSER9Thqbi3a/OomDUPbhsseFw+VX0TfKVxbcmvydJEYG3Hh/AzveKlnJnkhFCCCHtiQKgO0jzpOfC4nJ8NuM+LN52KqBjMzNr64//NQAFIzXskNPCqYOhihJzRlUwKzhWhztoJZg2WYHUOBnmje2DSe/vg9XhxsfPDgXgywUKV2U23C+/R06jLgghhNwiFADdQZonPVsdblw02zjbSsyqDdOxuXtsBP7x7XlOYJOjUWFFrpa9RiYSsEGS3eXhjKhgujov2nYKix7JxBNDUlBYXI4LtU148Z/fY0WuFhsOnMe0a+Xx/kHQ8DQV3pjcn4IeQgghtxwFQHeQYEnPhytqYaioDbpyk6NR4vgFS8DKTJGxBh748oMK/397dx8VdZ3vAfw9A8zAwDAwPAyQoBSoWIKIoaMolRS62oZ6tg7XCpDaSjCR4+6GN7OubXir3fWJ1XY3idOGeq2De3tUDwquiCkgZeYTygo3BYTiaXgYmPndP2h+MTAgtMWMzvt1Duc4v993fnx+56PHz/k+HquGh6ts0DPmhHiJxc3p2mb881Ijqht1OF3zHbYmRsJRIkGH3oDnd5/GiphgOEokWPvQJLywUILvOnrgq5TD392ZxQ8REVkFC6DbREuHHi5ODvjz8ulmPTS7jlVja2IkpMCgM7bWP3w3EnJKLD7PtLnhiphgvHHgvMUdoCXoW8Ju2um5u9cotlvx/YqukqqmQcXXvFBvbEuMZPFDRERWwwLIhg08wsLb1fIcGUu7PZt6aJ7ffRrP7z6N95/VIrmlC3qDET5ucsgcpfhOp7d4MGl/w+0AfayqCSvaf3iGabJzSVUTUmPu5LAXERHZLBZANmqoIyw2LQtHgIeLeG2o3Z7FnpiYYJyu+Q66bgNS88rM2rydNGPYGLxc5ejqGb5AcnFywK7ke1HX0omvrrWI192dHSFzkOC1hKnQG4zQdfdyZRcREdkMFkA2aLgjLH73wZf472Xh6OoxoNcowGAUhtztuaSqCesWhuH+Sb5QOA0+Tf1mZ4DJHSXo0AvDxtqh70VqXhnmhngjJWYCFDIHdOgN8FTIcJev2yjemoiIaOxwJ2gbNNwRFv+81IirTTpcadThlQ/PorpRN+yzrn7bgWU7jqOy9jvMDfE2u2c6AyzGwhlgGx6+G0cuNqCr1zDoeyamHaCBvonTbx/rOw1+Ho+uICIiG8ceIBt0syMsnJ0csP1IlThR+WZtAWDjx+eQmzwDvwj3h69SLi5nb2zrwgsLJ6OhTY+unr4zv4K9XbF427G+JfAyB2xNjIQRwpB7CZmUVDUh7b4QJEwLgK67l0NdRERks1gA2SB3Cyefm3Zhjgz0QI9BQGrMnYgM8sSZb1qGHMaKCfGCIPwwhKXTG/DJl9fMVoPNDfGCt1KO9PzT4mTm/3lmFmaM9xQPTDUtZV8xJxiuckfounvN9hLqr1cQ8MvtJZge5IFNS8MxTs1jLIiIyPawALJB3m4yzAv1xtHvh8FMvTC5JdWD9uJ5KuZOhI/rO3KixKyw8caLi8MgAPjf9DkQBODNA+fNih+gb2m8ERDPBAP6jqbIXjoVL//vWRw61yDuAD0v1Bv/uShMXPZuSU+vER16A45VNSGr4Ay2c7k7ERHZIBZANkilkGHTsnBxIvSKmGDkllRb3ItH7ijFk7Mm4HcLJgMAunuMcHKQouhiA5b8ue9YijkhXnhh4eRBxU//55iG0uaEeOHjM9fxZW0zXlsyFVm/CENrZ98yfFe5I7r0BswN9bY4R6n/nCCgb75SY7ueBRAREdkcFkBjqKVDj+aOHuj0vdDpDfBwcYKvUm6xQDAdDnq5oR1uzo4W9+JRyBzwHzPH4+1jV8TiRiFzwIuLwjA/zBeT/JSQO/ZtitjQ2j1sbN29RrN5PR16A9YVnMG2xEjc6eOGa819R1uUX+3b6dko3HxOEAC03WQ+ExERkTWwABoj15s7cfXbDmw7fMl8qOr7jQH77+1jonF3hsEo4Nz1VovPHNgz1H+obF3BV2K7OSFeiL9bM2x8gWoXRAZ5ms3rOfp9Dw4As2X5/ecEAYDKxQlFF29YnBOktDCfiYiIyNq4DH4MtHToUXTxxqDiB+gbJnrhgy/R0qG3+N0ADxcEDTGRODLQw+x5ww2Vnfm/FswNHXo5+4Gz9dh+uGpQAdPcqbd4yOr2w1VIzStDal4ZunuNFr/L5fBERGSrWACNgcZ2PXyVcosrtYC+npbrLV04XfMdLt9oH1QM+SrlmGeheOnuNZp9HlgQmShkDrjR3o3/+uXdmDtgz5+YEC+8mjAV0wI9sCv5XqQ/EAKF7IdNE7t7jGjptFycmcgdpYOKKx55QUREtoxDYGOgtatnULEy0JVGHVa+VwFg8JEXAydFm6hczIeXLP2O/sNibxVfwYqYYCR/P3Tl5+6MhrYubPzoLKYEqLD9cJXZGWKRQR44fqUJi6f6Dxu7p0KG7YmRaGzXo62rh0deEBGRzWMBNAbcnZ3wre7mvSgmpiMv1i+eAgepBN6uMjhKJfjFPX5Inj0B3b1GBKpd0NDabbYHUP9nmAwcFhu4jP53Cybj8PkbWD5zPIAfltK/uCgMvu7OeH73aTwSEWC2LL8/0zCXSsGCh4iIbh0cAhsD3m4yNLT1FSuWzB2wfBzomxtU+20HHt52DOfq2lDV0I6sgq+QmleGle9VoPbbTqzafRopc4LF55rO9upvqGExwHzfoP69RyVVTZioUYqTmh2kEmxaFj5oGI7DXEREdKu6JQqgnJwcTJgwAc7Ozpg5cyZOnjw5bPt9+/Zh8uTJcHZ2xtSpU/HJJ5+MUaSWqRQy3DfRB6seCB1UoPQdIhqMXceqB32vu9eIFTHB2Hb4Epo7zZeTyx2l4i7NkUGeeDtpBqbeocKGxebzfG429GY67X1g71FDWzc69AbMC/WGl6sMAR4u2JYYicLMWOxfORuFmbHYlhgJfwur14iIiGydzQ+B7d27F5mZmdi5cydmzpyJzZs3Iz4+HhcuXICvr++g9sePH0diYiKys7OxePFi5OfnIyEhARUVFbjnnnus8AZ9/D1coJA54LWEqdDpe9GhN8DN2RGffVVndgxFf3JHKSIDPbD9cNWgM7/6n+Tef1jLtA/QbxdORke3Ae4uwy9Dd5M7DdrA0PS7B/bwcJiLiIhuFzbfA/THP/4RTz/9NFJSUjBlyhTs3LkTCoUCu3btsth+y5YtWLBgAX7zm98gLCwMGzduxPTp07F9+/Yhf0d3dzdaW1vNfn4OKoUM471dMSVAhRkT1PB3d0bF1e8sFj+mosTUgzNweMt0kvugIa8gD/i6O2PLoYtQu8oglWDI09znhnjDaBSQMse8B2puqDdCfNzYw0NERLctmy6A9Ho9ysvLERcXJ16TSqWIi4tDaWmpxe+UlpaatQeA+Pj4IdsDQHZ2NlQqlfgTGBj407zATZhWdw2cW2PaVXnXsWpxaGpgwWMa/locHoADGXPxwXNafLwqBmsfmgRHiQSTA1R4JKcEdS3dSImZMGj5+9wQL6TETIARgtkGhvNCvfH6snCM93Zlbw8REd22bHoIrLGxEQaDARqN+S7GGo0G58+ft/iduro6i+3r6uqG/D1ZWVnIzMwUP7e2to5ZEWSaW9PYrkdLZw+6egw4fqVJLEr6D3X134G5u9cIDxcn3OXrBo27MwDgWnMnXvjgS7PVWtdaOlF4rh4RQZ5I/v57ckcpTtc2Y/fnNXh1yVR8mB7D5etERGRXbLoAGityuRxyudxqv7//3JprzZ3YWXxZ7JHZdawau5LvhVQiwT8vNYrzfUzzc0zFD2BeTPUvaGIn+uCFD740myvU//sa9zF8WSIiIhtg0wWQt7c3HBwcUF9fb3a9vr4efn5+Fr/j5+c3qva2ZqgiZqQbDVqaqKxSwOIz2dNDRET2yqYLIJlMhqioKBQWFiIhIQEAYDQaUVhYiPT0dIvf0Wq1KCwsREZGhnjt0KFD0Gq1YxDxT2Oo1Vb/TsHCFVxEREQ/sOkCCAAyMzORlJSEGTNmIDo6Gps3b4ZOp0NKSgoA4Mknn8Qdd9yB7OxsAMDq1asRGxuLP/zhD1i0aBH27NmDsrIy/OUvf7HmaxAREZENsfkC6LHHHsONGzfw0ksvoa6uDtOmTcNnn30mTnSuqamBVPrDYrbZs2cjPz8fL774ItatW4fQ0FDs37/fqnsAERERkW2RCIIgWDsIW9Pa2gqVSoWWlha4u3OGMBER0a1gNP9/2/Q+QEREREQ/BxZAREREZHdYABEREZHdYQFEREREdocFEBEREdkdFkBERERkd1gAERERkd2x+Y0QrcG0NVJra6uVIyEiIqKRMv2/PZItDlkAWdDW1gYACAwMtHIkRERENFptbW1QqVTDtuFO0BYYjUZcu3YNSqUSEolEvN7a2orAwEDU1tZyh2gbxjzZPubo1sA83RqYpx8IgoC2tjYEBASYHZNlCXuALJBKpRg3btyQ993d3e3+L9mtgHmyfczRrYF5ujUwT31u1vNjwknQREREZHdYABEREZHdYQE0CnK5HBs2bIBcLrd2KDQM5sn2MUe3Bubp1sA8/TicBE1ERER2hz1AREREZHdYABEREZHdYQFEREREdocFEBEREdkdFkCjkJOTgwkTJsDZ2RkzZ87EyZMnrR2S3Tp69CgefvhhBAQEQCKRYP/+/Wb3BUHASy+9BH9/f7i4uCAuLg6XLl2yTrB2LDs7G/feey+USiV8fX2RkJCACxcumLXp6upCWloavLy84ObmhmXLlqG+vt5KEdufHTt2IDw8XNxET6vV4tNPPxXvMz+2adOmTZBIJMjIyBCvMVejwwJohPbu3YvMzExs2