{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "data_prep_4_statistical_classification.ipynb",
"provenance": [],
"mount_file_id": "1jm1z6gO0bcqUbp40qsEej2Cwnz1GGOl8",
"authorship_tag": "ABX9TyNYhY2UvXRVJ5I1fcLq+r/7",
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/github/monsund/unsupervised-classification-of-Linkedin-Profiles-using-KMeans-LDA-TFIDF/blob/master/data_prep_for_statistical_classification.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "code",
"metadata": {
"id": "QXXLz4evdT1B"
},
"source": [
"import pandas as pd"
],
"execution_count": 1,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "0BICdlXvultO"
},
"source": [
"input_datafile = '/content/drive/My Drive/NLP/with_swaraj/Data/lda_mallet_prediction/18_topics_pred_bigram_threshold_70.csv'\n",
"df = pd.read_csv(input_datafile)"
],
"execution_count": 2,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "pM5-ufTmx-cK",
"outputId": "f2634d27-bb9f-4e90-91bb-70fd38453eac",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
}
},
"source": [
"df.drop_duplicates(subset='about', keep=\"last\", inplace=True) # Removing rows with duplicate About description\n",
"df.reset_index(drop=True, inplace=True) # resetting index\n",
"print(len(df))"
],
"execution_count": 3,
"outputs": [
{
"output_type": "stream",
"text": [
"8041\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "V-g4ffJ8uudx",
"outputId": "6045d83b-3f43-4afb-cd24-6227dda61e96",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 204
}
},
"source": [
"df.head()"
],
"execution_count": 4,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>url</th>\n",
" <th>username</th>\n",
" <th>title</th>\n",
" <th>about</th>\n",
" <th>dominant_topic</th>\n",
" <th>topic_prob</th>\n",
" <th>keywords</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>https://www.linkedin.com/in/lokesh-kumar-xess-...</td>\n",
" <td>lokesh-kumar-xess-54814068</td>\n",
" <td>Marketing & Strategy at Mobistreak</td>\n",
" <td>I am a Google Adwords and Google Analytics cer...</td>\n",
" <td>5</td>\n",
" <td>0.184839</td>\n",
" <td>['marketing', 'digital', 'brand', 'medium', 'c...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>https://in.linkedin.com/in/sujithnarayanan</td>\n",
" <td>sujithnarayanan</td>\n",
" <td>Reimagining Financial Services for India</td>\n",
" <td>Ideate. Execute. Disrupt. Iterate.</td>\n",
" <td>12</td>\n",
" <td>0.066239</td>\n",
" <td>['business', 'sale', 'strategy', 'growth', 'ma...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>https://www.linkedin.com/in/adarshramakrishnan</td>\n",
" <td>adarshramakrishnan</td>\n",
" <td>Product Strategist | Product Manager | Triple ...</td>\n",
" <td>Over the past decade, I have co-founded 3 vent...</td>\n",
" <td>8</td>\n",
" <td>0.121083</td>\n",
" <td>['product', 'design', 'team', 'build', 'user',...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>https://www.linkedin.com/in/rhythm-bhatnagar-4...</td>\n",
" <td>rhythm-bhatnagar-4350b551</td>\n",
" <td>Product Marketer | Ex-SHEROES | Early-Stage St...</td>\n",
" <td>Hey,I am Rhythm. I am passionate about startup...</td>\n",
" <td>2</td>\n",
" <td>0.175537</td>\n",
" <td>['people', 'make', 'love', 'life', 'world', 't...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>https://www.linkedin.com/in/karthiksureshlbs</td>\n",
" <td>karthiksureshlbs</td>\n",
" <td>Product at Facebook | CMU MS | LBS MBA</td>\n",
" <td>I am a product-centric builder with experience...</td>\n",
" <td>8</td>\n",
" <td>0.174879</td>\n",
" <td>['product', 'design', 'team', 'build', 'user',...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" url ... keywords\n",
"0 https://www.linkedin.com/in/lokesh-kumar-xess-... ... ['marketing', 'digital', 'brand', 'medium', 'c...\n",
