Davis Cup Qualifiers stats & predictions

Detailed Player Profiles

Elevate your understanding of the game by exploring detailed profiles of key players participating in today's qualifiers.

• Jane Doe - Rising Star from Canada

  Jane Doe has quickly risen through the ranks with her aggressive playing style and remarkable consistency. Watch out for her powerful serves and strategic gameplay as she represents Canada in this year's qualifiers. Average Serve Speed: Overclocked at an impressive speed reaching up to km/h.
  Highest Ranking Achieved: World No.45 in singles.
  Past Achievements: Winner of multiple junior Grand Slam titles.

• Alex Smith - Veteran Champion from Spain

  Alex Smith brings years of experience to his team, having competed in numerous international tournaments. Known for his tactical acumen and resilience under pressure, he remains a formidable opponent. Total Davis Cup Appearances: Over decades-long career.
  Famous Matches: Notable victories against top-tier players.
  Rewarding Comebacks: Overcame injuries to secure crucial wins.

  vivimadhu/CSE-5320<|file_sep|>/assignment1/final_project/README.md # CSE5320 # Final Project # Movie Recommender System ## Group Members: 1. Sowmya Nallamothu 2. Priyanka Palakurthi 3. Shriya Sridharan ## Introduction A movie recommender system is an application that helps users discover movies based on their preferences.The idea behind any recommender system is that if two users agree on one issue then they are likely to agree on others as well. There are two main types of recommender systems: 1) **Content Based Filtering**: Content-based filtering recommends items similar to what a user liked in the past based on item features. 2) **Collaborative Filtering**: Collaborative filtering uses ratings given by users on items or content that they have consumed before. ## Dataset used We used movielens dataset for building our recommender system. The dataset contains three files: 1) `ratings.csv` file contains information about user ratings given to movies. | userId | movieId | rating | timestamp | |--------|---------|--------|-----------| |1 |31 |2.5 |1260759144 | |1 |1029 |3 |1260759179 | 2) `movies.csv` file contains information about movies. |movieId | title | genres | |--------|-----------|------------------------| |1 |Toy Story (1995)|Adventure|Animation|Children's|Comedy| |2 |Jumanji (1995) |Adventure|Children's|Fantasy| The dataset can be downloaded from [here](https://grouplens.org/datasets/movielens/). ## Building Recommendation System ### Preprocessing Data The dataset had many missing values which were handled appropriately before building recommendation system. ### Splitting Data into Training & Testing Set The data was split into training set & testing set using random sampling technique. ### Building Recommendation System using Collaborative Filtering We built recommendation system using collaborative filtering using `surprise` library in python. #### Collaborative Filtering Model The model used was `SVD`. #### Evaluation Metrics We used RMSE (Root Mean Squared Error) metric to evaluate our model performance. #### Hyperparameter Tuning We did hyperparameter tuning using grid search approach. ## Results We got RMSE value as `0.8798` which shows that our model is performing well. ## Running code To run code follow these steps: 1) Clone this repository git clone https://github.com/shriyasridharan/CSE5320.git 2) Go inside `final_project` folder cd final_project/ 3) Run following command python main.py <|file_sep|># CSE5320 # Assignment-4 # Author : Priyanka Palakurthi import pandas as pd import numpy as np import matplotlib.pyplot as plt from sklearn.feature_extraction.text import TfidfVectorizer from sklearn.metrics.pairwise import cosine_similarity def main(): # load data df = pd.read_csv('movies.csv', encoding='latin-1') # create tf-idf matrix tfidf = TfidfVectorizer(stop_words='english') tfidf_matrix = tfidf.fit_transform(df['overview']) # compute cosine similarity similarity = cosine_similarity(tfidf_matrix) # index mapping indices = pd.Series(df.index, index=df['title']).drop_duplicates() # function that takes in movie title as input & outputs most similar movies def get_recommendations(title): idx = indices[title] sim_scores = list(enumerate(similarity[idx])) sim_scores = sorted(sim_scores, key=lambda x: x[1], reverse=True) sim_scores = sim_scores[1:11] movie_indices = [i[0] for i in sim_scores] return df['title'].iloc[movie_indices] # user input title = input("Enter Movie Title : ") print(get_recommendations(title)) if __name__ == "__main__": main() <|repo_name|>vivimadhu/CSE-5320<|file_sep|>/assignment2/README.md # CSE5320 # Assignment-2 # Author : Priyanka Palakurthi ## Steps #### Step-1 : Data Collection I collected data from IMDB website. #### Step-2 : Data Cleaning I cleaned data by removing missing values & unwanted columns. #### Step-3 : Data Visualization I plotted graphs showing relationship between budget & revenue. #### Step-4 : Data Preprocessing I performed one hot encoding on genres column. #### Step-5 : Splitting Data into Train & Test Sets I split data into train set & test set using random sampling technique. #### Step-6 : Building Model I built model using linear regression algorithm. #### Step-7 : Evaluating Model I evaluated model performance using RMSE metric. ### Results The RMSE value obtained was `0.974`. It means that model performance is good. ### Running Code To run code follow these steps: 1) Clone this repository git clone https://github.com/shriyasridharan/CSE5320.git 2) Go inside `assignment2` folder cd assignment2/ 3) Run following command python main.py <|file_sep|># CSE5320 # Assignment-4 # Author : Priyanka Palakurthi import pandas as pd import numpy as np from sklearn.metrics.pairwise import cosine_similarity def main(): # load data df = pd.read_csv('movies.csv', encoding='latin-1') # create feature vector features = ['keywords', 'cast', 'genres', 'director'] features_vector = [] for i in range(len(df)): temp_list = [] for feature in features: try: feature_list = df[feature][i].split('|') except: feature_list = [] temp_list.extend(feature_list) features_vector.append(temp_list) df['features'] = features_vector # compute cosine similarity similarity_matrix = cosine_similarity(df['features'], df['features']) # index mapping indices = pd.Series(df.index, index=df['title']).drop_duplicates() # function that takes in movie title as input & outputs most similar movies def get_recommendations(title): idx = indices[title] sim_scores = list(enumerate(similarity_matrix[idx])) sim_scores = sorted(sim_scores, key=lambda x: x[1], reverse=True) sim_scores = sim_scores[1:11] movie_indices = [i[0] for i in sim_scores] return df['title'].iloc[movie_indices] # user input title = input("Enter Movie Title : ") print(get_recommendations(title)) if __name__ == "__main__": main() <|repo_name|>vivimadhu/CSE-5320<|file_sep|>/assignment1/README.md # CSE5320 # Assignment-1 ## Part A - Sentiment Analysis ### Author : Sowmya Nallamothu This project involves implementation of Sentiment Analysis using Naive Bayes Classifier. Sentiment Analysis is also known as opinion mining which involves determining whether a piece of text is positive or negative. Naive Bayes classifier is based on Bayes Theorem which states that probability of an event occurring given another event has already occurred is equal to probability of event occurring times probability second event occurring given first event has already occurred divided by probability second event occurring. ### Steps Involved: * **Step -1** - Load data. * **Step -2** - Preprocess data. * **Step -3** - Extract features from text. * **Step -4** - Build model. * **Step -5** - Evaluate model performance. ### Results: We got accuracy score as `90%` which means our model is performing well. ### Running Code: To run code follow these steps: 1) Clone this repository git clone https://github.com/shriyasridharan/CSE5320.git 2) Go inside `assignment1` folder cd assignment1/ 3) Go inside partA folder cd partA/ 4) Run following command python main.py ## Part B - Text Classification ### Author : Shriya Sridharan This project involves implementation of Text Classification using KNN algorithm. Text classification refers to process of classifying text documents into predefined categories based on its content. KNN algorithm finds k nearest neighbors based on distance metric & assigns class label based on majority voting. ### Steps Involved: * **Step -1** - Load data. * **Step -2** - Preprocess data. * **Step -3** - Extract features from text. * **Step -4** - Build model. * **Step -5** - Evaluate model performance. * **Step -6** - Visualize confusion matrix. ### Results: We got accuracy score as `90%` which means our model is performing well. ### Running Code: To run code follow these steps: 1) Clone this repository git clone https://github.com/shriyasridharan/CSE5320.git 2) Go inside `assignment1` folder cd assignment1/ 3) Go inside partB folder cd partB/ 4) Run following command python main.py <|file_sep|># CSE5320 # Final Project ## Group Members: 1. Sowmya Nallamothu 2. Priyanka Palakurthi 3. Shriya Sridharan ## Steps Involved: #### Step-1 : Preprocessing Data We preprocessed data by removing missing values & dropping unwanted columns. #### Step-2 : Splitting Data into Training & Testing Set We split data into training set & testing set using random sampling technique. #### Step-3 : Building Recommendation System using Collaborative Filtering We built recommendation system using collaborative filtering using `surprise` library in python. ##### Collaborative Filtering Model The model used was `SVD`. ##### Evaluation Metrics We used RMSE (Root Mean Squared Error) metric to evaluate our model performance. ##### Hyperparameter Tuning We did hyperparameter tuning using grid search approach. ## Results We got RMSE value as `0.8798` which shows that our model is performing well.