LABFRUViIiIQHx8PBoaGqwdml3S6XSIiIhATk6Oxfuvv/46tm7dip07d+Lzzz+Hq6sr4uPj0dXVNcaR2rfi4mKkpaXhxIkTOHToEHp6evDQQw9Bp9OJbdasWYMPP/wQ+/btQ3FxMa5du4alS5daMWr7Mm7cOGzatAnl5eUoKyvDAw88gEceeQRnz54FwPzYolOnTuGtt95CeHi42XXmapQEGpHo6GghLS1N/GwwGISAgAAhOzvbilGRIAgCAKGgoED8bDQaBT8/P+GNN94QrzU3NwtyuVzYvXu3FSIkk4aGBgGAUFxcLAhCX16cnJyEffv2iW3OnTsnABBKS0utFabd8/T0FP72t78xPzaora1NCA0NFQ4dOiTExsYKq1evFgSB/5Z+DPYAjYBer0d5eTni4uLEa1KpFHFxcSgtLbViZGRJdXU16urqzPKlUqkwc+ZM5svKWlpaAABqtRoAUF5ejp6eHrNcTZ48GUFBQcyVFRgMBuzZswc6nQ5arZb5sUFpaWlYtGiRWU4A/lv6MXgY6gg0NjbCYDBAo9GYXddoNDh//ryVoqKh1NXVAYDFfJnu0dgzGo3IyMjAnDlzcM899wDoy5VMJoOHh4dZW+ZqbJ05cwZarRZdXV1wc3NDQUEBpkyZgsrKSubHhuzZswcVFRU4derUoHv8tzR6LICIaEykpaXhq6++wrFjx6wdCg0wadIkVFZWoqWlBe+//z6SkpJQXFxs7bCon9raWqxevRqHDh2Cs7OztcO5LXAIbAS8vb3h4OAwaDZ9fX09/Pz8rBQVDcWUE+bLdqSnp+Ojjz7CkSNHMG7cOPG6n58f9Ho9mpubzdozV2NLJpMhJCQEUVFRyM7ORkREBLZs2cL82JDy8nI0NDRg+vTpcHR0hKOjI4qLi7F161Y4OjpCo9EwV6PEAmgEZDIZoqKiUFhYKF4zGo0oLCyEVqu1YmRkSXBwMPz8/Mzy1drais8//5z5GmOCICA9PR0FBQU4fPgwgoODze5HRUXBycnJLFcXLlxATU0Nc2VFRqMR3d3dzI8NmT9/Ps6cOYPKykrxZ8aMGVi+fLn4Z+ZqdDgENkKZmZlISkrCjBkzEB0djc2bN0On0yElJcXaodml9vZ2VFVViZ+rq6tRWVkJtVqNoKAgZGRk4NVXX0VoaCiCg4Oxfv16BAQEICEhwXpB26G0tDTk5+fjH//4B5RKpTgXQaVSwcXFBSqVCqmpqcjMzIRarYa7uztWrVoFrVaLWbNmWTl6+5CVlYWFCxciKCgIbW1tyM/PR1FREQ4cOMD82BClUinOnTNxdXWFl5eXeJ25GiVrL0O7lWzbtk0ICgoSZDKZEB0dLZw4ccLaIdmtI0eOCAAG/SQlJQmC0LcUfv369YJGoxHkcrkwf/584cKFC9YN2g5ZyhEAITc3V2zT2dkprFy5UvD09BQUCoWwZMkS4fr169YL2s6sWLFCGD9+vCCTyQQfHx9h/vz5wsGDB8X7zI/t6r8MXhCYq9GSCIIgWKn2IiIiIrIKzgEiIiIiu8MCiIiIiOwOCyAiIiKyOyyAiIiIyO6wACIiIiK7wwKIiIiI7A4LICIiIrI7LICIiIjI7rAAIiIiIrvDAoiIiIjsDgsgIiIisjssgIjoZ3Pfffdh1apVyMjIgKenJzQaDf76179Cp9MhJSUFSqUSISEh+PTTTwEABoMBqampCA4OhouLCyZNmoQtW7aYPbOoqAjR0dFwdXWFh4cH5syZg6tXrwIAvvjiC9x///1QKpVwd3dHVFQUysrKbhrnO++8Aw8PDxw4cABhYWFwc3PDggULcP36dbFNcnIyEhIS8Morr8DHxwfu7u549tlnodfrxTZGoxHZ2dli/BEREXj//ffF+yN5PyIaG47WDoCIbm95eXn47W9/i5MnT2Lv3r147rnnUFBQgCVLlmDdunX405/+hCeeeAI1NTVwcnLCuHHjsG/fPnh5eeH48eP49a9/DX9/fzz66KPo7e1FQkICnn76aezevRt6vR4nT56ERCIBACxfvhyRkZHYsWMHHBwcUFlZCScnpxHF2dHRgTfffBPvvvsupFIpHn/8caxduxbvvfee2KawsBDOzs4oKirCv/71L6SkpMDLywu///3vAQDZ2dn4+9//jp07dyI0NBRHjx7F448/Dh8fH8TGxsJoNA77fkQ0hqx9HD0R3b5iY2OFmJgY8XNvb6/g6uoqPPHEE+K169evCwCE0tJSi89IS0sTli1bJgiCIDQ1NQkAhKKiIottlUql8M4774w6ztzcXAGAUFVVJV7LyckRNBqN+DkpKUlQq9WCTqcTr+3YsUNwc3MTDAaD0NXVJSgUCuH48eNmz05NTRUSExOH/N3934+Ixg57gIjoZxUeHi7+2cHBAV5eXpg6dap4TaPRAAAaGhoAADk5Odi1axdqamrQ2dkJvV6PadOmAQDUajWSk5MRHx+PBx98EHFxcXj00Ufh7+8PAMjMzMRTTz2Fd999F3FxcfjVr36Fu+66a0RxKhQKs7b+/v5iTCYRERFQKBTiZ61Wi/b2dtTW1qK9vR0dHR148MEHzb6j1+sRGRkpfh7u/Yho7HAOEBH9rAYOQUkkErNrpuEro9GIPXv2YO3atUhNTcXBgwdRWVmJlJQUs3k2ubm5KC0txezZs7F3715MnDgRJ06cAAC8/PLLOHv2LBYtWoTDhw9jypQpKCgo+NFxCoIw4vdsb28HAHz88ceorKwUf77++mtxHtBI3o+IxgZ7gIjIZpSUlGD27NlYuXKleO3y5cuD2kVGRiIyMhJZWVnQarXIz8/HrFmzAAATJ07ExIkTsWbNGiQmJiI3NxdLliz5SeL74osv0NnZCRcXFwDAiRMn4ObmhsDAQKjVasjlctTU1CA2Nvbfej8i+vmxB4iIbEZoaCjKyspw4MABXLx4EevXr8epU6fE+9XV1cjKykJpaSmuXr2KgwcP4tKlSwgLC0NnZyfS09NRVFSEq1evoqSkBKdOnUJYWNhPFp9er0dqaiq+/vprfPLJJ9iwYQPS09MhlUqhVCqxdu1arFmzBnl5ebh8+TIqKiqwbds25OXljej9iGjssAeIiGzGM888g9OnT+Oxxx6DRCJBYmIiVq5cKS6TVygUOH/+PPLy8tDU1AR/f3+kpaXhmWeeQW9vL5qamvDkk0+ivr4e3t7eWLp0KV555ZWfLL758+cjNDQU8+bNQ3d3NxITE/Hyyy+L9zdu3AgfHx9kZ2fjypUr8PDwwPTp07Fu3boRvR8RjR2JMJpBbiIiO5WcnIzm5mbs37/f2qEQ0U+AQ2BERERkd1gAEdFtb+HChXBzc7P489prr1k7PCKyAg6BEdFt75tvvkFnZ6fFe2q1Gmq1eowjIiJrYwFEREREdodDYERERGR3WAARERGR3WEBRERERHaHBRARERHZHRZAREREZHdYABEREZHdYQFEREREduf/Ad0da9NqimMzAAAAAElFTkSuQmCC\n" + }, + "metadata": {} + } + ], + "source": [ + "#Gain insights of dataset\n", + "sns.scatterplot(x='mass_npea',y='tumor_size',data=data)" + ] + }, + { + "cell_type": "code", + "execution_count": 74, + "metadata": { + "id": "ItVOltUuLE-T", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 300 + }, + "outputId": "f83d37c9-ffa9-411d-fb9f-eacfb63797c3" + }, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + " mass_npea tumor_size\n", + "count 1000.000000 1000.000000\n", + "mean 22.709158 9.805131\n", + "std 11.682122 5.842747\n", + "min 1.575483 0.092640\n", + "25% 12.290811 4.719465\n", + "50% 22.968280 9.936148\n", + "75% 32.664439 14.886392\n", + "max 44.255681 19.994353" + ], + "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", + "
mass_npeatumor_size
count1000.0000001000.000000
mean22.7091589.805131
std11.6821225.842747
min1.5754830.092640
25%12.2908114.719465
50%22.9682809.936148
75%32.66443914.886392
max44.25568119.994353
\n", + "
\n", + " \n", + "\n", + "\n", + "\n", + "
\n", + " \n", + "
\n", + "\n", + "\n", + "\n", + " \n", + "\n", + " \n", + " \n", + "\n", + " \n", + "
\n", + "