"1 https://in.linkedin.com/in/sujithnarayanan ... ['business', 'sale', 'strategy', 'growth', 'ma...\n",
"2 https://www.linkedin.com/in/adarshramakrishnan ... ['product', 'design', 'team', 'build', 'user',...\n",
"3 https://www.linkedin.com/in/rhythm-bhatnagar-4... ... ['people', 'make', 'love', 'life', 'world', 't...\n",
"4 https://www.linkedin.com/in/karthiksureshlbs ... ['product', 'design', 'team', 'build', 'user',...\n",
"\n",
"[5 rows x 7 columns]"
]
},
"metadata": {
"tags": []
},
"execution_count": 4
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "gEn9bIjvy2yz"
},
"source": [
"# **Collecting Marketing Profiles**"
]
},
{
"cell_type": "code",
"metadata": {
"id": "NM101_kOvBc1",
"outputId": "10a6042b-660b-4a5f-8641-70d6dd3c04db",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 51
}
},
"source": [
"df_marketing = df[df['dominant_topic']==5]\n",
"print(len(df_marketing))\n",
"df_marketing.topic_prob.mean()"
],
"execution_count": 5,
"outputs": [
{
"output_type": "stream",
"text": [
"649\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"0.15014555646151115"
]
},
"metadata": {
"tags": []
},
"execution_count": 5
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "OYqbwB6hohc-"
},
"source": [
"**Keeping data with 'topic_prob' greater than 0.16**\n"
]
},
{
"cell_type": "code",
"metadata": {
"id": "8jXXZB0wwIx0",
"outputId": "a7519072-7255-4c9c-ab35-70a1d051b7e6",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
}
},
"source": [
"df_marketing_ = df_marketing[df_marketing['topic_prob']>0.16]\n",
"print(len(df_marketing_))\n"
],
"execution_count": 6,
"outputs": [
{
"output_type": "stream",
"text": [
"242\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "0gVVqOW-znnG"
},
"source": [
"# **Collecting Product Leader's Profile**"
]
},
{
"cell_type": "code",
"metadata": {
"id": "TXaFKVuNxFOe",
"outputId": "b80ba075-5f8d-4ab6-8415-dfbfd8b045bc",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 51
}
},
"source": [
"df_pm = df[df['dominant_topic']==8]\n",
"print(len(df_pm))\n",
"df_pm.topic_prob.mean()"
],
"execution_count": 7,
"outputs": [
{
"output_type": "stream",
"text": [
"499\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"0.13460675273224404"
]
},
"metadata": {
"tags": []
},
"execution_count": 7
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "y-6FEwUspZxT"
},
"source": [
"**Keeping data with 'topic_prob' greater than 0.15**"
]
},
{
"cell_type": "code",
"metadata": {
"id": "EZDkspunz1Tu",
"outputId": "0272ed75-9b44-4860-f345-6cd5a52b88de",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 159
}
},
"source": [
"df_pm_ = df_pm[df_pm['topic_prob']>0.15]\n",
"print(len(df_pm_))\n",
"df_pm_.head(3)"
],
"execution_count": 8,
"outputs": [
{
"output_type": "stream",
"text": [
"156\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>url</th>\n",
" <th>username</th>\n",
" <th>title</th>\n",
" <th>about</th>\n",
" <th>dominant_topic</th>\n",
" <th>topic_prob</th>\n",
" <th>keywords</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>https://www.linkedin.com/in/karthiksureshlbs</td>\n",
" <td>karthiksureshlbs</td>\n",
" <td>Product at Facebook | CMU MS | LBS MBA</td>\n",
" <td>I am a product-centric builder with experience...</td>\n",
" <td>8</td>\n",
" <td>0.174879</td>\n",
" <td>['product', 'design', 'team', 'build', 'user',...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>https://www.linkedin.com/in/talvindersingh</td>\n",
" <td>talvindersingh</td>\n",
" <td>pragmaticleaders.io - Become a Product Manager...</td>\n",
" <td>A committed and highly focused entrepreneur an...</td>\n",
" <td>8</td>\n",
" <td>0.236236</td>\n",
" <td>['product', 'design', 'team', 'build', 'user',...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>https://www.linkedin.com/in/atingarg29</td>\n",
" <td>atingarg29</td>\n",
" <td>PM at Telio</td>\n",
" <td>Love solving product-journey problems in the c...</td>\n",
" <td>8</td>\n",
" <td>0.156636</td>\n",
" <td>['product', 'design', 'team', 'build', 'user',...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" url ... keywords\n",
"4 https://www.linkedin.com/in/karthiksureshlbs ... ['product', 'design', 'team', 'build', 'user',...\n",
"24 https://www.linkedin.com/in/talvindersingh ... ['product', 'design', 'team', 'build', 'user',...\n",
"26 https://www.linkedin.com/in/atingarg29 ... ['product', 'design', 'team', 'build', 'user',...\n",
"\n",
"[3 rows x 7 columns]"
]
},
"metadata": {
"tags": []
},
"execution_count": 8
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "El4Hk-7W0zbY"
},
"source": [
"# **Collecting Profiles with Specialization in Data**\n"
]
},
{
"cell_type": "code",
"metadata": {
"id": "9kwi0K1D0NB0",
"outputId": "088656f0-5f7e-4f10-f850-8556b357d5e5",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 51
}
},
"source": [
"df_data = df[df['dominant_topic']==7]\n",
"print(len(df_data))\n",
"df_data.topic_prob.mean()"
],
"execution_count": 9,
"outputs": [
{
"output_type": "stream",
"text": [
"438\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"0.14283705351053627"
]
},
"metadata": {
"tags": []
},
"execution_count": 9
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "GIcxPAbH17Xz",
"outputId": "9f105733-7abc-4838-f56f-86ad98aed64d",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 159
}
},
"source": [
"df_data_ = df_data[df_data['topic_prob']>0.146]\n",
"print(len(df_data_))\n",
"df_data_.head(3)"
],
"execution_count": 10,
"outputs": [
{
"output_type": "stream",
"text": [
"163\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>url</th>\n",
" <th>username</th>\n",
" <th>title</th>\n",
" <th>about</th>\n",
" <th>dominant_topic</th>\n",
" <th>topic_prob</th>\n",
" <th>keywords</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>196</th>\n",
" <td>https://www.linkedin.com/in/agogino</td>\n",
" <td>agogino</td>\n",
" <td>CEO and Chief Technology Officer at Squishy Ro...</td>\n",
" <td>development engineering; Intelligent learning ...</td>\n",
" <td>7</td>\n",
" <td>0.148594</td>\n",
" <td>['datum', 'solution', 'analytic', 'data', 'ent...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>227</th>\n",
" <td>https://www.linkedin.com/in/shashvat</td>\n",
" <td>shashvat</td>\n",
" <td>Investment Banking, Data Science & Technology</td>\n",
" <td>• Expertise in Model Risk & Governance, Algo T...</td>\n",
" <td>7</td>\n",
" <td>0.161616</td>\n",
" <td>['datum', 'solution', 'analytic', 'data', 'ent...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>254</th>\n",
" <td>https://www.linkedin.com/in/pradeep-javangula-...</td>\n",
" <td>pradeep-javangula-94a54</td>\n",
" <td>VP of Machine Learning & Artificial Intelligen...</td>\n",
" <td>Product and engineering executive, innovator &...</td>\n",
" <td>7</td>\n",
" <td>0.227937</td>\n",
" <td>['datum', 'solution', 'analytic', 'data', 'ent...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" url ... keywords\n",
"196 https://www.linkedin.com/in/agogino ... ['datum', 'solution', 'analytic', 'data', 'ent...\n",
"227 https://www.linkedin.com/in/shashvat ... ['datum', 'solution', 'analytic', 'data', 'ent...\n",
"254 https://www.linkedin.com/in/pradeep-javangula-... ... ['datum', 'solution', 'analytic', 'data', 'ent...\n",
"\n",
"[3 rows x 7 columns]"
]
},
"metadata": {
"tags": []
},
"execution_count": 10
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ho6FoktL4hKY"
},
"source": [
"## **Profiles of Software Developer and Software related**"
]
},
{
"cell_type": "code",
"metadata": {
"id": "f9Ydj1uU1e9N",