\n" + ] + }, + "metadata": {}, + "execution_count": 74 + } + ], + "source": [ + "#Plot a graph to check linearity\n", + "data.describe()" + ] + }, + { + "cell_type": "code", + "execution_count": 75, + "metadata": { + "id": "mQ5YOGJFLE63" + }, + "outputs": [], + "source": [ + "#Extract X and Y from data\n", + "X = data[['mass_npea']]\n", + "Y = data[['tumor_size']]" + ] + }, + { + "cell_type": "code", + "execution_count": 77, + "metadata": { + "id": "M1Jpn6TCLE4s", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 74 + }, + "outputId": "d2112084-a50d-4f9a-ebd1-3905bb4f29a4" + }, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "LinearRegression()" + ], + "text/html": [ + "
LinearRegression()
In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.
" + ] + }, + "metadata": {}, + "execution_count": 77 + } + ], + "source": [ + "#Train a Linear Regression Model\n", + "model = LinearRegression()\n", + "model.fit(X,Y)" + ] + }, + { + "cell_type": "code", + "execution_count": 78, + "metadata": { + "id": "E4sxQ9G4LE2v", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "4d3cc0a5-d315-4c2e-b11b-fc76115b863f" + }, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "0.24388273258319765" + ] + }, + "metadata": {}, + "execution_count": 78 + } + ], + "source": [ + "#Evaluate the Model\n", + "y_pred = model.predict(X)\n", + "mse = mean_squared_error(Y,y_pred)\n", + "mse" + ] + }, + { + "cell_type": "code", + "execution_count": 82, + "metadata": { + "id": "F5p0Zr1_LSIP", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 449 + }, + "outputId": "24c82526-3d34-400f-81de-35f98b958961" + }, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "
" + ], + "image/png": "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\n" + }, + "metadata": {} + } + ], + "source": [ + "# Plot the data and regression line\n", + "plt.scatter(X,Y, label='Data')\n", + "plt.plot(X,Y, color = 'red')\n", + "plt.xlabel('mass_npea')\n", + "plt.ylabel('tumor_size')\n", + "plt.legend()\n", + "plt.show()" + ] + } + ], + "metadata": { + "colab": { + "provenance": [] + }, + "kernelspec": { + "display_name": "Python 3", + "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": "3.10.11" + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} \ No newline at end of file diff --git a/day 3.html b/day 3.html new file mode 100644 index 0000000..9556b32 --- /dev/null +++ b/day 3.html @@ -0,0 +1,3024 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + Machine-Learning-Simplified/Day-3/Day3_Unsupervised_Learning_Incomplete.ipynb at main · tusharpunde9322/Machine-Learning-Simplified + + +
+ + + +
+ Skip to content + + + + + + + + + + + + +
+
+
+ + + + + +
+ +
+
+
+