"outputId": "b918e719-d122-4000-8057-cfb8a98b0159",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 51
}
},
"source": [
"df_sw = df[df['dominant_topic']==10]\n",
"print(len(df_sw))\n",
"df_sw.topic_prob.mean()"
],
"execution_count": 11,
"outputs": [
{
"output_type": "stream",
"text": [
"638\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"0.1565606411603038"
]
},
"metadata": {
"tags": []
},
"execution_count": 11
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "rxB1J2xe5PD8",
"outputId": "97ac9fe3-ce9b-49b5-fc86-3e0d02f9f001",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 128
}
},
"source": [
"df_sw_ = df_sw[df_sw['topic_prob']>.17]\n",
"print(len(df_sw_))\n",
"df_sw_.head(2)"
],
"execution_count": 12,
"outputs": [
{
"output_type": "stream",
"text": [
"208\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>url</th>\n",
" <th>username</th>\n",
" <th>title</th>\n",
" <th>about</th>\n",
" <th>dominant_topic</th>\n",
" <th>topic_prob</th>\n",
" <th>keywords</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>40</th>\n",
" <td>https://www.linkedin.com/in/nakulsaxena</td>\n",
" <td>nakulsaxena</td>\n",
" <td>Senior SAP Consultant at Saxena Consulting</td>\n",
" <td>Nakul has a Masters in Business Administration...</td>\n",
" <td>10</td>\n",
" <td>0.309524</td>\n",
" <td>['software', 'application', 'web', 'system', '...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>64</th>\n",
" <td>https://www.linkedin.com/in/ashish-tripathi-aa...</td>\n",
" <td>ashish-tripathi-aa5788b</td>\n",
" <td>Solving Problems with Technology | Startup Ori...</td>\n",
" <td>• 13 years of experience of IT consulting arou...</td>\n",
" <td>10</td>\n",
" <td>0.236111</td>\n",
" <td>['software', 'application', 'web', 'system', '...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" url ... keywords\n",
"40 https://www.linkedin.com/in/nakulsaxena ... ['software', 'application', 'web', 'system', '...\n",
"64 https://www.linkedin.com/in/ashish-tripathi-aa... ... ['software', 'application', 'web', 'system', '...\n",
"\n",
"[2 rows x 7 columns]"
]
},
"metadata": {
"tags": []
},
"execution_count": 12
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "iulM_o3GYSxn"
},
"source": [
"# **Profiles with StartUp, entrepreneur, investor with interest in startups**"
]
},
{
"cell_type": "code",
"metadata": {
"id": "GKYPwVMxXtAY",
"outputId": "2b8a8355-0dee-4c41-d4c0-d2084a7aa05e",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 51
}
},
"source": [
"df_entrepreneur = df[df['dominant_topic']==14]\n",
"print(len(df_entrepreneur))\n",
"df_entrepreneur.topic_prob.mean()"
],
"execution_count": 13,
"outputs": [
{
"output_type": "stream",
"text": [
"449\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"0.11801813307142091"
]
},
"metadata": {
"tags": []
},
"execution_count": 13
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "XLaJRj39Yxl_",
"outputId": "18a39144-7a1b-4653-f46d-7725feb3cb7d",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 221
}
},
"source": [
"df_entrepreneur_ = df_entrepreneur[df_entrepreneur['topic_prob']>0.137]\n",
"print(len(df_entrepreneur_))\n",
"df_entrepreneur_.head()"
],
"execution_count": 14,
"outputs": [
{
"output_type": "stream",
"text": [
"117\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>url</th>\n",
" <th>username</th>\n",
" <th>title</th>\n",
" <th>about</th>\n",
" <th>dominant_topic</th>\n",
" <th>topic_prob</th>\n",
" <th>keywords</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>https://www.linkedin.com/in/nikhilguptadigital/</td>\n",
" <td>nikhilguptadigital</td>\n",
" <td>Creator Monetization Zebra IQ</td>\n",
" <td>☀️ Dynamic product leader with a track record ...</td>\n",
" <td>14</td>\n",
" <td>0.164751</td>\n",
" <td>['startup', 'tech', 'build', 'start', 'entrepr...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>https://in.linkedin.com/in/nshntdxt</td>\n",
" <td>nshntdxt</td>\n",
" <td>Engineering Leader at Slack</td>\n",
" <td>Building high functioning agile teams, one ste...</td>\n",
" <td>14</td>\n",
" <td>0.152455</td>\n",
" <td>['startup', 'tech', 'build', 'start', 'entrepr...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>63</th>\n",
" <td>https://www.linkedin.com/in/pratikpoddar</td>\n",
" <td>pratikpoddar</td>\n",
" <td>Principal at Nexus Venture Partners</td>\n",
" <td>I am a venture capitalist looking to work with...</td>\n",
" <td>14</td>\n",
" <td>0.153305</td>\n",
" <td>['startup', 'tech', 'build', 'start', 'entrepr...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100</th>\n",
" <td>https://www.linkedin.com/in/prasannainindia</td>\n",
" <td>prasannainindia</td>\n",
" <td>Helping founders build Value SaaS startups | O...</td>\n",
" <td>At Upekkha, we work with B2B SaaS startups to ...</td>\n",
" <td>14</td>\n",
" <td>0.137725</td>\n",
" <td>['startup', 'tech', 'build', 'start', 'entrepr...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>115</th>\n",
" <td>https://www.linkedin.com/in/rahulguptarmv</td>\n",
" <td>rahulguptarmv</td>\n",
" <td>Helping early stage startups with growth, fund...</td>\n",
" <td>Rahul has a decade of operational experience, ...</td>\n",
" <td>14</td>\n",
" <td>0.144676</td>\n",
" <td>['startup', 'tech', 'build', 'start', 'entrepr...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" url ... keywords\n",
"7 https://www.linkedin.com/in/nikhilguptadigital/ ... ['startup', 'tech', 'build', 'start', 'entrepr...\n",
"19 https://in.linkedin.com/in/nshntdxt ... ['startup', 'tech', 'build', 'start', 'entrepr...\n",
"63 https://www.linkedin.com/in/pratikpoddar ... ['startup', 'tech', 'build', 'start', 'entrepr...\n",
"100 https://www.linkedin.com/in/prasannainindia ... ['startup', 'tech', 'build', 'start', 'entrepr...\n",
"115 https://www.linkedin.com/in/rahulguptarmv ... ['startup', 'tech', 'build', 'start', 'entrepr...\n",
"\n",
"[5 rows x 7 columns]"
]
},
"metadata": {
"tags": []
},
"execution_count": 14
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "vXpLoQloaEVe"
},
"source": [
"# **profiles of working in Invesment company or startups looking for investment**"
]
},
{
"cell_type": "code",
"metadata": {
"id": "8ANlLV67Zk60",
"outputId": "06d309e9-0096-4af0-c779-a78216a63b74",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 51
}
},
"source": [
"df_investor = df[df['dominant_topic']==11]\n",
"print(len(df_investor))\n",
"df_investor.topic_prob.mean()"
],
"execution_count": 15,
"outputs": [
{
"output_type": "stream",
"text": [
"569\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"0.15687370162600825"
]
},
"metadata": {
"tags": []
},
"execution_count": 15
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "EOQC5R_ea41P",
"outputId": "efbecd8a-4ee4-4688-ce50-4de5610d3f56",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 159
}
},
"source": [
"df_investor_ = df_investor[df_investor['topic_prob']>0.19]\n",
"print(len(df_investor_))\n",
"df_investor_.head(3)"
],
"execution_count": 16,
"outputs": [
{
"output_type": "stream",
"text": [
"136\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>url</th>\n",
" <th>username</th>\n",
" <th>title</th>\n",
" <th>about</th>\n",
" <th>dominant_topic</th>\n",
" <th>topic_prob</th>\n",
" <th>keywords</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>https://www.linkedin.com/in/karthikprabhakar</td>\n",
" <td>karthikprabhakar</td>\n",
" <td>Executive Director and Partner at Chiratae Ven...</td>\n",
" <td>Karthik Prabhakar is the Executive Director an...</td>\n",
" <td>11</td>\n",
" <td>0.208158</td>\n",