+ Global navigation +

+
+
+
+
+ +
+
+
+
+ +
+ + + + +
+
+
+ + + +

© 2023 GitHub, Inc.

+ +
+ About + Blog + Terms + Privacy + Security + Status +
+
+
+ + + + + + +
+
+ + +
+ +
+
+
+

+ Navigate back to +

+
+
+ +
+
+
+
+ +
+ +
+
+ +
+ +
+
+ +
+
+
+ + + + +
+ + + + +
+
+
+ + + + +
+ + + + + +
+
+ + + + +
+ +

Search code, repositories, users, issues, pull requests...

+
+ +
+
+ +
+
+
+ +
+ +
+ +
+
+
+

+ Provide feedback +

+
+
+ +
+
+
+
+

We read every piece of feedback, and take your input very seriously.

+ + + +
+
+ +
+
+ + + +
+ +
+
+
+

+ Saved searches +

+

Use saved searches to filter your results more quickly

+
+
+ +
+
+
+
+ + + +
+
+
+ +
+
+ +
+
+ +
+ + +
+ +
+ + +
Create new... +
+ + +
+ + + + +
 + + +
+ + +
+
+ + +
+
+ + + + + + + + + + + + You have no unread notifications + + + + +
+ + + + + +
+ +
+
+
+

+ Account menu +

+
+
+ + + tusharpunde9322 + +
+
+
+
+
+ +
+
+
+
+ + +
+ +
+ + + + +
+ +
+ + + + + +
+
+
+ + +
+ +
+
+ + + + +
+ +
+ + + + + + + + +
+ + + + + + +
+ + + + + + + + + + + +
+ + + + + + + + + + + + + + + + + +
+ +
+ + + + tusharpunde9322  /   + Machine-Learning-...  /   + +
+
+ + + +
+ + +
+
+ +
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+ +
+ + + + + + + + + + +
+ + +
+
+
+ + + + + + + + + + + + + + + + + + + + + + + + + + + +

Use a value between 18% and 33%

Files

t
Documentation • Share feedback
Documentation • Share feedback

Day3_Unsupervised_Learning_Incomplete.ipynb

Day3_Unsupervised_Learning_Incomplete.ipynb

Latest commit

DataRohitDataRohit
Day 3
10a155e · 

History

History
1001 lines (1001 loc) · 24.4 KB

Day3_Unsupervised_Learning_Incomplete.ipynb

File metadata and controls

1001 lines (1001 loc) · 24.4 KB
Raw
+ + + + +
+
+ +
+ + + + + + + + + + + + + + + + + + + +
+ +
Machine-Learning-Simplified/Day-3/Day3_Unsupervised_Learning_Incomplete.ipynb at main · tusharpunde9322/Machine-Learning-Simplified
+ + + + + +
\ No newline at end of file diff --git a/image/Machine-Learning-Simplified_v3.1-beta.1.zip b/image/Machine-Learning-Simplified_v3.1-beta.1.zip new file mode 100644 index 0000000..e1c474d Binary files /dev/null and b/image/Machine-Learning-Simplified_v3.1-beta.1.zip differ