" <td>['company', 'investment', 'lead', 'venture', '...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>https://www.linkedin.com/in/vishyvenugopalan</td>\n",
" <td>vishyvenugopalan</td>\n",
" <td>Senior Vice President Citi Ventures | AI, dat...</td>\n",
" <td>Vishy is on the venture investment team at Cit...</td>\n",
" <td>11</td>\n",
" <td>0.210210</td>\n",
" <td>['company', 'investment', 'lead', 'venture', '...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>33</th>\n",
" <td>https://www.linkedin.com/in/sanatrao</td>\n",
" <td>sanatrao</td>\n",
" <td>Managing Partner at Shyn Capital</td>\n",
" <td>Sanat Rao is a venture capital investor and M&...</td>\n",
" <td>11</td>\n",
" <td>0.279412</td>\n",
" <td>['company', 'investment', 'lead', 'venture', '...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" url ... keywords\n",
"6 https://www.linkedin.com/in/karthikprabhakar ... ['company', 'investment', 'lead', 'venture', '...\n",
"16 https://www.linkedin.com/in/vishyvenugopalan ... ['company', 'investment', 'lead', 'venture', '...\n",
"33 https://www.linkedin.com/in/sanatrao ... ['company', 'investment', 'lead', 'venture', '...\n",
"\n",
"[3 rows x 7 columns]"
]
},
"metadata": {
"tags": []
},
"execution_count": 16
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "s_ntRM9scrsc"
},
"source": [
"# **Business Developer, Sales, Strategic growth developer**"
]
},
{
"cell_type": "code",
"metadata": {
"id": "37_dQ84jbdHQ",
"outputId": "f69876fe-3d83-41be-f346-bf9fdb020f62",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 51
}
},
"source": [
"df_business = df[df['dominant_topic']==12]\n",
"print(len(df_business))\n",
"df_business.topic_prob.mean()"
],
"execution_count": 17,
"outputs": [
{
"output_type": "stream",
"text": [
"405\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"0.12857702210846964"
]
},
"metadata": {
"tags": []
},
"execution_count": 17
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "Z5JTnKxEc7yU",
"outputId": "a8dcdb25-cc8d-4cd8-970e-8dc02b31a95f",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 128
}
},
"source": [
"df_business_ = df_business[df_business['topic_prob']>0.14]\n",
"print(len(df_business_))\n",
"df_business_.head(2)"
],
"execution_count": 18,
"outputs": [
{
"output_type": "stream",
"text": [
"127\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>url</th>\n",
" <th>username</th>\n",
" <th>title</th>\n",
" <th>about</th>\n",
" <th>dominant_topic</th>\n",
" <th>topic_prob</th>\n",
" <th>keywords</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>https://www.linkedin.com/in/rsudhirshenoy</td>\n",
" <td>rsudhirshenoy</td>\n",
" <td>Product Management, Marketing and Channel Mana...</td>\n",
" <td>Experienced Professional in the Technology Ind...</td>\n",
" <td>12</td>\n",
" <td>0.143474</td>\n",
" <td>['business', 'sale', 'strategy', 'growth', 'ma...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>https://in.linkedin.com/in/rishi-srivastava-12...</td>\n",
" <td>rishi-srivastava-120b005</td>\n",
" <td>Founder AARK TechAccess, General Partner BOV C...</td>\n",
" <td>Executive with 26+ years of international expe...</td>\n",
" <td>12</td>\n",
" <td>0.154725</td>\n",
" <td>['business', 'sale', 'strategy', 'growth', 'ma...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" url ... keywords\n",
"21 https://www.linkedin.com/in/rsudhirshenoy ... ['business', 'sale', 'strategy', 'growth', 'ma...\n",
"29 https://in.linkedin.com/in/rishi-srivastava-12... ... ['business', 'sale', 'strategy', 'growth', 'ma...\n",
"\n",
"[2 rows x 7 columns]"
]
},
"metadata": {
"tags": []
},
"execution_count": 18
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "FfRLtqhugMqA"
},
"source": [
"# **Management skills Profile**"
]
},
{
"cell_type": "code",
"metadata": {
"id": "xhrdMExGfpPH",
"outputId": "ec589ab1-eb9c-4bf7-95bb-c0a14cb14b23",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 51
}
},
"source": [
"df_manager = df[df['dominant_topic']==3]\n",
"print(len(df_manager))\n",
"df_manager.topic_prob.mean()"
],
"execution_count": 19,
"outputs": [
{
"output_type": "stream",
"text": [
"326\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"0.13591641734432516"
]
},
"metadata": {
"tags": []
},
"execution_count": 19
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "spsGGNqRgie8",
"outputId": "8c41777a-84be-4258-e939-2b0d6dc5481d",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 128
}
},
"source": [
"df_manager_ = df_manager[df_manager['topic_prob']>0.14]\n",
"print(len(df_manager_))\n",
"df_manager_.head(2)"
],
"execution_count": 20,
"outputs": [
{
"output_type": "stream",
"text": [
"131\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>url</th>\n",
" <th>username</th>\n",
" <th>title</th>\n",
" <th>about</th>\n",
" <th>dominant_topic</th>\n",
" <th>topic_prob</th>\n",
" <th>keywords</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>96</th>\n",
" <td>https://www.linkedin.com/in/kievewang</td>\n",
" <td>kievewang</td>\n",
" <td>Sr. Executive Assistant</td>\n",
" <td>Skills: Customer Service, Technical/Customer S...</td>\n",
" <td>3</td>\n",
" <td>0.181637</td>\n",
" <td>['management', 'customer', 'manage', 'process'...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>228</th>\n",
" <td>https://www.linkedin.com/in/imnikhilbhaskaran/</td>\n",
" <td>imnikhilbhaskaran</td>\n",
" <td>Associate Director, Customer Success at Icertis</td>\n",
" <td>I am passionate about delivering world class T...</td>\n",
" <td>3</td>\n",
" <td>0.156695</td>\n",
" <td>['management', 'customer', 'manage', 'process'...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" url ... keywords\n",
"96 https://www.linkedin.com/in/kievewang ... ['management', 'customer', 'manage', 'process'...\n",
"228 https://www.linkedin.com/in/imnikhilbhaskaran/ ... ['management', 'customer', 'manage', 'process'...\n",
"\n",
"[2 rows x 7 columns]"
]
},
"metadata": {
"tags": []
},
"execution_count": 20
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "EiJec0rlIoa7"
},
"source": [
"# **HR Profiles**"
]
},
{
"cell_type": "code",
"metadata": {
"id": "3vVZRFWag9HS",
"outputId": "074ecbc4-3428-441c-a086-e69c74ba3719",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 162
}
},
"source": [
"df_hr = df[df['dominant_topic']==4]\n",
"print(len(df_hr))\n",
"df_hr.head(2)"
],
"execution_count": 21,
"outputs": [
{
"output_type": "stream",
"text": [
"309\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>url</th>\n",
" <th>username</th>\n",
" <th>title</th>\n",
" <th>about</th>\n",
" <th>dominant_topic</th>\n",
" <th>topic_prob</th>\n",
" <th>keywords</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>178</th>\n",
" <td>https://www.linkedin.com/in/jonathan-parisot-1...</td>\n",
" <td>jonathan-parisot-10054625</td>\n",
" <td>Co-Founder & CEO at Actiondesk (YC S19)</td>\n",
" <td>Building Actiondesk, a spreadsheet software na...</td>\n",
" <td>4</td>\n",
" <td>0.087037</td>\n",
" <td>['team', 'build', 'lead', 'leadership', 'organ...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>298</th>\n",
" <td>https://www.linkedin.com/in/meghan-herring-049...</td>\n",
" <td>meghan-herring-0491635</td>\n",
" <td>Senior Technical Recruiter</td>\n",
" <td>SENIOR TECHNICAL RECRUITER / HUMAN RESOURCES L...</td>\n",
" <td>4</td>\n",
" <td>0.140461</td>\n",
" <td>['team', 'build', 'lead', 'leadership', 'organ...</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" url ... keywords\n",
"178 https://www.linkedin.com/in/jonathan-parisot-1... ... ['team', 'build', 'lead', 'leadership', 'organ...\n",
"298 https://www.linkedin.com/in/meghan-herring-049... ... ['team', 'build', 'lead', 'leadership', 'organ...\n",
"\n",
"[2 rows x 7 columns]"
]
},
"metadata": {
"tags": []
},
"execution_count": 21
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ppfPSV0ZU5gI"
},
"source": [
"**Marking rows for about section description with keywords of HR**"
]
},
{
"cell_type": "code",
"metadata": {
"id": "TKB9De2SJU9_",
"outputId": "4c824920-24b8-46f6-b71d-1d781f8856a9",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 119
}
},
"source": [
"hr_word = set(['hr ', ' hr' 'human resource', 'recruit'])\n",
"df_hr['checking_hr_word'] = df_hr.about.apply(lambda x: ['true' for word in hr_word if word in x.lower() ])\n",
"# df_hr.head(2)"
],
"execution_count": 22,
"outputs": [
{
"output_type": "stream",
"text": [
"/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py:2: 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",
" \n"
],
"name": "stderr"
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "OoJYNcQ_VQqT"
},
"source": [
"**collecting dataframe row_index where an about section has HR related words**"
]
},
{
"cell_type": "code",
"metadata": {
"id": "xq_yj5BQKHc3"
},
"source": [
"row_index_with_hr_words = []\n",
"for row in df_hr.index:\n",
" if len(df_hr['checking_hr_word'][row])!=0:\n",
" row_index_with_hr_words.append(row)\n",
" # print(row,'\\n')"
],
"execution_count": 23,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "gxcBB06-VrIm"
},
"source": [
"**Collecting final Rows with HR related about section**"
]
},
{
"cell_type": "code",
"metadata": {
"id": "Gbumj-5cM6WW"
},
"source": [
"final_df_hr_list = []\n",
"for index in row_index_with_hr_words:\n",
" url = df_hr.url[index]\n",
" username = df_hr.username[index]\n",
" title = df_hr.title[index]\n",
" about = df_hr.about[index]\n",
" dominant_topic = df_hr.dominant_topic[index]\n",
" topic_prob = df_hr.topic_prob[index]\n",
" keywords = df_hr.keywords[index]\n",
" dic = {'url':url,'username':username,'title':title,'about':about,'dominant_topic':dominant_topic,'topic_prob':topic_prob,'keywords':keywords}\n",
" final_df_hr_list.append(dic)\n",
" \n",
"df_hr_ = pd.DataFrame(final_df_hr_list)"
],
"execution_count": 24,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "uAEIOZ8vSyf-",
"outputId": "a2968841-fab5-410d-f1d5-83dbbc0f4699",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
}
},
"source": [
"df_hr_ = df_hr_[df_hr_['topic_prob']>0.15]\n",
"len(df_hr_)\n"
],
"execution_count": 25,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"85"
]
},
"metadata": {
"tags": []
},
"execution_count": 25
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "P7XRsRqbXSPJ"
},
"source": [
"# **Final Data Preparation for Statistical Model Classification**"
]
},
{
"cell_type": "code",
"metadata": {
"id": "wgxy8cf-XcKz"
},
"source": [
"df_final_data = pd.concat([df_marketing_,df_pm_,df_data_,df_sw_, df_entrepreneur_, df_investor_,df_manager_,df_business_,df_hr_],axis=0)"
],
"execution_count": 26,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "DpeZ3nGqYXRF",
"outputId": "ab0e544d-d912-4c3e-d45a-af4538a1828c",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 34
}
},
"source": [
"len(df_final_data)"
],
"execution_count": 27,
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"1365"
]
},
"metadata": {
"tags": []
},
"execution_count": 27
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "sm9j-OXtcPWx"
},
"source": [
"# **Export final data frame**"
]
},
{
"cell_type": "code",
"metadata": {
"id": "YII0kg0Hcs3W"
},
"source": [
"df_final_data.to_csv('/content/drive/My Drive/NLP/with_swaraj/Data/data_for_statistical_classification_1.csv')"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "yZywI1nndJes"
},
"source": [
""
],
"execution_count": null,
"outputs": []
}
]
}